WO2023276410A1 - Sludge treatment management apparatus and sludge treatment management method - Google Patents

Sludge treatment management apparatus and sludge treatment management method Download PDF

Info

Publication number
WO2023276410A1
WO2023276410A1 PCT/JP2022/017790 JP2022017790W WO2023276410A1 WO 2023276410 A1 WO2023276410 A1 WO 2023276410A1 JP 2022017790 W JP2022017790 W JP 2022017790W WO 2023276410 A1 WO2023276410 A1 WO 2023276410A1
Authority
WO
WIPO (PCT)
Prior art keywords
sludge
sludge treatment
management device
cost
operating
Prior art date
Application number
PCT/JP2022/017790
Other languages
French (fr)
Japanese (ja)
Inventor
浩樹 宮川
光太郎 北村
万規子 宇田川
卓也 安東
健之 黒津
利典 三木
孝道 大久保
庄司 斎藤
Original Assignee
株式会社日立製作所
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 株式会社日立製作所 filed Critical 株式会社日立製作所
Publication of WO2023276410A1 publication Critical patent/WO2023276410A1/en

Links

Images

Classifications

    • C—CHEMISTRY; METALLURGY
    • C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F11/00—Treatment of sludge; Devices therefor
    • C—CHEMISTRY; METALLURGY
    • C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F11/00—Treatment of sludge; Devices therefor
    • C02F11/12—Treatment of sludge; Devices therefor by de-watering, drying or thickening
    • C02F11/121—Treatment of sludge; Devices therefor by de-watering, drying or thickening by mechanical de-watering
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply

Definitions

  • the present invention relates to a sludge treatment management device and a sludge treatment management method.
  • Patent Document 1 discloses an operation support device that supports the operation of a sewage treatment plant.
  • This operation support device refers to a storage unit that stores a database of sewage treatment equipment for each sewage treatment plant and a predetermined numerical model, inflow conditions to the sewage treatment plant, operating conditions of the sewage treatment plant, and data in the storage unit.
  • Effluent water quality calculation means for calculating a predicted value of effluent water quality from the sewage treatment plant in a predetermined period, an operation cost calculation means for calculating a predicted value of operation cost for sewage treatment at the sewage treatment plant based on the operating conditions, and effluent quality Calculation of the expected discharge pollutant load at the sewage treatment plant and an indicator of the effect of purchasing or selling the allowance, based on the forecasted value, the forecasted operating cost, and the allowance conditions, including the allowance and the purchase or sale price of this allowance. and processing effect calculation means for calculating a frame transaction effect index value.
  • the driving support device of Patent Document 1 is a technology related to water treatment, and does not consider driving support for sludge treatment at all.
  • Sludge generated in the process of sewage treatment and wastewater treatment is carried out as industrial waste through dehydration treatment to reduce volume and volume, and is reused as landfill treatment, fuel and resources.
  • Transportation costs and collection costs are generally determined by volume unit price, and in order to reduce the cost, it is desirable to reduce the ratio of water to solid content, that is, the water content, as much as possible in the dehydration process. be
  • the purpose of the present invention is to present appropriate operating conditions for a sludge treatment system.
  • a sludge treatment management device which is one aspect of the invention disclosed in the present application, has a processor that executes a program and a storage device that stores the program, and is accessible to a sludge treatment system that treats sludge.
  • a management device wherein the processor, for each of a plurality of operating conditions for operating the sludge treatment system, calculates a dehydration cost for dewatering the sludge in the sludge treatment system and the sludge treatment system based on the operating conditions.
  • FIG. 1 is an explanatory diagram showing a system configuration example of a sludge treatment management system.
  • FIG. 2 is a block diagram illustrating an example hardware configuration of a management server.
  • FIG. 3 is an explanatory diagram showing an example of the unit price management table.
  • FIG. 4 is an explanatory diagram showing an example of a flocculant table.
  • FIG. 5 is an explanatory diagram showing an example of a constraint condition table.
  • FIG. 6 is an explanatory diagram showing an example of an actually measured inflow sludge properties table.
  • FIG. 7 is an explanatory diagram showing an example of a flocculation condition table.
  • FIG. 8 is an explanatory diagram showing an example of an actually measured dehydrated sludge properties table.
  • FIG. 1 is an explanatory diagram showing a system configuration example of a sludge treatment management system.
  • FIG. 2 is a block diagram illustrating an example hardware configuration of a management server.
  • FIG. 3 is an explanatory diagram showing
  • FIG. 9 is an explanatory diagram showing an example of a measured dehydrated sludge amount table.
  • FIG. 10 is an explanatory diagram showing an example of a sludge injection pump actual measurement table.
  • FIG. 11 is an explanatory diagram showing an example of a flocculation tank actual measurement table.
  • FIG. 12 is an explanatory diagram showing an example of a dehydrator actual measurement table.
  • FIG. 13 is an explanatory diagram showing an example of a dehydrated sludge transfer pump actual measurement table.
  • FIG. 14 is an explanatory diagram showing an example of an operator actual measurement table.
  • FIG. 15 is an explanatory diagram of an example of a maintenance management table.
  • FIG. 16 is an explanatory diagram showing an example of a sludge inflow/outflow balance table.
  • FIG. 17 is an explanatory diagram showing an example of a dehydrated sludge inflow/outflow balance table.
  • FIG. 18 is a flow chart showing an example of a sludge treatment planning processing procedure by the management server.
  • FIG. 19 is a graph showing the relationship between operating conditions and total cost.
  • FIG. 1 is an explanatory diagram showing a system configuration example of a sludge treatment management system.
  • the sludge treatment management system 100 has a management server 101 and a sludge treatment system 102 .
  • the management server 101 and the sludge treatment system 102 are communicably connected via a network 103 such as the Internet, LAN (Local Area Network), WAN (Wide Area Network).
  • the management server 101 is a computer that manages the inside of the sludge treatment system 102 .
  • the sludge treatment system 102 is a system for treating sludge 120 that has undergone water treatment.
  • the sludge treatment system 102 has a sludge storage tank 121.
  • the sludge storage tank 121 stores sludge 120 that has undergone water treatment.
  • the water level gauge 122 detects the water level of the sludge 120 stored in the sludge storage tank 121 .
  • the detected sensor data is transmitted to the management server 101 .
  • a water temperature sensor 123 detects the water temperature of the sludge 120 stored in the sludge storage tank 121 .
  • the detected sensor data is transmitted to the management server 101 .
  • the flow meter 124 detects the flow rate [m 3 /h] of the sludge 120 flowing from the water treatment system, which is the upstream process.
  • the detected sensor data is transmitted to the management server 101 .
  • the sludge injection pump 130 injects the sludge 120 in the sludge storage tank 121 and discharges it into the floc formation tank 150 .
  • a flow meter 131 detects the flow rate of the sludge 120 discharged from the sludge injection pump 130 .
  • the detected sensor data is transmitted to the management server 101 .
  • the pH sensor 132 detects the hydrogen ion concentration of the sludge 120 discharged from the sludge injection pump 130 .
  • the detected sensor data is transmitted to the management server 101 .
  • the electric conductivity sensor 133 detects the electric conductivity of the sludge 120 discharged from the sludge injection pump 130. The detected sensor data is transmitted to the management server 101 .
  • the sludge concentration sensor 134 detects the sludge concentration of the sludge 120 discharged from the sludge injection pump 130 .
  • the detected sensor data is transmitted to the management server 101 .
  • the chemical pump 140 injects the coagulant into the sludge 120.
  • a flow meter 141 detects the flow rate of the coagulant injected into the sludge 120 .
  • the detected sensor data is transmitted to the management server 101 .
  • the floc formation tank 150 sucks the sludge 120 to form flocs, and discharges the formed flocs to the dehydrator 160 .
  • the floc forming tank 150 has a rapid agitator 151 , a slow agitator 152 , motors 153 and 154 , a pressure gauge 155 and a floc sensor 156 .
  • the rapid agitator 151 rapidly agitates the sludge in the flocculation tank 150 .
  • the slow agitator 152 agitates the sludge 120 in the flocculation tank 150 at an agitation speed slower than the agitation speed of the rapid agitator 151 .
  • the motor 153 rotates the rapid stirrer 151 and detects the rotation speed of the rapid stirrer 151 .
  • the detected sensor data is transmitted to the management server 101 .
  • the motor 154 rotates the slow stirrer 152 and detects the rotation speed of the slow stirrer 152 .
  • the detected sensor data is transmitted to the management server 101 .
  • the pressure gauge 155 detects the discharge pressure for discharging the formed flocs to the dehydrator 160.
  • the detected sensor data is transmitted to the management server 101 .
  • the floc sensor 156 detects the diameter [mm] of the flocs as the properties of the flocs formed by photographing the flocs in the floc forming tank 150 .
  • the floc diameter [mm] for example, the median value of the floc diameter distribution is adopted.
  • the detected sensor data is transmitted to the management server 101 .
  • the dehydrator 160 dewaters the flocs from the flocculation tank 150, separates the desorbed liquid 167A from the flocs, and discharges it to the dehydrated sludge hopper 180 as dehydrated sludge 167B.
  • the dehydrator 160 has position sensors 161 to 164 , a back pressure applying plate 165 and a dehydrator driver 166 .
  • the position sensors 161 to 164 detect the position of the back pressure applying plate 165 .
  • the detected sensor data is transmitted to the management server 101 .
  • the back pressure imparting plate 165 is a mechanism for controlling the back pressure to the dehydrator 160.
  • the back pressure increases when the back pressure applying plate 165 approaches the interior of the dehydrator 160, and decreases when it separates.
  • the moisture content sensor 168 detects the moisture content of the dehydrated sludge 167B from the dehydrator 160.
  • the detected sensor data is transmitted to the management server 101 .
  • the flow meter 169 detects the flow rate of the dehydrated sludge 167B from the dehydrator 160.
  • the detected sensor data is transmitted to the management server 101 .
  • the dehydrated sludge transfer pump 170 sucks the dehydrated sludge 167B from the dehydrator 160 and discharges it to the dehydrated sludge hopper 180.
  • the pressure gauge 171 detects the discharge pressure at which the dehydrated sludge transfer pump 170 discharges the dehydrated sludge 167B to the dehydrated sludge hopper 180.
  • the detected sensor data is transmitted to the management server 101 .
  • the dehydrated sludge hopper 180 stores the dehydrated sludge 167B from the dehydrator 160.
  • the weight sensor 181 detects the weight of the dehydrated sludge 167B stored in the dehydrated sludge hopper 180.
  • FIG. The detected sensor data is transmitted to the management server 101 .
  • the flow meter 182 detects the flow rate of the dehydrated sludge 167B discharged from the dehydrated sludge hopper 180.
  • FIG. The detected sensor data is transmitted to the management server 101 .
  • FIG. 2 is a block diagram showing a hardware configuration example of the management server 101.
  • the management server 101 has a processor 201 , a storage device 202 , an input device 203 , an output device 204 and a communication interface (communication IF) 205 .
  • Processor 201 , storage device 202 , input device 203 , output device 204 and communication IF 205 are connected by bus 206 .
  • a processor 201 controls the management server 101 .
  • a storage device 202 serves as a work area for the processor 201 .
  • the storage device 202 is a non-temporary or temporary recording medium that stores various programs and data.
  • Examples of the storage device 202 include ROM (Read Only Memory), RAM (Random Access Memory), HDD (Hard Disk Drive), and flash memory.
  • the input device 203 inputs data.
  • Input devices 203 include, for example, a keyboard, mouse, touch panel, numeric keypad, scanner, and microphone.
  • the output device 204 outputs data.
  • Output devices 204 include, for example, displays, printers, and speakers.
  • Communication IF 205 connects to network 103 to transmit and receive data.
  • FIG. 3 to 17 configuration examples of a group of tables that can be read and written by the management server 101 will be described with reference to FIGS. 3 to 17.
  • FIG. These table groups are stored in the storage device 202, for example.
  • the fixed value (however, it can be set arbitrarily)
  • Some fields e.g. flocculation tank capacity, unit price of electricity, etc.) can only be set to values that can be changed, while others (e.g., water temperature, sludge concentration, etc.) can only be set to actual values that change over time.
  • There are fields that can be both values and actual values eg flocculant dosage, rapid stirrer speed, etc.).
  • fields that can be either fixed values or measured values if fixed values are set, calculation efficiency can be improved and the amount of space used in the storage device 202 can be reduced. It is possible to improve the accuracy of the result. Therefore, in the table group shown below, fields that can be either fixed values or measured values will be described using either the fixed values or the measured values, but the other may be set.
  • FIG. 3 is an explanatory diagram showing an example of the unit price management table.
  • the unit price management table 300 is a table for managing various unit prices.
  • the unit price management table 300 has, as fields, a personnel cost unit price 301 , a transportation cost unit price 302 , a pick-up cost unit price 303 , a maintenance unit price 304 , and an electricity bill unit price 305 .
  • the labor cost unit price 301 is the labor unit price per hour per operator engaged in the sludge treatment system 102 .
  • the transportation cost unit price 302 is the unit cost of transporting the dehydrated sludge 167B to the outside of the sludge treatment system 102 .
  • the collection cost unit price 303 is the unit cost to be paid to the collection destination of the transported dehydrated sludge 167B.
  • the maintenance unit price 304 is the unit price of the cost required for maintenance of the sludge treatment system 102 .
  • the electricity bill unit price 305 is the unit price of the electricity bill in the sludge treatment system 102 .
  • FIG. 4 is an explanatory diagram showing an example of a flocculant table.
  • the flocculant table 400 is a table that defines information about flocculants.
  • the flocculant table 400 has, as fields, a drug unit price 401 , a stock solution concentration 402 , and a flocculant injection amount 403 .
  • the chemical unit price 401 is the price per kilogram of the chemical that constitutes the coagulant.
  • Stock concentration 402 is the concentration of the chemical stock solution per liter of water.
  • the coagulant injection amount 403 is the amount of coagulant injected by the chemical pump 140 per second.
  • the values of the chemical unit price 401, the stock solution concentration 402, and the coagulant injection amount 403 can be set arbitrarily.
  • the coagulant injection amount 403 may be calculated by the management server 101 using the following formula (1) at predetermined time intervals.
  • Flocculant injection amount [L/s] number of chemical pump strokes [times/s] x chemical pump stroke length [L/times] (1)
  • FIG. 5 is an explanatory diagram showing an example of a constraint condition table.
  • the constraint table 500 is a table that defines constraints. Constraints are conditions to be complied with when calculating the total cost of the sludge treatment system 102 .
  • Constraint condition table 500 includes, as fields, maximum working hours per person 501, upper limit of drive current 502, upper limit of inflow pressure 503, upper limit of outflow pressure 504, sludge storage tank capacity 505, maximum dewatered sludge hopper. It has an allowable storage weight 506 and a dewatered sludge scheduled discharge time 507 .
  • the maximum working hours per person 501 is the maximum working hours per operator engaged in the sludge treatment system 102 .
  • the driver current upper limit value 502 is the upper limit value of the drive current of the dehydrator driver.
  • the inflow pressure upper limit 503 is the upper limit of the inflow pressure of the dehydrated sludge transfer pump 170 .
  • the outflow pressure upper limit value 504 is the upper limit value of the outflow pressure of the dehydrated sludge transfer pump 170 .
  • the sludge storage tank capacity 505 is a capacity that allows the sludge 120 to be stored in the sludge storage tank 121 .
  • the dewatered sludge hopper maximum permissible storage weight 506 is the maximum permissible weight of the dehydrated sludge hopper 180 that can store the dehydrated sludge 167B.
  • the scheduled time 507 for carrying out the dewatered sludge is the scheduled time for carrying out the dehydrated sludge 167B from the sludge treatment system 102 .
  • FIG. 6 is an explanatory diagram showing an example of an actually measured inflow sludge properties table.
  • the measured inflow sludge properties table 600 is a table that records measured values relating to properties of sludge that has flowed into the sludge treatment system 102 .
  • the actually measured inflow sludge property table 600 includes, as fields, operation date and time 601, upstream process operating conditions 602, water temperature 603, pH 604, electrical conductivity 605, sludge concentration 606, moisture content 607, weather 608, It has seasons 609 and measured formation floc properties 610 .
  • the date and time of operation 601 is the date and time when the sludge treatment system 102 was operated.
  • the values excluding the operation date and time 601 of each entry in the actually measured inflow sludge property table 600 are the measured values at the time interval from the operation date and time 601 to the operation date and time 601 of the next entry. If multiple measured values are obtained during the time interval, the value of each entry is a representative value of the multiple measured values.
  • the representative value may be the average value, median value, maximum value, minimum value, or mode value of a plurality of measured values (the same applies to subsequent tables). In the following description, representative values are also referred to as “actual values”.
  • the upstream process operating conditions 602 are operating conditions for water treatment, which is the upstream process of the sludge treatment system 102 .
  • the upstream process operating conditions 602 are representative values of parameters that are estimated to affect the properties of inflow sludge in water treatment at the operating date and time 601. For example, aeration air volume, sludge return rate, MLSS (activated sludge There is a concentration of suspended solids (Mixed Liquor Suspended Solids).
  • the water temperature 603 is the measured value of the temperature of the sludge 120 flowing through the sludge treatment system 102 detected by the water temperature sensor 123 .
  • pH 604 is the measured hydrogen ion concentration of the sludge 120 flowing through the sludge treatment system 102 detected by the pH sensor 132 .
  • the electrical conductivity 605 is the measured electrical conductivity of the sludge 120 flowing into the sludge treatment system 102 detected by the electrical conductivity sensor 133 .
  • the sludge concentration 606 is the measured value of the concentration of the sludge 120 flowing into the sludge treatment system 102 detected by the sludge concentration sensor 134 .
  • the moisture content 607 is an actual measurement value of the percentage of moisture contained in the dehydrated sludge 167B detected by the moisture content sensor 168 .
  • the weather 608 is the weather conditions at the driving date 601, such as sunny, cloudy, rainy, and snowy.
  • a season 609 is a section of one year such as spring, summer, vacancy, and winter divided by the weather.
  • the measured formed floc property 610 is the measured value of the flow rate of the sludge 120 detected by the flow meter 131 at the operating date and time 601 .
  • FIG. 7 is an explanatory diagram showing an example of a flocculation condition table.
  • the flocculation condition table 700 is a table that defines flocculation conditions.
  • the flocculation condition table 700 includes, as fields, an operation date and time 601, a coagulant injection rate 701, a rapid stirrer rotation speed 702, a slow stirrer rotation speed 703, a flocculation tank capacity 704, and a processing amount per hour. 705 and .
  • the flocculation conditions are the conditions necessary for the dehydrator to form flocs. Defined by throughput 705 .
  • the flocculant injection rate 701, the rapid stirrer rotation speed 702, the slow stirrer rotation speed 703, and the throughput per hour 705 may be defined as either fixed values or measured values, but in FIG. will be described as an example.
  • the coagulant injection rate 701 is the rate at which the coagulant is injected at the operating date and time.
  • the coagulant injection rate 701 is calculated based on the stock solution concentration 402, the coagulant injection amount 403, and the sludge flow rate [m 3 /h].
  • the sludge flow rate [m 3 /h] is the flow rate of sludge flowing into the flocculation tank 150, and is detected by the flow meter 131, for example.
  • the coagulant injection rate 701 is calculated by the following formula (2).
  • Flocculant injection rate [mg/L] Stock solution concentration [mg/L] ⁇ flocculant injection amount [L/S] ⁇ sludge flow rate [m 3 /h] ⁇ unit conversion factor (2)
  • the rapid stirrer rotation speed 702 is the measured value of the rotation speed [rpm] of the rapid stirrer at the operating date and time 601 .
  • the slow stirrer rotation speed 703 is the measured value of the rotation speed [rpm] of the slow stirrer at the operating date and time 601 .
  • the flocculation tank capacity 704 is a fixed value indicating the capacity of the flocculation tank 150 .
  • the throughput per hour 705 is the flow rate of sludge flowing into the flocculation tank 150, that is, the sludge flow rate described above, and is detected by the flow meter 131, for example. Further, the management server 101 may calculate the processing amount 705 per hour by the following formula (3) using the rotation speed of the dehydrator driving machine.
  • the dehydrator driver rotation speed is the rotation speed of the dehydrator driver 166 and is detected by the dehydrator driver 166 .
  • the rotation speed of the dehydrator driving machine may be a fixed value or an actually measured value.
  • the dehydrator characteristic factor may be any value.
  • the management server 101 uses machine learning based on the measured value of the dehydrator driving machine rotation speed detected from the dehydrator driving machine 166 and the measured value of the sludge flow rate [m 3 /h] detected from the flow meter 131.
  • a regression equation may be generated and the dehydrator characteristic coefficient in the regression equation may be applied to the above equation (3).
  • the management server 101 also uses the actually measured inflow sludge property table 600 and the floc formation condition table 700 to generate a function f1 for predicting the formed floc property [mm] (see formula (4) below).
  • the inflow sludge property of the above formula (4) is, for example, the upstream process operating conditions 602, water temperature 603, pH 604, electrical conductivity 605, sludge concentration in the actually measured inflow sludge property table 600 measured a predetermined time before the operation date and time 601. 606, moisture content 607, weather 608, and season 609.
  • the management server 101 inputs the actually measured formed floc property 610 for each operating date and time 601 to the left side of the above equation (4) as correct data, and inputs the inflow sludge properties and Floc formation conditions (coagulant injection rate 701 to processing amount per hour 705) are input as learning data, and a function f1 is generated as a regression equation by machine learning.
  • FIG. 8 is an explanatory diagram showing an example of an actually measured dehydrated sludge properties table.
  • the measured dewatered sludge property table 800 is a table for recording actual measurement values relating to the properties of the dehydrated sludge 167B dewatered in the sludge treatment system 102 .
  • the measured dehydrated sludge property table 800 has, as fields, an operation date 601, a measured formed floc property 610, a dehydrator operating condition 801, and a measured dehydrated sludge property 802.
  • the dehydrator operating conditions 801 are conditions necessary for the operation of the dehydrator, and specifically, for example, the dehydrator driving machine actually measured rotational speed 811, the actually measured press-in pressure 812, and the actually measured applied back pressure level 813. have.
  • the dehydrator driving machine actual rotation speed 811 is the actual measurement value of the rotation speed of the dehydrator driving machine at the operating date and time 601 .
  • the measured injection pressure 812 is the measured value of the pressure at which the sludge is injected into the dehydrator at the operation date and time 601, and is detected by the pressure gauge 155.
  • the measured applied back pressure level 813 is the position of the back pressure applying plate 165 at the operation date and time 601, and is detected by the position sensors 161-164.
  • the measured dehydrated sludge property 802 is a measured value indicating the property of the dewatered sludge 167B dehydrated by the dehydrator at the operation date and time 601. Specifically, for example, the water content detected by the water content sensor 168 at the operation date and time 601. It is obtained by multiplying 607 by a predetermined unit conversion factor.
  • the management server 101 uses the actually measured dehydrated sludge property table 800 to generate a function f2 for predicting the dehydrated sludge property [t/m 3 ] (see formula (5) below).
  • the management server 101 inputs the measured dehydrated sludge property 802 for each operating date and time 601 to the left side of the above equation (5) as correct data, and the right side of the above formula (5) to the measured formed floc property 610 for each operating date and time 601 and A dehydrator operating condition 801 is input as learning data, and a function f2 is generated as a regression equation by machine learning.
  • FIG. 9 is an explanatory diagram showing an example of a measured dehydrated sludge amount table.
  • the actually measured dewatered sludge amount table 900 is a table that records the actually measured value regarding the amount of the dehydrated sludge 167B dewatered in the sludge treatment system 102 .
  • the measured dehydrated sludge amount table 900 has an operation date 901 and a measured dewatered sludge amount 902 as fields.
  • the operation date 901 is the date when the sludge treatment system 102 was operated.
  • the actually measured dewatered sludge amount 902 is the actually measured value of the dehydrated sludge amount on the day of operation, and is detected by the weight sensor 181, for example.
  • the management server 101 uses the actually measured dehydrated sludge property table 800 and the actually measured dehydrated sludge amount table 900 to generate a function f3 for predicting the amount of dehydrated sludge [t/day] (see formula (6) below).
  • Amount of dewatered sludge [t/day] f3 (dewatered sludge properties [t/m 3 ], planned treatment target sludge volume [m 3 /day], dehydration process operating conditions) (6)
  • the management server 101 inputs the measured dewatered sludge amount 902 for each operation day 901 to the left side of the above equation (6) as correct data, and inputs the measured dewatered sludge property 802 for each operation day 901 to the right side of the equation (6).
  • a planned treatment target sludge amount and dehydration process operating conditions are input as learning data, and a function f3 is generated as a regression equation by machine learning.
  • the planned treatment target sludge amount [m 3 /day] on the right side of the above equation (6) is the amount of sludge 120 on the planned treatment target day.
  • the management server 101 calculates the amount of sludge 120 on the past planned processing target date using the following formula (7).
  • the processing amount per hour [m 3 /h] in the above formula (7) is the processing amount per hour 705 of the operation date and time 601, which is the past planned processing target day.
  • the sludge treatment end time is the end time of the sludge treatment on the past planned treatment day
  • the sludge treatment start time is the start time of the sludge treatment on the past planned treatment day.
  • Equation (7) above is applied to each of the past planned processing target days, but the actually measured value of the processing amount 705 per hour is stored in the flocculation condition table 700 for each operation date 601 . Therefore, the planned treatment target sludge volume [m 3 / day] for each planned treatment target day in the past is the representative value (average value, median value, maximum value, (either the minimum value or the most frequent value) multiplied by (sludge treatment end time - sludge treatment start time) for that day.
  • the dehydration process operating conditions of the above formula (6) are the dehydrator operating conditions 801 and flocculation conditions (coagulant injection rate 701, rapid stirrer rotation speed 702, slow stirrer rotation speed 703, flocculation tank capacity 704 and throughput per hour 705). Therefore, when the function f3 is generated, the management server 101 inputs the dehydration process operation conditions for the past planned processing target date into the above equation (6).
  • FIG. 10 is an explanatory diagram showing an example of a sludge injection pump actual measurement table.
  • the sludge injection pump actual measurement table 1000 is a table for recording actual measurement values regarding the sludge injection pump 130 .
  • the sludge injection pump actual measurement table has, as fields, an operation date and time 601, a sludge injection pump actual power consumption 1001, an actual injection pressure 812, and a sludge injection pump actual rotation speed 1002.
  • the sludge injection pump measured power consumption 1001 is the measured value of the power consumed by the sludge injection pump 130 at the operating date and time 601, and is detected by a power meter (not shown).
  • the actually measured rotation speed of the sludge injection pump 1002 is the actual measurement value of the rotation speed of the sludge injection pump 130 at the operating date and time 601 and is detected by the sludge injection pump 130 .
  • the management server 101 uses the sludge injection pump actual measurement table 1000 to generate a function f3 for predicting the sludge injection pump power consumption [kWh] (see formula (8) below).
  • the management server 101 inputs the measured power consumption 1001 of the sludge injection pump for each operation date and time 601 to the left side of the above equation (8) as correct data, and the measured injection pressure 812 for each operation date and time 601 to the right side of the above equation (8).
  • the actually measured number of rotations of the sludge injection pump 1002 and the operation time are input as learning data, and the function f4 is generated as a regression equation by machine learning.
  • the operating time is a time interval between consecutive values of the operating date and time 601 .
  • FIG. 11 is an explanatory diagram showing an example of a flocculation tank actual measurement table.
  • the flocculation tank actual measurement table 1100 is a table for recording the measured values regarding the flocculation tank 150 .
  • the floc formation tank actual measurement table 1100 includes, as fields, an operation date and time 601, a floc formation tank measured power consumption 1101, a rapid agitator actual measurement rotational speed 1102, a slow agitator actual rotational speed 1103, and an actual floc formation property 610. and have
  • the flocculation tank measured power consumption 1101 is the measured value of the power consumed by the flocculation tank 150 at the operating date and time 601, and is detected by a power meter (not shown).
  • the measured rapid stirrer rotation speed 1102 is the measured value of the rotation speed of the rapid stirrer 151 actually measured at the operating date and time 601 and is detected by the motor 153 .
  • the measured rotation speed of the slow stirrer 1103 is the rotation speed of the slow stirrer 152 actually measured at the operating date and time 601 , and is detected by the motor 154 .
  • the management server 101 uses the flocculation tank actual measurement table 1100 to generate a function f5 for predicting the power consumption [kWh] of the flocculation tank (see formula (9) below).
  • the management server 101 inputs the actual power consumption 1101 of the flocculation tank for each operating date and time 601 to the left side of the above equation (9) as correct data, and inputs the rapid stirrer power consumption for each operating date and time 601 to the right side of the above equation (9).
  • the actually measured number of rotations 1102, the actually measured number of rotations 1103 of the slow stirrer, and the operation time are inputted as learning data, and the function f5 is generated as a regression equation by machine learning.
  • the operating time is a time interval between consecutive values of the operating date and time 601 .
  • FIG. 12 is an explanatory diagram showing an example of a dehydrator actual measurement table.
  • the dehydrator actual measurement table 1200 is a table for recording actual measurement values regarding the dehydrator 160 .
  • the dehydrator actual measurement table 1200 includes, as fields, an operation date and time 601, a dehydrator actual power consumption 1201, a dehydrator drive actual rotation speed 811, an actual applied back pressure level 813, an actual formed floc property 610, a time per throughput 705;
  • the dehydrator measured power consumption 1201 is the measured value of the power consumed by the dehydrator at the operating date and time 601, and is detected by a power meter (not shown).
  • the management server 101 uses the dehydrator actual measurement table 1200 to generate a function f6 for predicting the dehydrator power consumption [kWh] (see formula (10) below).
  • Dehydrator power consumption [kWh] f6 (rotation speed of dehydrator driving machine, applied back pressure level, properties of flocs formed, throughput per hour, operating time) (10)
  • the management server 101 inputs the measured power consumption of the dehydrator 1201 for each operating date and time 601 to the left side of the above equation (10) as correct data, and inputs the measured dehydrator power consumption for each operating date and time 601 to the right side of the above equation (10).
  • Electric energy 1201, dehydrator drive actually measured rotation speed 811, actually measured applied back pressure level 813, actually measured formed floc property 610, throughput per hour 705 and operating time are input as learning data, and the function f6 is calculated by machine learning as a regression equation.
  • the operating time is a time interval between consecutive values of the operating date and time 601 .
  • FIG. 13 is an explanatory diagram showing an example of a dehydrated sludge transfer pump actual measurement table.
  • the dehydrated sludge transfer pump actual measurement table 1300 is a table for recording actual measurement values relating to the dehydrated sludge transfer pump 170 .
  • the dewatered sludge transfer pump actual measurement table 1300 includes, as fields, an operation date and time 601, a dewatered sludge transfer pump actually measured power consumption 1301, an actually measured dewatered sludge property 802, a dewatered sludge transfer pump actually measured rotation speed 1302, and an actually measured discharge pressure 1303. , has
  • the dehydrated sludge transfer pump measured power consumption 1301 is the measured value of the power consumed by the dehydrated sludge transfer pump 170 at the operating date and time 601, and is detected by a power meter (not shown).
  • the actual measurement rotation speed 1302 of the dehydrated sludge transfer pump is the actual measurement value of the rotation speed of the dewatered sludge transfer pump 170 at the operating date and time 601 and is detected by the dewatered sludge transfer pump 170 .
  • the measured discharge pressure 1303 is the measured value of the discharge pressure at which the dewatered sludge transfer pump 170 discharges the dehydrated sludge 167B to the dewatered sludge hopper 180 at the operating date and time 601, and is detected by the pressure gauge 171.
  • the management server 101 uses the dewatered sludge transfer pump actual measurement table 1300 to generate a function f7 for predicting the power consumption [kWh] of the dewatered sludge transfer pump (see formula (11) below).
  • the management server 101 inputs the measured power consumption 1301 of the dehydrated sludge transfer pump for each operation date and time 601 to the left side of the above equation (11) as correct data, and the measured dehydrated sludge for each operation date and time 601 to the right side of the above equation (11).
  • the properties 802, the actual rotation speed 1302 of the dehydrated sludge transfer pump, and the operation time are input as learning data, and the function f7 is generated as a regression equation by machine learning. It should be noted that the operating time is a time interval between consecutive values of the operating date and time 601 .
  • the management server 101 also uses the measured dehydrated sludge amount table 900 and the dehydrated sludge transfer pump actual measurement table 1300 to generate a function f9 for predicting the sludge transfer pump discharge pressure (see formula (12) below).
  • the management server 101 inputs the measured discharge pressure 1303 for each operation date and time 601 to the left side of the above equation (12) as correct data, and the right side of the above equation (12) for each operation date and time 601
  • the actually measured dewatered sludge property 802 and the actually measured dewatered The sludge amount 902 is input as learning data, and a function f8 is generated as a regression equation by machine learning.
  • FIG. 14 is an explanatory diagram showing an example of an operator actual measurement table.
  • the operator actual measurement table 1400 is a table for recording actual measurement values relating to operators.
  • the operator actual measurement table 1400 has, as fields, an operating date 901, a number of persons 1401, and an actual working hours 1402.
  • FIG. 14 is an explanatory diagram showing an example of an operator actual measurement table.
  • the operator actual measurement table 1400 is a table for recording actual measurement values relating to operators.
  • the operator actual measurement table 1400 has, as fields, an operating date 901, a number of persons 1401, and an actual working hours 1402.
  • the number of people 1401 is the number of operators engaged in the operation of the sludge treatment system 102 on the operating day 901.
  • the actual working hours 1402 are the working hours of operators engaged in the operation of the sludge treatment system 102 on the operating day 901 .
  • the number of people 1401 and actual working hours 1402 are acquired from, for example, a labor management system (not shown).
  • FIG. 15 is an explanatory diagram of an example of a maintenance management table.
  • the maintenance management table 1500 is a table for managing maintenance frequency of the sludge treatment system 102 .
  • the maintenance management table 1500 has operation period 1501 and maintenance frequency 1502 as fields.
  • the operation period 1501 is a fixed number of consecutive days during which the sludge treatment system 102 has been operated, and is defined by the start date and end date of the consecutive days.
  • the constant number of consecutive days is, for example, one month, three months, six months, one year, or the like.
  • the number of times of maintenance 1502 is the number of times of maintenance of the sludge treatment system 102 performed during the operation period 1501 .
  • the management server 101 uses the maintenance management table 1500 to generate a regression equation including a function f9 that predicts the maintenance frequency [times/operating period] (see equation (13) below).
  • the management server 101 inputs the number of times of maintenance 1502 for each operation period 1501 to the left side of the above equation (13) as correct data, and inputs the actual measurement formation floc property of the operation date and time 601 for each operation period 1501 to the right side of the above equation (13).
  • the measured dewatered sludge property 802 at the operating date and time 601 for each operating period 1501, and the equipment operating time for each operating period 1501 are input as learning data, and a regression equation including the function f9 is calculated by machine learning. Generate.
  • Equipment operating time [h] Planned amount of sludge to be treated [m 3 /day] ⁇ Treatment amount per hour [m 3 /h] ⁇ Operating days [day] (14)
  • the planned treatment target sludge volume [m 3 / day] for each planned treatment target day in the past is the representative value (average value, median value, maximum value, minimum value , or mode) multiplied by (sludge treatment end time - sludge treatment start time) of the day.
  • the device operating time [h] may simply be a value obtained by multiplying the number of operating days in the operating period 1501 by the operating time per day.
  • FIG. 16 is an explanatory diagram showing an example of a sludge inflow/outflow balance table.
  • the sludge inflow/outflow balance table 1600 is a table for managing the sludge inflow/outflow balance of the sludge treatment system 102 .
  • the sludge inflow balance table 1600 has, as fields, an operation date 601, a measured inflow sludge amount 1601, a measured outflow sludge amount 1602, and a measured water level 1603.
  • the measured inflow sludge amount 1601 is the measured value of the inflow amount of sludge 120 from the water treatment system to the sludge storage tank 121 at the operation date and time 601 .
  • the measured value is, for example, a value obtained by multiplying the representative value of the sludge flow rate detected by the flowmeter 124 at the operating date and time 601 by the time interval of the operating date and time 601 .
  • the measured outflow sludge amount 1602 is the measured value of the outflow amount of sludge from the sludge storage tank at the operation date and time 601 .
  • the measured value is, for example, a value obtained by multiplying the representative value of the sludge flow rate detected by the flowmeter 131 at the operating date and time 601 by the time interval of the operating date and time 601 .
  • the measured water level 1603 is the measured value of the water level of the sludge storage tank 121 at the operating date and time 601 and is detected by the water level gauge 122 .
  • the management server 101 also uses the sludge inflow/outflow balance table 1600 to generate a function f10 that predicts the sludge inflow/outflow balance for the next t hours (see formulas (15) and (16) below).
  • Amount of inflow sludge f11 (property of inflow sludge before t hours) (16)
  • the management server 101 inputs the measured inflow sludge amount 1601 for each operation date and time 601 to the left side of the above equation (16) as correct data, and the operation date and time 601 t hours before the operation date 601 to the right side of the above equation (16)
  • Inflow sludge properties upstream process operating conditions 602, water temperature 603, pH 604, electrical conductivity 605, sludge concentration 606, water content 607, weather 608 in the actually measured inflow sludge property table 600, measured t hours before the operation date and time 601 , season 609 are input as learning data, and a function f11 for predicting the amount of inflow sludge is generated as a regression equation by machine learning.
  • the management server 101 inputs (actually measured inflow sludge amount 1601 ⁇ actually measured outflow sludge amount 1602) for each operation date 601 to the left side of the above equation (15) as correct data, and inputs the operation date and time to the right side of the above equation (16).
  • the measured inflow sludge amount 1601 at the operation date and time 601 t hours before 601 and the planned treatment target sludge amount (calculated by the above formula (7)) t hours before the operation date and time 601 are input as learning data, and machine learning , a function f10 for predicting the sludge inflow/outflow balance for t hours from now on is generated as a regression equation.
  • FIG. 17 is an explanatory diagram showing an example of a dehydrated sludge inflow/outflow balance table.
  • the dehydrated sludge inflow/outflow balance table 1700 is a table for managing the dehydrated sludge inflow/outflow balance of the sludge treatment system 102 .
  • the dewatered sludge inflow/outflow balance table 1700 has, as fields, an operation date/time 601, a measured inflow dewatered sludge amount 1701, and a measured outflow dehydrated sludge amount 1702.
  • the measured inflow dehydrated sludge amount 1701 is the measured value of the inflow amount of the dehydrated sludge 167B into the dewatered sludge hopper 180 at the operation date and time 601 .
  • the measured value is, for example, a value obtained by multiplying the representative value of the dehydrated sludge flow rate detected by the flowmeter 169 at the operating date and time 601 by the time interval of the operating date and time 601 .
  • the measured outflow dewatered sludge amount 1702 is the measured value of the outflow amount of the dewatered sludge 167B from the dewatered sludge hopper 180 at the operation date and time 601.
  • the measured value is, for example, a value obtained by multiplying the representative value of the dehydrated sludge flow rate detected by the flow meter 182 at the operating date and time 601 by the time interval of the operating date and time 601 .
  • the measured stored weight 1703 is the measured value of the weight of the dehydrated sludge 167B stored in the dewatered sludge hopper 180 at the operating date and time 601, and is detected by the weight sensor 181.
  • the management server 101 also uses the dehydrated sludge inflow balance table 1700 to generate a function f11 that predicts the dehydrated sludge inflow balance for the next t hours (see formula (17) below).
  • the management server 101 inputs (actually measured inflow dehydrated sludge amount 1701 - measured outflow dehydrated sludge amount 1702) for each operation date 601 to the left side of the above equation (17) as correct data, and inputs the operation date and time to the right side of the above equation (17).
  • the measured dewatered sludge property 802 at the operating date and time 601 t hours before 601 and the planned amount of sludge to be treated (calculated by the above formula (7)) at t hours before the operating date and time 601 are input as learning data, and machine learning is performed.
  • a function f12 for predicting the amount of inflow sludge is generated as a regression equation.
  • FIG. 18 is a flow chart showing an example of a sludge treatment planning processing procedure by the management server 101.
  • the management server 101 acquires prediction conditions, for example, by input from the user (step S1801). Prediction conditions are parameters necessary for predicting the total cost. Specifically, for example, the forecast period, the weather and season during the forecast period, the number of drivers during the forecast period, and the dewatered sludge during the forecast period. is the scheduled time 507 of unloading.
  • the forecast target period is the period for which you want to formulate a sludge treatment plan, for example, one day (for example, the next day), one week, or one month when the date is specified.
  • the minimum unit of the prediction target period is a predetermined period of time (for example, 10 minutes, 30 minutes, 1 hour, 1 day (from the sludge treatment start time to the sludge treatment end time)) that is the same as the time width of the operation date and time 601 .
  • the management server 101 acquires the fixed conditions of the sludge treatment system 102 by reading them from the storage device 202 (step S1802).
  • the fixed conditions are fixed values included in each of the tables 300, 400, 500, 600, 700, 800, 900, 1000, 1100, 1200, 1300, 1400, 1500, 1600, and 1700 described above.
  • the unit price management table 300, flocculant table 400, constraint table 500, and flocculation tank capacity 704 are read.
  • the management server 101 acquires sensor data for an unselected and oldest time slot (hereinafter referred to as a target time slot; the duration of the target time slot is the above-described predetermined time period) in the prediction target period. (Step S1803). Specifically, for example, the management server 101 stores a set of measured values in the same time zone, the same season, and the same weather as the target time zone in the table 600 for the properties of inflowing sludge, the table 700 for floc formation conditions, and the table 700 for the conditions for forming flocs, Table 800, measured dehydrated sludge amount table 900, sludge injection pump actual measurement table 1000, floc forming tank actual measurement table 1100, dehydrator actual measurement table 1200, dehydrated sludge transfer pump actual measurement table 1300, operator actual measurement table 1400, maintenance management table 1500, sludge It is extracted from the inflow/outflow balance table 1600 and the dewatered sludge inflow/outflow balance table 1700 and read as sensor data.
  • the management server 101 selects any one set of measured values. Specifically, for example, the management server 101 may select a set of the most recent measured values. Also, the management server 101 may acquire a set of average values of the same type of actual measurement values as sensor data.
  • Operating conditions are a set of variable parameters required to operate the sludge treatment system 102 . That is, the operating condition is a set of combinations of values input to the explanatory variables on the right side of the above equations (1) to (17).
  • the group of explanatory variables that make up the operating conditions are throughput per hour, dehydrator driving machine rotation speed, injection pressure, applied back pressure level, flocculant injection rate, rapid stirrer rotation speed, slow speed They are the rotation speed of the agitator, the rotation speed of the dehydrated sludge transfer pump, the sludge treatment start time, and the sludge treatment end time.
  • a plurality of combinations of the values of the explanatory variable group that serve as the operating conditions are set.
  • the management server 101 calculates the total cost C for the target time period for each of the plurality of operating conditions (step S1805).
  • the total cost C is calculated, for example, by the following formula (18).
  • dehydrated sludge carrying-out cost Ca [Dewatered sludge transport cost Ca]
  • the dehydrated sludge carrying-out cost Ca is calculated by the following formula (19).
  • Dewatered sludge transport cost Ca Amount of dehydrated sludge [t/day] x (unit transportation cost [yen/t] + unit price of collection cost [yen/t]) (19)
  • the transportation cost unit price 302 and the pick-up cost unit price 303 are fixed values, and the values obtained in step S1802 are substituted.
  • the predicted value of the amount of dehydrated sludge [t/day] is calculated by the above formula (6).
  • the predicted value of the dehydrated sludge property [t/m 3 ] on the right side of the above formula (6) is calculated by the above formula (5).
  • the predicted value of the formed floc property on the right side of the above equation (5) is calculated by the above equation (4).
  • the management server 101 acquires the inflow sludge properties (upstream process operating conditions 602, water temperature 603, pH 604, electrical conductivity 605, sludge concentration 606, water content 607, weather 608, season 609, acquired as sensor data in the target time period). ) and the floc formation conditions are substituted into the right side of the above equation (4).
  • the flocculation conditions the coagulant injection rate 701, the rapid stirrer rotation speed 702, the slow stirrer rotation speed 703, and the throughput per hour 705 are assigned as operating conditions, and the flocculation tank capacity 704 is assigned as a fixed value.
  • the predicted value of the properties of the flocs formed is calculated and substituted into the above equation (5).
  • the management server 101 substitutes the dehydrator operating conditions 801 (dehydrator driving machine rotation speed, injection pressure, applied back pressure level), which are operating conditions, into the above equation (5).
  • the predicted value of the dehydrated sludge property is calculated and substituted into the above equation (6).
  • the predicted value of the planned amount of sludge to be treated [m 3 /day] is calculated by the above formula (7).
  • the processing amount per hour [m 3 /h], the sludge treatment end time, and the sludge treatment start time on the right side of the above equation (7) are operating conditions.
  • the predicted value of the planned amount of sludge to be treated [m 3 /day] is calculated and substituted into the above equation (6).
  • dehydration process operating conditions of the above formula (6) include dehydrator operating conditions 801 which are operating conditions, and floc formation conditions which are operating conditions and fixed values (coagulant injection rate 701, rapid stirrer rotation speed 702, Slow stirrer rpm 703, flocculation tank capacity 704 and throughput per hour 705) are substituted.
  • dehydrator operating conditions 801 which are operating conditions
  • floc formation conditions which are operating conditions and fixed values (coagulant injection rate 701, rapid stirrer rotation speed 702, Slow stirrer rpm 703, flocculation tank capacity 704 and throughput per hour 705) are substituted.
  • dehydration cost Cb [Dehydration cost Cb]
  • the dehydration cost Cb is calculated by the following formula (20).
  • Dehydration cost Cb flocculant cost Cb1 + equipment driving cost Cb2 + operator personnel cost Cb3 + equipment maintenance cost Cb4 (20)
  • the coagulant cost Cb1 is calculated by the following formula (21).
  • Coagulant cost Cb1 chemical unit price [yen/kg] x coagulant injection rate [mg/L] x processing amount per hour [m 3 /h] x unit conversion factor (fixed value) (21)
  • the drug unit price 401 and the unit conversion factor are fixed values, and the values obtained in step S1802 are substituted.
  • the management server 101 calculates the predicted value of the coagulant cost Cc by substituting the coagulant injection rate 701 and the throughput per hour [m 3 /h], which are the operating conditions, into the above equation (21). .
  • the device driving cost Cb2 is calculated by the following formula (22).
  • Equipment driving cost [yen] power consumption [kWh] x unit price of electricity [yen/kWh] (22)
  • the electricity bill unit price 305 is a fixed value, and the value obtained in step S1802 is substituted.
  • the predicted value of power consumption [kWh] is calculated by the following formula (23A).
  • Power consumption [kWh] Power consumption of sludge injection pump [kWh] + Power consumption of floc forming tank [kWh] + Power consumption of dehydrator [kWh] + Power consumption of dehydrated sludge transfer pump [kWh] (23A)
  • the predicted value of the sludge injection pump power consumption [kWh] is calculated by the above formula (8).
  • the injection pressure is a value defined by the operating conditions.
  • the operating time is also a value calculated from the difference between the sludge treatment start time and the sludge treatment end time, which are operating conditions.
  • the management server 101 calculates the predicted value of the sludge injection pump power consumption [kWh] by substituting the measured value of the sludge injection pump actual rotation speed 1002 acquired as the sensor data for the target time period into the above equation (8). do.
  • the predicted value of the flocculation tank power consumption [kWh] is calculated by the above formula (9).
  • the rapid stirrer rotation speed and the slow stirrer rotation speed are values defined by the operating conditions.
  • the operating time is also a value calculated from the difference between the sludge treatment start time and the sludge treatment end time, which are operating conditions.
  • the predicted value of the properties of the flocs formed is calculated by the above formula (4). That is, the management server 101 acquires the inflow sludge properties (upstream process operating conditions 602, water temperature 603, pH 604, electrical conductivity 605, sludge concentration 606, water content 607, weather 608, season 609, acquired as sensor data in the target time period). ) and flocculation conditions (coagulant injection rate 701, rapid stirrer rotation speed 702, slow stirrer rotation speed 703, flocculation tank capacity 704, and throughput per hour 705) are calculated by the above formula (4). to the right side of .
  • inflow sludge properties upstream process operating conditions 602, water temperature 603, pH 604, electrical conductivity 605, sludge concentration 606, water content 607, weather 608, season 609, acquired as sensor data in the target time period.
  • flocculation conditions coagulant injection rate 701, rapid stirrer rotation speed 702, slow stirrer rotation speed 703, flocculation tank capacity 704, and throughput per hour 705
  • the management server 101 calculates the predicted value of the sludge injection pump power consumption [kWh].
  • the predicted value of the dehydrator power consumption [kWh] is calculated by the above formula (10).
  • the rotation speed of the dehydrator driving machine, the applied back pressure level, and the throughput per hour are values defined by the operating conditions.
  • the operating time is also a value calculated from the difference between the sludge treatment start time and the sludge treatment end time, which are operating conditions.
  • the properties of flocs formed are calculated by the above formula (4) and substituted into the above formula (10), as in the case of the floc formation tank power consumption [kWh]. In this way, the management server 101 calculates the predicted value of the dehydrator power consumption [kWh].
  • the predicted value of the power consumption [kWh] of the dewatered sludge transfer pump is calculated by the above formula (11).
  • the rotation speed of the dewatered sludge transfer pump is a value defined by the operating conditions.
  • the operating time is also a value calculated from the difference between the sludge treatment start time and the sludge treatment end time, which are operating conditions.
  • the dehydrated sludge properties are calculated by the above formula (5).
  • the properties of flocs formed in the formula (5) are calculated by the formula (4) and substituted into the formula (5).
  • the management server 101 substitutes the dehydrator operating conditions 801 (dehydrator driving machine rotation speed, injection pressure, applied back pressure level), which are operating conditions, into the above equation (5).
  • the management server 101 calculates the predicted value of the power consumption [kWh] of the dehydrated sludge transfer pump.
  • the personnel cost unit price 301 is a fixed value, and the value obtained in step S1802 is substituted into the above formula (23B).
  • the number of people [people] is the value of the prediction condition acquired in step S1801, and is substituted into the above equation (23B).
  • the predicted value of working hours [h] is calculated by the following formula (24).
  • Working hours Planned amount of sludge to be treated [m 3 /day] ⁇ amount of treatment per hour [m 3 /h] (24)
  • the throughput per hour [m 3 /h] in the above formula (24) is an operating condition.
  • the predicted value of the planned amount of sludge to be treated [m 3 /day] is calculated by the above equation (7).
  • the processing amount per hour [m 3 /h], the sludge treatment end time, and the sludge treatment start time on the right side of the above equation (7) are operating conditions.
  • the predicted value of the planned amount of sludge to be treated [m 3 /day] is calculated and substituted into the above equation (24).
  • the management server 101 calculates the operator personnel cost Cb3 for the target time period by dividing the operator personnel cost per day calculated by the above formula (23B) by the time span (predetermined time) of the target time period.
  • Equipment maintenance cost Cb4 The equipment maintenance cost during the operation period is calculated by the following formula (25).
  • Equipment maintenance cost during operation period [yen] maintenance unit price [yen/time] x maintenance frequency (time/operation period) (25)
  • the maintenance unit price 304 is a fixed value, and the value obtained in step S1802 is substituted into the above formula (25).
  • the predicted value of maintenance frequency (times/operating period) is calculated by the above formula (13).
  • the predicted value of the properties of the flocs formed is calculated by Equation (4) above. That is, the management server 101 acquires the inflow sludge properties (upstream process operating conditions 602, water temperature 603, pH 604, electrical conductivity 605, sludge concentration 606, water content 607, weather 608, season 609, acquired as sensor data in the target time period). ), operating conditions, and flocculation conditions that are fixed values (coagulant injection rate 701, rapid stirrer rotation speed 702, slow stirrer rotation speed 703, flocculation tank capacity 704, and throughput per hour 705). to the right side of the above equation (4).
  • the inflow sludge properties upstream process operating conditions 602, water temperature 603, pH 604, electrical conductivity 605, sludge concentration 606, water content 607, weather 608, season 609, acquired as sensor data in the target time period.
  • operating conditions, and flocculation conditions that are fixed values (coagulant injection rate 701, rapid stirrer rotation speed 702, slow stirrer rotation speed 703, flocculation tank capacity
  • the predicted value of the appliance operating time is calculated by Equation (14) above.
  • the throughput per hour [m 3 /h] in the above formula (14) is an operating condition.
  • the predicted value of the planned amount of sludge to be treated [m 3 /day] is calculated by the above formula (7).
  • the number of operating days in the above formula (14) is the number of days in the prediction target period.
  • the management server 101 divides the equipment maintenance cost [yen] in the operation period calculated by the above formula (25) by the number of days in the prediction target period and by the time span (predetermined time) of the target time zone. , the equipment maintenance cost Cb4 for the target time period is calculated.
  • the management server 101 calculates the dehydration cost Cb for the target time period by summing the flocculant cost Cb1, the equipment driving cost Cb2, the operator labor cost Cb3, and the equipment maintenance cost Cb4 according to the above equation (20). Then, the management server 101 adds the dewatered sludge carrying-out cost Ca calculated by the above formula (19) and the dehydration cost Cb calculated by the above formula (20) using the above formula (18). A total cost C is calculated.
  • step S1805 the management server 101 determines whether there is an operating condition that has not been selected in step S1807 and has the lowest total cost (step S1806). If there is an unselected operating condition with the lowest total cost (step S1806: Yes), the management server 101 selects an unselected operating condition with the lowest total cost (step S1807).
  • step S1807 the unselected operating condition with the lowest total cost is selected, so when the selected operating condition complies with all of the following constraints (A) to (F), in step S1806, unselected Moreover, there is no operating condition with the lowest total cost (step S1806: No), and the process proceeds to step S1809. As a result, it is possible to suppress wasteful determination of compliance with the constraint.
  • the management server 101 determines whether or not the restrictions on the dewatered sludge scheduled discharge time 507 acquired in step S1801 are complied with using the following formula (26).
  • Time of target time zone + (planned amount of sludge to be treated - amount of treatment per hour x elapsed treatment time) / amount of treatment per hour ⁇ scheduled time to carry out dewatered sludge ...
  • the time in the target time period is a certain time in the target time period, and may be, for example, the oldest time or the latest time in the target time period.
  • the elapsed treatment time is the time that the sludge treatment has elapsed in the target time zone, and in this case, it is the time width (predetermined time) of the target time zone. If the above formula (26) is satisfied, the selected operating condition complies with the constraint (B), otherwise the constraint (B) is violated.
  • the management server 101 determines whether or not the predicted current value of each motor 153 , 154 , 166 in the target time period is equal to or less than the driver current upper limit value 502 of the constraint condition table 500 . It is assumed that the current values of the motors 153, 154, and 166 are measured for each operation date/time 601 by an ammeter (not shown).
  • the management server 101 uses, for example, the current values of the motors 153 and 154 for each past operating date and time 601 and the power consumption [kWh] for each past operating date and time 601 to calculate a regression equation by machine learning. Predicted current values of the motors 153 and 154 in the target time period are calculated by substituting the flocculation tank power consumption [kWh] in the target time period into the regression equation.
  • the management server 101 uses, for example, the current value of the dehydrator driving machine 166 for each past operation date and time 601 and the dehydrator power consumption [kWh] for each past operation date and time 601 to By creating a regression equation and substituting the dehydrator power consumption [kWh] in the target time period into the regression equation, the predicted current value of the dehydrator driver 166 in the target time period is calculated. If the predicted current values of the motors 153, 154, 166 in the target time period are all equal to or less than the driver current upper limit value 502 of the constraint table 500, the selected operating condition complies with the constraint (C). violates constraint (C).
  • the management server 101 determines whether or not the injection pressure of the sludge injection pump 130 , which is the selected operating condition, is equal to or less than the inflow pressure upper limit value 503 of the constraint condition table 500 .
  • the management server 101 also determines whether or not the measured discharge pressure 1303 of the dehydrated sludge transfer pump 170 acquired as sensor data for the target time period is equal to or less than the outflow pressure upper limit value 504 of the constraint condition table 500 .
  • the selected operating condition complies with the constraint (D). , otherwise constraint (D) is violated.
  • the management server 101 determines whether or not the constraint regarding the sludge storage tank capacity 505 of the constraint condition table 500 acquired in step S1802 is complied with using the following formula (27).
  • the water level in the target time period on the left side of the above equation (27) is the actually measured water level 1603 acquired as the sensor data in the target time period.
  • the sludge inflow/outflow balance for t hours from now on is calculated by the above formula (15).
  • the predicted value of the planned amount of sludge to be treated [m 3 /day] in the above formula (15) is calculated by the above formula (7).
  • the processing amount per hour [m 3 /h], the sludge treatment end time, and the sludge treatment start time on the right side of the above equation (7) are selected operating conditions.
  • the inflow sludge properties (upstream process operating conditions 602, water temperature 603, pH 604, electrical conductivity 605, sludge concentration 606, water content 607 , weather 608, and season 609) are data acquired as sensor data for the target time period in step S1803. If the above formula (27) is satisfied, the selected operating condition complies with the constraint (E), otherwise the constraint (E) is violated.
  • the management server 101 determines whether or not the restriction regarding the dewatered sludge hopper maximum allowable storage weight 506 in the restriction condition table 500 acquired in step S1802 is complied with using the following formula (28).
  • the storage weight in the target time period on the left side of the above equation (28) is the actually measured storage weight 1703 acquired as the sensor data in the target time period.
  • the dewatered sludge inflow/outflow balance for t hours from now on is calculated by the above equation (17).
  • the measured dehydrated sludge property in the above formula (17) is the measured dehydrated sludge property 802 of the actually measured dewatered sludge property table 800 acquired as the sensor data for the target time period in step S1803.
  • the predicted value of the planned amount of sludge to be treated [m 3 /day] in the above formula (17) is calculated by the above formula (7).
  • the processing amount per hour [m 3 /h], the sludge treatment end time, and the sludge treatment start time on the right side of the above equation (7) are selected operating conditions. If the above formula (28) is satisfied, the selected operating condition complies with the constraint (F), otherwise the constraint (F) is violated.
  • Fig. 19 is a graph showing the relationship between the operating conditions and the total cost C.
  • condition 4 is the operating condition that minimizes the total cost C, but the constraints (A) to (F) are not complied with. Therefore, condition 3 is the operating condition that complies with the constraints (A) to (F) and minimizes the total cost C.
  • step S1806 determines whether or not the search has ended (step S1809). That is, if there is an unprocessed target time period, the search is not finished (step S1809: No), so the process proceeds to step S1803. The process moves to step S1810.
  • the management server 101 formulates a sludge treatment plan for each target time zone (step S1810). Specifically, for example, the management server 101, based on the operating conditions (hereinafter referred to as optimum operating conditions) with the lowest overall cost among the operating conditions that comply with all of the constraints (A) to (F), sludge treatment Formulate a plan for each target time period.
  • optimum operating conditions the operating conditions with the lowest overall cost among the operating conditions that comply with all of the constraints (A) to (F)
  • the sludge treatment plan is information including the dehydration process operating conditions and the planned amount of sludge to be treated in the target time zone.
  • the planned amount of sludge to be treated in the target time period is a predicted value of the planned amount of sludge to be treated [m 3 /day] in the target time period calculated using the above formula (17).
  • the dehydration process operating conditions are the dehydrator operating conditions and floc formation conditions during the target time period.
  • the dehydrator operating conditions in the target time period are the optimum operating conditions.
  • the flocculation conditions in the target time period are the flocculant injection rate 701, the rapid stirrer rotation speed 702, the slow stirrer rotation speed 703, and the throughput per hour 705, which are the optimum operating conditions, and the flocculation tank capacity at a fixed value. 704.
  • the management server 101 specifies the sludge treatment start time and sludge treatment end time for each day of the prediction target period from the sludge treatment plan for each target time period. Specifically, for example, the management server 101 determines the start time of the oldest time period of each day as the sludge treatment start time. In addition, the management server 101 determines the end time of the latest time period of the target time period of each day as the sludge treatment end time.
  • the management server 101 stores the total cost C corresponding to the optimum operating condition, the dewatered sludge carrying-out cost Ca, the dehydration cost Cb, the coagulant cost Cb1, the equipment driving cost Cb2, the operator labor cost Cb3, the equipment
  • the maintenance cost Cb4 is set as an output target.
  • the management server 101 outputs the calculation results (at least one of the sludge treatment plan, the optimum operating conditions, and various costs) for each target time period in a displayable manner (step S1811). Specifically, for example, the management server 101 displays the data on a display, which is an example of the output device 204, or transmits data to another computer that can communicate via the network 103 so that the data can be displayed.
  • the management server 101 calculates the total cost, dehydrated sludge carrying-out cost, dehydration cost, coagulant cost, equipment driving cost, operator labor cost, equipment maintenance cost when the processing of FIG. 18 is not executed, It may be set as an output target. Specifically, for example, the management server 101 calculates the dehydrated sludge carrying-out cost, the dehydration cost, the coagulant cost, the device driving cost, the operator labor cost, and the device maintenance cost under the operating conditions when the process of FIG. 18 is not applied. calculate. As a result, it is possible to display and output the cost comparison results (graphs and tables) between the case where the processing of FIG. 18 is applied and the case where the processing is not applied. This enables the operator to judge whether or not to adopt the output operating conditions from a more objective point of view.
  • the management server 101 formulates a sludge treatment plan that satisfies the constraints (A) to (F) and is excellent in total cost C.
  • the operator can determine which operating conditions are optimal without understanding the complex trade-off relationship between the reduction in the dewatered sludge transport cost Ca and the increase in the dewatering cost Cb due to the reduction of the water content and the instantaneous calculation. be able to determine whether there is
  • the sludge treatment system 102 could not be operated at the optimum point of the total cost C due to various circumstances, but the sludge treatment system 102 can be operated under more advantageous operating conditions at the total cost C. .
  • the need to rely on the rules of thumb of experienced operators is reduced. Therefore, technology inheritance becomes relatively easy, contributing to the realization of sustainable securing of resources.
  • the cost of carrying out sludge is reduced, improving the economic efficiency of sewage treatment.
  • the sludge treatment management system 100 of this embodiment can be applied, for example, to the operation and maintenance of the dehydration process in organic industrial wastewater treatment.
  • the present invention is not limited to the above-described embodiments, and includes various modifications and equivalent configurations within the spirit of the attached claims.
  • the above-described embodiments have been described in detail in order to explain the present invention in an easy-to-understand manner, and the present invention is not necessarily limited to those having all the described configurations.
  • part of the configuration of one embodiment may be replaced with the configuration of another embodiment.
  • the configuration of another embodiment may be added to the configuration of one embodiment.
  • other configurations may be added, deleted, or replaced with respect to a part of the configuration of each embodiment.
  • each configuration, function, processing unit, processing means, etc. described above may be implemented in hardware, for example, by designing a part or all of them with an integrated circuit, and the processor implements each function. It may be realized by software by interpreting and executing a program to execute.
  • Storage devices such as memory, hard disk, SSD (Solid State Drive), or IC (Integrated Circuit) card, SD card, DVD (Digital Versatile Disc) Can be stored on media.
  • control lines and information lines indicate those that are considered necessary for explanation, and do not necessarily indicate all the control lines and information lines necessary for implementation. In practice, it can be considered that almost all configurations are interconnected.

Landscapes

  • Engineering & Computer Science (AREA)
  • Water Supply & Treatment (AREA)
  • Business, Economics & Management (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Economics (AREA)
  • Organic Chemistry (AREA)
  • Chemical & Material Sciences (AREA)
  • Environmental & Geological Engineering (AREA)
  • Hydrology & Water Resources (AREA)
  • General Health & Medical Sciences (AREA)
  • Strategic Management (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Mechanical Engineering (AREA)
  • Tourism & Hospitality (AREA)
  • Primary Health Care (AREA)
  • Marketing (AREA)
  • Human Resources & Organizations (AREA)
  • Public Health (AREA)
  • Treatment Of Sludge (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

This sludge treatment management apparatus has a processor for executing a program and a storage device for storing the program, and is accessible to a sludge treatment system for treating sludge. The sludge treatment management device executes a calculation process for calculating, regarding each of a plurality of operation conditions for operating the sludge treatment system and on the basis of the operation condition, a dehydrating cost of dehydrating the sludge in the sludge treatment system and a carry-out cost of carrying out dehydrated sludge from the sludge treatment system and for calculating a total cost by adding the carry-out cost and the dehydrating cost; a determination process for determining a specific operation condition on the basis of the total cost for each of the operation conditions, calculated by the calculation process; and an output process for outputting the specific operation condition determined by the determination process.

Description

汚泥処理管理装置および汚泥処理管理方法Sludge treatment management device and sludge treatment management method 参照による取り込みImport by reference
　本出願は、令和３年（２０２１年）６月３０日に出願された日本出願である特願２０２１－１０８４４８の優先権を主張し、その内容を参照することにより、本出願に取り込む。 This application claims the priority of Japanese Patent Application No. 2021-108448 filed on June 30, 2021, and the contents thereof are incorporated into this application by reference.
　本発明は、汚泥処理管理装置および汚泥処理管理方法に関する。 The present invention relates to a sludge treatment management device and a sludge treatment management method.
　下記特許文献１は、下水処理場の運転支援を行う運転支援装置を開示する。この運転支援装置は、下水処理場ごとの下水処理機器のデータベースおよび所定の数値モデルを格納する記憶部と、下水処理場への流入条件、下水処理場の運転条件、記憶部のデータを参照して、所定期間における下水処理場からの放流水質予測値を算出する放流水質演算手段と、運転条件に基づいて下水処理場における下水処理の運転費予測値を算出する運転費演算手段と、放流水質予測値、運転費予測値および排出枠およびこの排出枠の購入または売却価格を含む排出枠条件に基づいて、下水処理場における排出汚濁負荷予測値の算出および排出枠の購入または売却による効果の指標である枠取引効果指標値の算出を行う処理効果演算手段と、を備える。 Patent Document 1 below discloses an operation support device that supports the operation of a sewage treatment plant. This operation support device refers to a storage unit that stores a database of sewage treatment equipment for each sewage treatment plant and a predetermined numerical model, inflow conditions to the sewage treatment plant, operating conditions of the sewage treatment plant, and data in the storage unit. Effluent water quality calculation means for calculating a predicted value of effluent water quality from the sewage treatment plant in a predetermined period, an operation cost calculation means for calculating a predicted value of operation cost for sewage treatment at the sewage treatment plant based on the operating conditions, and effluent quality Calculation of the expected discharge pollutant load at the sewage treatment plant and an indicator of the effect of purchasing or selling the allowance, based on the forecasted value, the forecasted operating cost, and the allowance conditions, including the allowance and the purchase or sale price of this allowance. and processing effect calculation means for calculating a frame transaction effect index value.
特開２００６－２１０８５号公報Japanese Unexamined Patent Application Publication No. 2006-21085
　しかしながら、上記特許文献１の運転支援装置は水処理に関する技術であり、汚泥処理に対する運転支援については何ら考慮されていない。下水処理および排水処理の過程で発生する汚泥は、容量および容積を下げる脱水処理などを経て産業廃棄物として搬出され、埋め立て処理、燃料および資源として再利用される。輸送費および引取費の搬出にかかる費用は一般的に容量単価で定められており、そのコスト低減のために固形分に対する水分の比率、すなわち含水率を脱水工程にて可能な限り下げることが望まれる。 However, the driving support device of Patent Document 1 is a technology related to water treatment, and does not consider driving support for sludge treatment at all. Sludge generated in the process of sewage treatment and wastewater treatment is carried out as industrial waste through dehydration treatment to reduce volume and volume, and is reused as landfill treatment, fuel and resources. Transportation costs and collection costs are generally determined by volume unit price, and in order to reduce the cost, it is desirable to reduce the ratio of water to solid content, that is, the water content, as much as possible in the dehydration process. be
　一方で含水率を低減するための諸施策にはそれぞれコストが生じる。たとえば、汚泥の脱水性を上げるために薬品添加量を増やせば、薬品コストが増大する。したがって、含水率低減による搬出費用の低減と施策のためのコストはトレードオフの関係にある。汚泥処理の経済的運用のためには、これらトレードオフの関係を熟知し最適点での運用を続けることが望まれる。 On the other hand, various measures to reduce the moisture content incur costs. For example, increasing the amount of chemicals added to increase the dewaterability of sludge will increase the cost of chemicals. Therefore, there is a trade-off relationship between the reduction in shipping cost due to the reduction in moisture content and the cost for measures. For the economical operation of sludge treatment, it is desirable to know these trade-off relationships and to continue operation at the optimum point.
　ところが、汚泥の性状は下水および排水の性状変化に伴い刻々と変化すること、トレードオフの関係は非常に複雑で判断が容易でないことから、最適な運転点の判断をタイムリーに下すことは容易でない。また、判断基準も運転員の経験則に依存しているのが現状であり、技術継承の観点でも問題点が生じている。 However, the properties of sludge change from moment to moment as the properties of sewage and wastewater change, and the trade-off relationship is extremely complex and difficult to judge. not. In addition, the current situation is that the judgment criteria also depend on the operator's experience, and there is also a problem from the viewpoint of technology succession.
　本発明は、汚泥処理システムの適切な運転条件を提示することを目的とする。 The purpose of the present invention is to present appropriate operating conditions for a sludge treatment system.
　本願において開示される発明の一側面となる汚泥処理管理装置は、プログラムを実行するプロセッサと、前記プログラムを記憶する記憶デバイスと、を有し、汚泥を処理する汚泥処理システムにアクセス可能な汚泥処理管理装置であって、前記プロセッサは、前記汚泥処理システムを運転する複数の運転条件の各々について、前記運転条件に基づいて、前記汚泥処理システムで前記汚泥を脱水する脱水コストと、前記汚泥処理システムから脱水汚泥を搬出する搬出コストと、を算出し、前記搬出コストと前記脱水コストとを加算した総合コストを算出する算出処理と、前記算出処理によって算出された前記運転条件ごとの総合コストに基づいて、特定の運転条件を決定する決定処理と、前記決定処理によって決定された特定の運転条件を出力する出力処理と、を実行することを特徴とする。 A sludge treatment management device, which is one aspect of the invention disclosed in the present application, has a processor that executes a program and a storage device that stores the program, and is accessible to a sludge treatment system that treats sludge. A management device, wherein the processor, for each of a plurality of operating conditions for operating the sludge treatment system, calculates a dehydration cost for dewatering the sludge in the sludge treatment system and the sludge treatment system based on the operating conditions. Based on the total cost for each operating condition calculated by the calculation process of calculating the carrying-out cost of carrying out the dewatered sludge from the a determination process for determining a specific operating condition; and an output process for outputting the specific operating condition determined by the decision process.
　本発明の代表的な実施の形態によれば、汚泥処理システムの適切な運転条件を提示することができる。前述した以外の課題、構成及び効果は、以下の実施例の説明により明らかにされる。 According to the representative embodiment of the present invention, suitable operating conditions for the sludge treatment system can be presented. Problems, configurations, and effects other than those described above will be clarified by the following description of the embodiments.
図１は、汚泥処理管理システムのシステム構成例を示す説明図である。FIG. 1 is an explanatory diagram showing a system configuration example of a sludge treatment management system. 図２は、管理サーバのハードウェア構成例を示すブロック図である。FIG. 2 is a block diagram illustrating an example hardware configuration of a management server. 図３は、単価管理テーブルの一例を示す説明図である。FIG. 3 is an explanatory diagram showing an example of the unit price management table. 図４は、凝集剤テーブルの一例を示す説明図である。FIG. 4 is an explanatory diagram showing an example of a flocculant table. 図５は、制約条件テーブルの一例を示す説明図である。FIG. 5 is an explanatory diagram showing an example of a constraint condition table. 図６は、実測流入汚泥性状テーブルの一例を示す説明図である。FIG. 6 is an explanatory diagram showing an example of an actually measured inflow sludge properties table. 図７は、フロック形成条件テーブルの一例を示す説明図である。FIG. 7 is an explanatory diagram showing an example of a flocculation condition table. 図８は、実測脱水汚泥性状テーブルの一例を示す説明図である。FIG. 8 is an explanatory diagram showing an example of an actually measured dehydrated sludge properties table. 図９は、実測脱水汚泥量テーブルの一例を示す説明図である。FIG. 9 is an explanatory diagram showing an example of a measured dehydrated sludge amount table. 図１０は、汚泥圧入ポンプ実測テーブルの一例を示す説明図である。FIG. 10 is an explanatory diagram showing an example of a sludge injection pump actual measurement table. 図１１は、フロック形成槽実測テーブルの一例を示す説明図である。FIG. 11 is an explanatory diagram showing an example of a flocculation tank actual measurement table. 図１２は、脱水機実測テーブルの一例を示す説明図である。FIG. 12 is an explanatory diagram showing an example of a dehydrator actual measurement table. 図１３は、脱水汚泥移送ポンプ実測テーブルの一例を示す説明図である。FIG. 13 is an explanatory diagram showing an example of a dehydrated sludge transfer pump actual measurement table. 図１４は、運転員実測テーブルの一例を示す説明図である。FIG. 14 is an explanatory diagram showing an example of an operator actual measurement table. 図１５は、メンテナンス管理テーブルの一例を示す説明図である。FIG. 15 is an explanatory diagram of an example of a maintenance management table. 図１６は、汚泥流入出収支テーブルの一例を示す説明図である。FIG. 16 is an explanatory diagram showing an example of a sludge inflow/outflow balance table. 図１７は、脱水汚泥流入出収支テーブルの一例を示す説明図である。FIG. 17 is an explanatory diagram showing an example of a dehydrated sludge inflow/outflow balance table. 図１８は、管理サーバによる汚泥処理計画策定処理手順例を示すフローチャートである。FIG. 18 is a flow chart showing an example of a sludge treatment planning processing procedure by the management server. 図１９は、運転条件と総合コストとの関係を示すグラフである。FIG. 19 is a graph showing the relationship between operating conditions and total cost.
　＜システム構成例＞
　図１は、汚泥処理管理システムのシステム構成例を示す説明図である。汚泥処理管理システム１００は、管理サーバ１０１と、汚泥処理システム１０２と、を有する。管理サーバ１０１および汚泥処理システム１０２は、インターネット、ＬＡＮ（Ｌｏｃａｌ　Ａｒｅａ　Ｎｅｔｗｏｒｋ）、ＷＡＮ（Ｗｉｄｅ　Ａｒｅａ　Ｎｅｔｗｏｒｋ）などのネットワーク１０３を介して通信可能に接続される。管理サーバ１０１は、汚泥処理システム１０２の系内を管理するコンピュータである。汚泥処理システム１０２は、水処理された汚泥１２０を処理するシステムである。 <System configuration example>
FIG. 1 is an explanatory diagram showing a system configuration example of a sludge treatment management system. The sludge treatment management system 100 has a management server 101 and a sludge treatment system 102 . The management server 101 and the sludge treatment system 102 are communicably connected via a network 103 such as the Internet, LAN (Local Area Network), WAN (Wide Area Network). The management server 101 is a computer that manages the inside of the sludge treatment system 102 . The sludge treatment system 102 is a system for treating sludge 120 that has undergone water treatment.
　汚泥処理システム１０２は、汚泥貯留槽１２１を有する。汚泥貯留槽１２１は、水処理された汚泥１２０を貯留する。水位計１２２は、汚泥貯留槽１２１に貯留されている汚泥１２０の水位を検出する。検出されたセンサデータは、管理サーバ１０１に送信される。 The sludge treatment system 102 has a sludge storage tank 121. The sludge storage tank 121 stores sludge 120 that has undergone water treatment. The water level gauge 122 detects the water level of the sludge 120 stored in the sludge storage tank 121 . The detected sensor data is transmitted to the management server 101 .
　水温センサ１２３は、汚泥貯留槽１２１に貯留されている汚泥１２０の水温を検出する。検出されたセンサデータは、管理サーバ１０１に送信される。流量計１２４は、上流プロセスである水処理システムから流入される汚泥１２０の流量［ｍ３／ｈ］を検出する。検出されたセンサデータは、管理サーバ１０１に送信される。 A water temperature sensor 123 detects the water temperature of the sludge 120 stored in the sludge storage tank 121 . The detected sensor data is transmitted to the management server 101 . The flow meter 124 detects the flow rate [m 3 /h] of the sludge 120 flowing from the water treatment system, which is the upstream process. The detected sensor data is transmitted to the management server 101 .
　汚泥圧入ポンプ１３０は、汚泥貯留槽１２１の汚泥１２０を圧入し、フロック形成槽１５０に排出する。流量計１３１は、汚泥圧入ポンプ１３０から排出される汚泥１２０の流量を検出する。検出されたセンサデータは、管理サーバ１０１に送信される。 The sludge injection pump 130 injects the sludge 120 in the sludge storage tank 121 and discharges it into the floc formation tank 150 . A flow meter 131 detects the flow rate of the sludge 120 discharged from the sludge injection pump 130 . The detected sensor data is transmitted to the management server 101 .
　ペーハーセンサ１３２は、汚泥圧入ポンプ１３０から排出される汚泥１２０の水素イオン濃度を検出する。検出されたセンサデータは、管理サーバ１０１に送信される。 The pH sensor 132 detects the hydrogen ion concentration of the sludge 120 discharged from the sludge injection pump 130 . The detected sensor data is transmitted to the management server 101 .
　電気伝導度センサ１３３は、汚泥圧入ポンプ１３０から排出される汚泥１２０の電気伝導度を検出する。検出されたセンサデータは、管理サーバ１０１に送信される。 The electric conductivity sensor 133 detects the electric conductivity of the sludge 120 discharged from the sludge injection pump 130. The detected sensor data is transmitted to the management server 101 .
　汚泥濃度センサ１３４は、汚泥圧入ポンプ１３０から排出される汚泥１２０の汚泥濃度を検出する。検出されたセンサデータは、管理サーバ１０１に送信される。 The sludge concentration sensor 134 detects the sludge concentration of the sludge 120 discharged from the sludge injection pump 130 . The detected sensor data is transmitted to the management server 101 .
　薬液ポンプ１４０は、凝集剤を汚泥１２０に注入する。流量計１４１は、汚泥１２０に注入される凝集剤の流量を検出する。検出されたセンサデータは、管理サーバ１０１に送信される。 The chemical pump 140 injects the coagulant into the sludge 120. A flow meter 141 detects the flow rate of the coagulant injected into the sludge 120 . The detected sensor data is transmitted to the management server 101 .
　フロック形成槽１５０は、汚泥１２０を吸入してフロックを形成し、形成したフロックを脱水機１６０に排出する。フロック形成槽１５０は、急速撹拌機１５１と、緩速撹拌機１５２と、モータ１５３，１５４と、圧力計１５５と、フロックセンサ１５６と、を有する。 The floc formation tank 150 sucks the sludge 120 to form flocs, and discharges the formed flocs to the dehydrator 160 . The floc forming tank 150 has a rapid agitator 151 , a slow agitator 152 , motors 153 and 154 , a pressure gauge 155 and a floc sensor 156 .
　急速撹拌機１５１は、フロック形成槽１５０内の汚泥を急速で撹拌する。緩速撹拌機１５２は、急速撹拌機１５１の撹拌速度よりも遅い撹拌速度でフロック形成槽１５０内の汚泥１２０を撹拌する。 The rapid agitator 151 rapidly agitates the sludge in the flocculation tank 150 . The slow agitator 152 agitates the sludge 120 in the flocculation tank 150 at an agitation speed slower than the agitation speed of the rapid agitator 151 .
　モータ１５３は、急速撹拌機１５１を回転駆動し、急速撹拌機１５１の回転数を検出する。検出されたセンサデータは、管理サーバ１０１に送信される。 The motor 153 rotates the rapid stirrer 151 and detects the rotation speed of the rapid stirrer 151 . The detected sensor data is transmitted to the management server 101 .
　モータ１５４は、緩速撹拌機１５２を回転駆動し、緩速撹拌機１５２の回転数を検出する。検出されたセンサデータは、管理サーバ１０１に送信される。 The motor 154 rotates the slow stirrer 152 and detects the rotation speed of the slow stirrer 152 . The detected sensor data is transmitted to the management server 101 .
　圧力計１５５は、形成されたフロックを脱水機１６０に排出する排出圧力を検出する。検出されたセンサデータは、管理サーバ１０１に送信される。 The pressure gauge 155 detects the discharge pressure for discharging the formed flocs to the dehydrator 160. The detected sensor data is transmitted to the management server 101 .
　フロックセンサ１５６は、フロック形成槽１５０内のフロックを撮影することで、フロックの直径［ｍｍ］を形成フロック性状として検出する。フロックの直径［ｍｍ］は、たとえば、フロックの直径分布の中央値が採用される。検出されたセンサデータは、管理サーバ１０１に送信される。 The floc sensor 156 detects the diameter [mm] of the flocs as the properties of the flocs formed by photographing the flocs in the floc forming tank 150 . For the floc diameter [mm], for example, the median value of the floc diameter distribution is adopted. The detected sensor data is transmitted to the management server 101 .
　脱水機１６０は、フロック形成槽１５０からのフロックを脱水し、フロックから脱離液１６７Ａを分離して、脱水汚泥１６７Ｂとして脱水汚泥ホッパー１８０に排出する。脱水機１６０は、位置センサ１６１～１６４と、背圧付与板１６５と、脱水機駆動機１６６と、を有する。 The dehydrator 160 dewaters the flocs from the flocculation tank 150, separates the desorbed liquid 167A from the flocs, and discharges it to the dehydrated sludge hopper 180 as dehydrated sludge 167B. The dehydrator 160 has position sensors 161 to 164 , a back pressure applying plate 165 and a dehydrator driver 166 .
　位置センサ１６１～１６４は、背圧付与板１６５の位置を検出する。検出されたセンサデータは、管理サーバ１０１に送信される。 The position sensors 161 to 164 detect the position of the back pressure applying plate 165 . The detected sensor data is transmitted to the management server 101 .
　背圧付与板１６５は、脱水機１６０への背圧を制御する機構である。背圧付与板１６５が脱水機１６０の内部に接近すると背圧が高くなり、離間すると低くなる。 The back pressure imparting plate 165 is a mechanism for controlling the back pressure to the dehydrator 160. The back pressure increases when the back pressure applying plate 165 approaches the interior of the dehydrator 160, and decreases when it separates.
　含水率センサ１６８は、脱水機１６０からの脱水汚泥１６７Ｂの含水率を検出する。検出されたセンサデータは、管理サーバ１０１に送信される。 The moisture content sensor 168 detects the moisture content of the dehydrated sludge 167B from the dehydrator 160. The detected sensor data is transmitted to the management server 101 .
　流量計１６９は、脱水機１６０からの脱水汚泥１６７Ｂの流量を検出する。検出されたセンサデータは、管理サーバ１０１に送信される。 The flow meter 169 detects the flow rate of the dehydrated sludge 167B from the dehydrator 160. The detected sensor data is transmitted to the management server 101 .
　脱水汚泥移送ポンプ１７０は、脱水機１６０からの脱水汚泥１６７Ｂを吸入し、脱水汚泥ホッパー１８０に吐出する。 The dehydrated sludge transfer pump 170 sucks the dehydrated sludge 167B from the dehydrator 160 and discharges it to the dehydrated sludge hopper 180.
　圧力計１７１は、脱水汚泥移送ポンプ１７０が脱水汚泥１６７Ｂを脱水汚泥ホッパー１８０に吐出する吐出圧力を検出する。検出されたセンサデータは、管理サーバ１０１に送信される。 The pressure gauge 171 detects the discharge pressure at which the dehydrated sludge transfer pump 170 discharges the dehydrated sludge 167B to the dehydrated sludge hopper 180. The detected sensor data is transmitted to the management server 101 .
　脱水汚泥ホッパー１８０は、脱水機１６０からの脱水汚泥１６７Ｂを貯留する。重量センサ１８１は、脱水汚泥ホッパー１８０に貯留された脱水汚泥１６７Ｂの重量を検出する。検出されたセンサデータは、管理サーバ１０１に送信される。流量計１８２は、脱水汚泥ホッパー１８０から排出される脱水汚泥１６７Ｂの流量を検出する。検出されたセンサデータは、管理サーバ１０１に送信される。 The dehydrated sludge hopper 180 stores the dehydrated sludge 167B from the dehydrator 160. The weight sensor 181 detects the weight of the dehydrated sludge 167B stored in the dehydrated sludge hopper 180. FIG. The detected sensor data is transmitted to the management server 101 . The flow meter 182 detects the flow rate of the dehydrated sludge 167B discharged from the dehydrated sludge hopper 180. FIG. The detected sensor data is transmitted to the management server 101 .
　＜管理サーバ１０１のハードウェア構成例＞
　図２は、管理サーバ１０１のハードウェア構成例を示すブロック図である。管理サーバ１０１は、プロセッサ２０１と、記憶デバイス２０２と、入力デバイス２０３と、出力デバイス２０４と、通信インターフェース（通信ＩＦ）２０５と、を有する。プロセッサ２０１、記憶デバイス２０２、入力デバイス２０３、出力デバイス２０４、および通信ＩＦ２０５は、バス２０６により接続される。プロセッサ２０１は、管理サーバ１０１を制御する。記憶デバイス２０２は、プロセッサ２０１の作業エリアとなる。また、記憶デバイス２０２は、各種プログラムやデータを記憶する非一時的なまたは一時的な記録媒体である。記憶デバイス２０２としては、たとえば、ＲＯＭ（Ｒｅａｄ　Ｏｎｌｙ　Ｍｅｍｏｒｙ）、ＲＡＭ（Ｒａｎｄｏｍ　Ａｃｃｅｓｓ　Ｍｅｍｏｒｙ）、ＨＤＤ（Ｈａｒｄ　Ｄｉｓｋ　Ｄｒｉｖｅ）、フラッシュメモリがある。入力デバイス２０３は、データを入力する。入力デバイス２０３としては、たとえば、キーボード、マウス、タッチパネル、テンキー、スキャナ、マイクがある。出力デバイス２０４は、データを出力する。出力デバイス２０４としては、たとえば、ディスプレイ、プリンタ、スピーカがある。通信ＩＦ２０５は、ネットワーク１０３と接続し、データを送受信する。 <Hardware Configuration Example of Management Server 101>
FIG. 2 is a block diagram showing a hardware configuration example of the management server 101. As shown in FIG. The management server 101 has a processor 201 , a storage device 202 , an input device 203 , an output device 204 and a communication interface (communication IF) 205 . Processor 201 , storage device 202 , input device 203 , output device 204 and communication IF 205 are connected by bus 206 . A processor 201 controls the management server 101 . A storage device 202 serves as a work area for the processor 201 . Also, the storage device 202 is a non-temporary or temporary recording medium that stores various programs and data. Examples of the storage device 202 include ROM (Read Only Memory), RAM (Random Access Memory), HDD (Hard Disk Drive), and flash memory. The input device 203 inputs data. Input devices 203 include, for example, a keyboard, mouse, touch panel, numeric keypad, scanner, and microphone. The output device 204 outputs data. Output devices 204 include, for example, displays, printers, and speakers. Communication IF 205 connects to network 103 to transmit and receive data.
　＜テーブルの構成例＞
　つぎに、図３～図１７を用いて、管理サーバ１０１が読み書き可能なテーブル群の構成例について説明する。これらテーブル群は、たとえば、記憶デバイス２０２に記憶される。なお、以下のテーブル群におけるフィールドの各々について、その値が固定値、実測値、または、固定値および実測値のいずれか、が採用されるが、対象物によっては固定値（ただし、任意に設定変更可能）にしか設定できないフィールド（たとえば、フロック形成槽容量、電気代単価など）もあれば、経時的に変動する実測値しか設定できないフィールド（たとえば、水温、汚泥濃度など）もあれば、固定値および実測値のいずれでもよいフィールド（たとえば、凝集剤注入量や急速撹拌機回転数など）がある。 <Table configuration example>
Next, configuration examples of a group of tables that can be read and written by the management server 101 will be described with reference to FIGS. 3 to 17. FIG. These table groups are stored in the storage device 202, for example. For each of the fields in the table group below, either a fixed value, an actual measured value, or a fixed value and an actual measured value is adopted, but depending on the object, the fixed value (however, it can be set arbitrarily) Some fields (e.g. flocculation tank capacity, unit price of electricity, etc.) can only be set to values that can be changed, while others (e.g., water temperature, sludge concentration, etc.) can only be set to actual values that change over time. There are fields that can be both values and actual values (eg flocculant dosage, rapid stirrer speed, etc.).
　固定値および実測値のいずれでもよいフィールドについては、固定値で設定すれば計算効率が向上し、かつ、記憶デバイス２０２の使用容量の低減化を図ることができ、実測値で設定すれば、計算結果の高精度化を図ることができる。したがって、以下に示すテーブル群において、固定値および実測値のいずれでもよいフィールドについては、固定値および実測値のいずれか一方を用いて説明するが、他方で設定してもよい。 For fields that can be either fixed values or measured values, if fixed values are set, calculation efficiency can be improved and the amount of space used in the storage device 202 can be reduced. It is possible to improve the accuracy of the result. Therefore, in the table group shown below, fields that can be either fixed values or measured values will be described using either the fixed values or the measured values, but the other may be set.
　［単価管理テーブル］
　図３は、単価管理テーブルの一例を示す説明図である。単価管理テーブル３００は、各種単価を管理するテーブルである。単価管理テーブル３００は、フィールドとして、人件費単価３０１と、運搬費単価３０２と、引取費単価３０３と、メンテナンス単価３０４と、電気代単価３０５と、を有する。 [Unit price management table]
FIG. 3 is an explanatory diagram showing an example of the unit price management table. The unit price management table 300 is a table for managing various unit prices. The unit price management table 300 has, as fields, a personnel cost unit price 301 , a transportation cost unit price 302 , a pick-up cost unit price 303 , a maintenance unit price 304 , and an electricity bill unit price 305 .
　人件費単価３０１は、汚泥処理システム１０２に従事する運転員の１人当たりの１時間の労働単価である。運搬費単価３０２は、脱水汚泥１６７Ｂを汚泥処理システム１０２外に運搬する費用の単価である。引取費単価３０３は、運搬された脱水汚泥１６７Ｂの引取先に支払う費用の単価である。メンテナンス単価３０４は、汚泥処理システム１０２のメンテナンスに必要な費用の単価である。電気代単価３０５は、汚泥処理システム１０２での電気代の単価である。 The labor cost unit price 301 is the labor unit price per hour per operator engaged in the sludge treatment system 102 . The transportation cost unit price 302 is the unit cost of transporting the dehydrated sludge 167B to the outside of the sludge treatment system 102 . The collection cost unit price 303 is the unit cost to be paid to the collection destination of the transported dehydrated sludge 167B. The maintenance unit price 304 is the unit price of the cost required for maintenance of the sludge treatment system 102 . The electricity bill unit price 305 is the unit price of the electricity bill in the sludge treatment system 102 .
　［凝集剤テーブル］
　図４は、凝集剤テーブルの一例を示す説明図である。凝集剤テーブル４００は、凝集剤に関する情報を規定するテーブルである。凝集剤テーブル４００は、フィールドとして、薬品単価４０１と、原液濃度４０２と、凝集剤注入量４０３と、を有する。薬品単価４０１は、凝集剤を構成する薬品の１キログラムあたりの価格である。原液濃度４０２は、水１リットル当たりの薬品原液の濃度である。凝集剤注入量４０３は、薬液ポンプ１４０で注入される凝集剤の１秒あたりの量である。薬品単価４０１、原液濃度４０２および凝集剤注入量４０３の値は、任意に設定可能である。 [Flocculant table]
FIG. 4 is an explanatory diagram showing an example of a flocculant table. The flocculant table 400 is a table that defines information about flocculants. The flocculant table 400 has, as fields, a drug unit price 401 , a stock solution concentration 402 , and a flocculant injection amount 403 . The chemical unit price 401 is the price per kilogram of the chemical that constitutes the coagulant. Stock concentration 402 is the concentration of the chemical stock solution per liter of water. The coagulant injection amount 403 is the amount of coagulant injected by the chemical pump 140 per second. The values of the chemical unit price 401, the stock solution concentration 402, and the coagulant injection amount 403 can be set arbitrarily.
　なお、凝集剤注入量４０３については、管理サーバ１０１が下記式（１）により所定時間ごとに算出してもよい。 Note that the coagulant injection amount 403 may be calculated by the management server 101 using the following formula (1) at predetermined time intervals.
凝集剤注入量［Ｌ/ｓ］
＝薬液ポンプストローク回数［回／ｓ］×薬液ポンプストローク長［Ｌ／回］…（１） Flocculant injection amount [L/s]
= number of chemical pump strokes [times/s] x chemical pump stroke length [L/times] (1)
　［制約条件テーブル］
　図５は、制約条件テーブルの一例を示す説明図である。制約条件テーブル５００は、制約条件を規定するテーブルである。制約条件は、汚泥処理システム１０２の総合コストの算出に当たり遵守すべき条件である。制約条件テーブル５００は、フィールドとして、１人当たり最大労働時間５０１と、駆動機電流上限値５０２と、流入圧力上限値５０３と、流出圧力上限値５０４と、汚泥貯留槽容量５０５と、脱水汚泥ホッパー最大許容貯留重量５０６と、脱水汚泥の搬出予定時刻５０７と、を有する。 [Constraint table]
FIG. 5 is an explanatory diagram showing an example of a constraint condition table. The constraint table 500 is a table that defines constraints. Constraints are conditions to be complied with when calculating the total cost of the sludge treatment system 102 . Constraint condition table 500 includes, as fields, maximum working hours per person 501, upper limit of drive current 502, upper limit of inflow pressure 503, upper limit of outflow pressure 504, sludge storage tank capacity 505, maximum dewatered sludge hopper. It has an allowable storage weight 506 and a dewatered sludge scheduled discharge time 507 .
　１人当たり最大労働時間５０１は、汚泥処理システム１０２に従事する運転員１人当たりの労働時間の最大値である。駆動機電流上限値５０２は、脱水機駆動機の駆動電流の上限値である。流入圧力上限値５０３は、脱水汚泥移送ポンプ１７０の流入圧力の上限値である。流出圧力上限値５０４は、脱水汚泥移送ポンプ１７０の流出圧力の上限値である。汚泥貯留槽容量５０５は、汚泥貯留槽１２１に汚泥１２０を貯留可能な容量である。脱水汚泥ホッパー最大許容貯留重量５０６は、脱水汚泥ホッパー１８０に脱水汚泥１６７Ｂを貯留可能な最大許容重量である。脱水汚泥の搬出予定時刻５０７は、脱水汚泥１６７Ｂを汚泥処理システム１０２から搬出する予定時刻である。 The maximum working hours per person 501 is the maximum working hours per operator engaged in the sludge treatment system 102 . The driver current upper limit value 502 is the upper limit value of the drive current of the dehydrator driver. The inflow pressure upper limit 503 is the upper limit of the inflow pressure of the dehydrated sludge transfer pump 170 . The outflow pressure upper limit value 504 is the upper limit value of the outflow pressure of the dehydrated sludge transfer pump 170 . The sludge storage tank capacity 505 is a capacity that allows the sludge 120 to be stored in the sludge storage tank 121 . The dewatered sludge hopper maximum permissible storage weight 506 is the maximum permissible weight of the dehydrated sludge hopper 180 that can store the dehydrated sludge 167B. The scheduled time 507 for carrying out the dewatered sludge is the scheduled time for carrying out the dehydrated sludge 167B from the sludge treatment system 102 .
　［実測流入汚泥性状テーブル］
　図６は、実測流入汚泥性状テーブルの一例を示す説明図である。実測流入汚泥性状テーブル６００は、汚泥処理システム１０２に流入した汚泥の性状に関する実測値を記録するテーブルである。実測流入汚泥性状テーブル６００は、フィールドとして、運転日時６０１と、上流プロセス運転条件６０２と、水温６０３と、ｐＨ６０４と、電気伝導度６０５と、汚泥濃度６０６と、含水率６０７と、天候６０８と、季節６０９と、実測形成フロック性状６１０と、を有する。 [Actual measurement inflow sludge property table]
FIG. 6 is an explanatory diagram showing an example of an actually measured inflow sludge properties table. The measured inflow sludge properties table 600 is a table that records measured values relating to properties of sludge that has flowed into the sludge treatment system 102 . The actually measured inflow sludge property table 600 includes, as fields, operation date and time 601, upstream process operating conditions 602, water temperature 603, pH 604, electrical conductivity 605, sludge concentration 606, moisture content 607, weather 608, It has seasons 609 and measured formation floc properties 610 .
　運転日時６０１は、汚泥処理システム１０２を運転した日付時刻である。具体的には、たとえば、実測流入汚泥性状テーブル６００の各エントリの運転日時６０１を除く値は、その運転日時６０１から次のエントリの運転日時６０１までの時間間隔での実測値である。当該時間間隔中に実測値が複数得られる場合には、当該各エントリの値は、複数の実測値の代表値となる。代表値は、複数の実測値の平均値、中央値、最大値、最小値、または最頻値のいずれもよい（以降のテーブルでも同様。）。以下、代表値である場合も「実測値」として説明する。 The date and time of operation 601 is the date and time when the sludge treatment system 102 was operated. Specifically, for example, the values excluding the operation date and time 601 of each entry in the actually measured inflow sludge property table 600 are the measured values at the time interval from the operation date and time 601 to the operation date and time 601 of the next entry. If multiple measured values are obtained during the time interval, the value of each entry is a representative value of the multiple measured values. The representative value may be the average value, median value, maximum value, minimum value, or mode value of a plurality of measured values (the same applies to subsequent tables). In the following description, representative values are also referred to as “actual values”.
　上流プロセス運転条件６０２は、汚泥処理システム１０２の上流プロセスである水処理の運転条件である。具体的には、上流プロセス運転条件６０２は、運転日時６０１の水処理における流入汚泥性状に影響を与えると推定されるパラメータの代表値であり、たとえば、曝気風量、汚泥返送率、ＭＬＳＳ（活性汚泥浮遊物質（Ｍｉｘｅｄ　Ｌｉｑｕｏｒ　Ｓｕｓｐｅｎｄｅｄ　Ｓｏｌｉｄｓ））濃度がある。 The upstream process operating conditions 602 are operating conditions for water treatment, which is the upstream process of the sludge treatment system 102 . Specifically, the upstream process operating conditions 602 are representative values of parameters that are estimated to affect the properties of inflow sludge in water treatment at the operating date and time 601. For example, aeration air volume, sludge return rate, MLSS (activated sludge There is a concentration of suspended solids (Mixed Liquor Suspended Solids).
　水温６０３は、水温センサ１２３で検出された汚泥処理システム１０２を流れる汚泥１２０の温度の実測値である。ｐＨ６０４は、ペーハーセンサ１３２で検出された汚泥処理システム１０２を流れる汚泥１２０の水素イオン濃度の実測値である。電気伝導度６０５は、電気伝導度センサ１３３で検出された汚泥処理システム１０２に流入された汚泥１２０の電気伝導度の実測値である。 The water temperature 603 is the measured value of the temperature of the sludge 120 flowing through the sludge treatment system 102 detected by the water temperature sensor 123 . pH 604 is the measured hydrogen ion concentration of the sludge 120 flowing through the sludge treatment system 102 detected by the pH sensor 132 . The electrical conductivity 605 is the measured electrical conductivity of the sludge 120 flowing into the sludge treatment system 102 detected by the electrical conductivity sensor 133 .
　汚泥濃度６０６は、汚泥濃度センサ１３４で検出された汚泥処理システム１０２に流入された汚泥１２０の濃度の実測値である。含水率６０７は、含水率センサ１６８で検出された脱水汚泥１６７Ｂに含まれる水分の割合の実測値である。天候６０８は、晴れ、曇り、雨、雪などの運転日時６０１における気象状態である。季節６０９は、春、夏、空き、冬など１年間を天候で区切った区間である。実測形成フロック性状６１０は、運転日時６０１において流量計１３１で検出された汚泥１２０の流量の実測値である。 The sludge concentration 606 is the measured value of the concentration of the sludge 120 flowing into the sludge treatment system 102 detected by the sludge concentration sensor 134 . The moisture content 607 is an actual measurement value of the percentage of moisture contained in the dehydrated sludge 167B detected by the moisture content sensor 168 . The weather 608 is the weather conditions at the driving date 601, such as sunny, cloudy, rainy, and snowy. A season 609 is a section of one year such as spring, summer, vacancy, and winter divided by the weather. The measured formed floc property 610 is the measured value of the flow rate of the sludge 120 detected by the flow meter 131 at the operating date and time 601 .
　［フロック形成条件テーブル］
　図７は、フロック形成条件テーブルの一例を示す説明図である。フロック形成条件テーブル７００は、フロック形成条件を規定するテーブルである。フロック形成条件テーブル７００は、フィールドとして、運転日時６０１と、凝集剤注入率７０１と、急速撹拌機回転数７０２と、緩速撹拌機回転数７０３と、フロック形成槽容量７０４と、時間当たり処理量７０５と、を有する。フロック形成条件とは、脱水機がフロックを形成するために必要な条件であり、凝集剤注入率７０１、急速撹拌機回転数７０２、緩速撹拌機回転数７０３、フロック形成槽容量７０４および時間当たり処理量７０５により規定される。 [Floc formation condition table]
FIG. 7 is an explanatory diagram showing an example of a flocculation condition table. The flocculation condition table 700 is a table that defines flocculation conditions. The flocculation condition table 700 includes, as fields, an operation date and time 601, a coagulant injection rate 701, a rapid stirrer rotation speed 702, a slow stirrer rotation speed 703, a flocculation tank capacity 704, and a processing amount per hour. 705 and . The flocculation conditions are the conditions necessary for the dehydrator to form flocs. Defined by throughput 705 .
　凝集剤注入率７０１、急速撹拌機回転数７０２、緩速撹拌機回転数７０３、および時間当たり処理量７０５は、固定値または実測値のいずれで規定してもよいが、図７では、実測値を例に挙げて説明する。 The flocculant injection rate 701, the rapid stirrer rotation speed 702, the slow stirrer rotation speed 703, and the throughput per hour 705 may be defined as either fixed values or measured values, but in FIG. will be described as an example.
　凝集剤注入率７０１は、運転日時における凝集剤を注入する割合である。凝集剤注入率７０１は、原液濃度４０２と、凝集剤注入量４０３と、汚泥流量［ｍ３／ｈ］と、に基づいて算出される。汚泥流量［ｍ３／ｈ］は、フロック形成槽１５０に汚泥が流入する流量であり、たとえば、流量計１３１によって検出される。凝集剤注入率７０１は、下記式（２）により算出される。 The coagulant injection rate 701 is the rate at which the coagulant is injected at the operating date and time. The coagulant injection rate 701 is calculated based on the stock solution concentration 402, the coagulant injection amount 403, and the sludge flow rate [m 3 /h]. The sludge flow rate [m 3 /h] is the flow rate of sludge flowing into the flocculation tank 150, and is detected by the flow meter 131, for example. The coagulant injection rate 701 is calculated by the following formula (2).
凝集剤注入率［ｍｇ／Ｌ］＝原液濃度［ｍｇ／Ｌ］×凝集剤注入量［Ｌ／Ｓ］÷汚泥流量［ｍ３／ｈ］×単位換算係数…（２） Flocculant injection rate [mg/L] = Stock solution concentration [mg/L] × flocculant injection amount [L/S] ÷ sludge flow rate [m 3 /h] × unit conversion factor (2)
　急速撹拌機回転数７０２は、運転日時６０１における急速撹拌機の回転数［ｒｐｍ］の実測値である。 The rapid stirrer rotation speed 702 is the measured value of the rotation speed [rpm] of the rapid stirrer at the operating date and time 601 .
　緩速撹拌機回転数７０３は、運転日時６０１における緩速撹拌機の回転数［ｒｐｍ］の実測値である。 The slow stirrer rotation speed 703 is the measured value of the rotation speed [rpm] of the slow stirrer at the operating date and time 601 .
　フロック形成槽容量７０４は、フロック形成槽１５０の容量を示す固定値である。 The flocculation tank capacity 704 is a fixed value indicating the capacity of the flocculation tank 150 .
　時間当たり処理量７０５は、フロック形成槽１５０に汚泥が流入する流量、すなわち、上述した汚泥流量であり、たとえば、流量計１３１によって検出される。また、管理サーバ１０１は、時間当たり処理量７０５を、脱水機駆動機回転数を用いて下記式（３）により算出してもよい。 The throughput per hour 705 is the flow rate of sludge flowing into the flocculation tank 150, that is, the sludge flow rate described above, and is detected by the flow meter 131, for example. Further, the management server 101 may calculate the processing amount 705 per hour by the following formula (3) using the rotation speed of the dehydrator driving machine.
時間当たり処理量［ｍ３／ｈ］＝脱水機駆動機回転数［ｒｐｍ］×脱水機特性係数
…（３） Processing amount per hour [m 3 /h] = dehydrator driving machine rotation speed [rpm] x dehydrator characteristic coefficient (3)
　脱水機駆動機回転数は、脱水機駆動機１６６の回転数であり、脱水機駆動機１６６により検出される。脱水機駆動機回転数は、固定値でもよく実測値でもよい。脱水機特性係数は、任意の値でもよい。また、管理サーバ１０１は、脱水機駆動機１６６から検出される脱水機駆動機回転数の実測値および流量計１３１から検出される汚泥流量［ｍ３／ｈ］の実測値に基づいて機械学習により回帰式を生成し、当該回帰式における脱水機特性係数を上記式（３）に適用してもよい。 The dehydrator driver rotation speed is the rotation speed of the dehydrator driver 166 and is detected by the dehydrator driver 166 . The rotation speed of the dehydrator driving machine may be a fixed value or an actually measured value. The dehydrator characteristic factor may be any value. In addition, the management server 101 uses machine learning based on the measured value of the dehydrator driving machine rotation speed detected from the dehydrator driving machine 166 and the measured value of the sludge flow rate [m 3 /h] detected from the flow meter 131. A regression equation may be generated and the dehydrator characteristic coefficient in the regression equation may be applied to the above equation (3).
　また、管理サーバ１０１は、実測流入汚泥性状テーブル６００およびフロック形成条件テーブル７００を用いて、形成フロック性状［ｍｍ］を予測する関数ｆ１を生成する（下記式（４）を参照。）。 The management server 101 also uses the actually measured inflow sludge property table 600 and the floc formation condition table 700 to generate a function f1 for predicting the formed floc property [mm] (see formula (4) below).
形成フロック性状［ｍｍ］＝ｆ１（流入汚泥性状，フロック形成条件）…（４） Formation floc property [mm] = f1 (inflow sludge property, floc formation condition) (4)
　上記式（４）の流入汚泥性状は、たとえば、運転日時６０１の所定時間前に実測された、実測流入汚泥性状テーブル６００における上流プロセス運転条件６０２、水温６０３、ｐＨ６０４、電気伝導度６０５、汚泥濃度６０６、含水率６０７、天候６０８、季節６０９の値である。 The inflow sludge property of the above formula (4) is, for example, the upstream process operating conditions 602, water temperature 603, pH 604, electrical conductivity 605, sludge concentration in the actually measured inflow sludge property table 600 measured a predetermined time before the operation date and time 601. 606, moisture content 607, weather 608, and season 609.
　管理サーバ１０１は、上記式（４）の左辺に運転日時６０１ごとの実測形成フロック性状６１０を正解データとして入力し、上記式（４）の右辺に、運転日時６０１ごとの上述した流入汚泥性状とフロック形成条件（凝集剤注入率７０１～時間当たり処理量７０５）を学習データとして入力し、機械学習により関数ｆ１を回帰式として生成する。 The management server 101 inputs the actually measured formed floc property 610 for each operating date and time 601 to the left side of the above equation (4) as correct data, and inputs the inflow sludge properties and Floc formation conditions (coagulant injection rate 701 to processing amount per hour 705) are input as learning data, and a function f1 is generated as a regression equation by machine learning.
　［実測脱水汚泥性状テーブル］
　図８は、実測脱水汚泥性状テーブルの一例を示す説明図である。実測脱水汚泥性状テーブル８００は、汚泥処理システム１０２で脱水された脱水汚泥１６７Ｂの性状に関する実測値を記録するテーブルである。実測脱水汚泥性状テーブル８００は、フィールドとして、運転日時６０１と、実測形成フロック性状６１０と、脱水機運転条件８０１と、実測脱水汚泥性状８０２と、を有する。 [Measured dehydrated sludge property table]
FIG. 8 is an explanatory diagram showing an example of an actually measured dehydrated sludge properties table. The measured dewatered sludge property table 800 is a table for recording actual measurement values relating to the properties of the dehydrated sludge 167B dewatered in the sludge treatment system 102 . The measured dehydrated sludge property table 800 has, as fields, an operation date 601, a measured formed floc property 610, a dehydrator operating condition 801, and a measured dehydrated sludge property 802.
　脱水機運転条件８０１は、脱水機の運転に必要な条件であり、具体的には、たとえば、脱水機駆動機実測回転数８１１と、実測圧入圧力８１２と、実測付与背圧レベル８１３と、を有する。 The dehydrator operating conditions 801 are conditions necessary for the operation of the dehydrator, and specifically, for example, the dehydrator driving machine actually measured rotational speed 811, the actually measured press-in pressure 812, and the actually measured applied back pressure level 813. have.
　脱水機駆動機実測回転数８１１は、運転日時６０１における脱水機駆動機の回転数の実測値である。 The dehydrator driving machine actual rotation speed 811 is the actual measurement value of the rotation speed of the dehydrator driving machine at the operating date and time 601 .
　実測圧入圧力８１２は、運転日時６０１において脱水機に汚泥が圧入される圧力の実測値であり、圧力計１５５によって検出される。 The measured injection pressure 812 is the measured value of the pressure at which the sludge is injected into the dehydrator at the operation date and time 601, and is detected by the pressure gauge 155.
　実測付与背圧レベル８１３は、運転日時６０１における背圧付与板１６５の位置であり、位置センサ１６１～１６４によって検出される。 The measured applied back pressure level 813 is the position of the back pressure applying plate 165 at the operation date and time 601, and is detected by the position sensors 161-164.
　実測脱水汚泥性状８０２は、運転日時６０１における脱水機で脱水された脱水汚泥１６７Ｂの性状を示す実測値であり、具体的には、たとえば、運転日時６０１において含水率センサ１６８で検出された含水率６０７に所定の単位換算係数を乗じることで求められる。 The measured dehydrated sludge property 802 is a measured value indicating the property of the dewatered sludge 167B dehydrated by the dehydrator at the operation date and time 601. Specifically, for example, the water content detected by the water content sensor 168 at the operation date and time 601. It is obtained by multiplying 607 by a predetermined unit conversion factor.
　管理サーバ１０１は、実測脱水汚泥性状テーブル８００を用いて、脱水汚泥性状［ｔ／ｍ３］を予測する関数ｆ２を生成する（下記式（５）を参照。）。 The management server 101 uses the actually measured dehydrated sludge property table 800 to generate a function f2 for predicting the dehydrated sludge property [t/m 3 ] (see formula (5) below).
脱水汚泥性状［ｔ／ｍ３］＝ｆ２（形成フロック性状，脱水機運転条件）…（５） Dehydrated sludge properties [t/m 3 ] = f2 (formed floc properties, dehydrator operating conditions) (5)
　管理サーバ１０１は、上記式（５）の左辺に運転日時６０１ごとの実測脱水汚泥性状８０２を正解データとして入力し、上記式（５）の右辺に、運転日時６０１ごとの実測形成フロック性状６１０および脱水機運転条件８０１を学習データとして入力し、機械学習により、関数ｆ２を回帰式として生成する。 The management server 101 inputs the measured dehydrated sludge property 802 for each operating date and time 601 to the left side of the above equation (5) as correct data, and the right side of the above formula (5) to the measured formed floc property 610 for each operating date and time 601 and A dehydrator operating condition 801 is input as learning data, and a function f2 is generated as a regression equation by machine learning.
　［実測脱水汚泥量テーブル］
　図９は、実測脱水汚泥量テーブルの一例を示す説明図である。実測脱水汚泥量テーブル９００は、汚泥処理システム１０２で脱水された脱水汚泥１６７Ｂの量に関する実測値を記録するテーブルである。実測脱水汚泥量テーブル９００は、フィールドとして、運転日９０１と、実測脱水汚泥量９０２と、を有する。 [Measured dewatered sludge volume table]
FIG. 9 is an explanatory diagram showing an example of a measured dehydrated sludge amount table. The actually measured dewatered sludge amount table 900 is a table that records the actually measured value regarding the amount of the dehydrated sludge 167B dewatered in the sludge treatment system 102 . The measured dehydrated sludge amount table 900 has an operation date 901 and a measured dewatered sludge amount 902 as fields.
　運転日９０１は、汚泥処理システム１０２を運転した年月日である。実測脱水汚泥量９０２は、運転日における脱水汚泥量の実測値であり、具体的には、たとえば、重量センサ１８１により検出される。 The operation date 901 is the date when the sludge treatment system 102 was operated. The actually measured dewatered sludge amount 902 is the actually measured value of the dehydrated sludge amount on the day of operation, and is detected by the weight sensor 181, for example.
　管理サーバ１０１は、実測脱水汚泥性状テーブル８００および実測脱水汚泥量テーブル９００を用いて、脱水汚泥量［ｔ／日］を予測する関数ｆ３を生成する（下記式（６）を参照。）。 The management server 101 uses the actually measured dehydrated sludge property table 800 and the actually measured dehydrated sludge amount table 900 to generate a function f3 for predicting the amount of dehydrated sludge [t/day] (see formula (6) below).
脱水汚泥量［ｔ／日］
＝ｆ３（脱水汚泥性状［ｔ／ｍ３］，計画処理対象汚泥量［ｍ３／日］，脱水プロセス運転条件）…（６） Amount of dewatered sludge [t/day]
= f3 (dewatered sludge properties [t/m 3 ], planned treatment target sludge volume [m 3 /day], dehydration process operating conditions) (6)
　管理サーバ１０１は、上記式（６）の左辺に運転日９０１ごとの実測脱水汚泥量９０２を正解データとして入力し、上記式（６）の右辺に、運転日９０１ごとの実測脱水汚泥性状８０２、計画処理対象汚泥量および脱水プロセス運転条件を学習データとして入力し、機械学習により、関数ｆ３を回帰式として生成する。 The management server 101 inputs the measured dewatered sludge amount 902 for each operation day 901 to the left side of the above equation (6) as correct data, and inputs the measured dewatered sludge property 802 for each operation day 901 to the right side of the equation (6). A planned treatment target sludge amount and dehydration process operating conditions are input as learning data, and a function f3 is generated as a regression equation by machine learning.
　上記式（６）の右辺の計画処理対象汚泥量［ｍ３／日］とは、計画処理対象日における汚泥１２０の量である。関数ｆ３の生成時には、管理サーバ１０１は、過去の計画処理対象日における汚泥１２０の量を下記式（７）により算出する。 The planned treatment target sludge amount [m 3 /day] on the right side of the above equation (6) is the amount of sludge 120 on the planned treatment target day. When generating the function f3, the management server 101 calculates the amount of sludge 120 on the past planned processing target date using the following formula (7).
計画処理対象汚泥量［ｍ３／日］
＝時間当たり処理量［ｍ３／ｈ］×（汚泥処理終了時刻－汚泥処理開始時刻）…（７） Amount of planned sludge to be treated [m 3 /day]
= amount of treatment per hour [m 3 /h] × (end time of sludge treatment - start time of sludge treatment) (7)
　上記式（７）の時間当たり処理量［ｍ３／ｈ］は、過去の計画処理対象日となる運転日時６０１の時間当たり処理量７０５である。汚泥処理終了時刻は、過去の計画処理対象日における汚泥処理の終了時刻であり、汚泥処理開始時刻は、過去の計画処理対象日における汚泥処理の開始時刻である。 The processing amount per hour [m 3 /h] in the above formula (7) is the processing amount per hour 705 of the operation date and time 601, which is the past planned processing target day. The sludge treatment end time is the end time of the sludge treatment on the past planned treatment day, and the sludge treatment start time is the start time of the sludge treatment on the past planned treatment day.
　上記式（７）は、過去の計画処理対象日の各々について適用されるが、時間当たり処理量７０５の実測値は、運転日時６０１ごとにフロック形成条件テーブル７００に格納されている。したがって、過去の計画処理対象日の各々の計画処理対象汚泥量［ｍ３／日］は、当該日の時間当たり処理量［ｍ３／ｈ］の代表値（平均値、中央値、最大値、最小値、または最頻値のいずれか）に、当該日の（汚泥処理終了時刻－汚泥処理開始時刻）を乗じた値となる。 Equation (7) above is applied to each of the past planned processing target days, but the actually measured value of the processing amount 705 per hour is stored in the flocculation condition table 700 for each operation date 601 . Therefore, the planned treatment target sludge volume [m 3 / day] for each planned treatment target day in the past is the representative value (average value, median value, maximum value, (either the minimum value or the most frequent value) multiplied by (sludge treatment end time - sludge treatment start time) for that day.
　また、上記式（６）の脱水プロセス運転条件は、脱水機運転条件８０１と、フロック形成条件（凝集剤注入率７０１、急速撹拌機回転数７０２、緩速撹拌機回転数７０３、フロック形成槽容量７０４および時間当たり処理量７０５）と、を含む実測値である。したがって、関数ｆ３の生成時には、管理サーバ１０１は、過去の計画処理対象日における脱水プロセス運転条件を上記式（６）に入力することになる。 Further, the dehydration process operating conditions of the above formula (6) are the dehydrator operating conditions 801 and flocculation conditions (coagulant injection rate 701, rapid stirrer rotation speed 702, slow stirrer rotation speed 703, flocculation tank capacity 704 and throughput per hour 705). Therefore, when the function f3 is generated, the management server 101 inputs the dehydration process operation conditions for the past planned processing target date into the above equation (6).
　［汚泥圧入ポンプ実測テーブル］
　図１０は、汚泥圧入ポンプ実測テーブルの一例を示す説明図である。汚泥圧入ポンプ実測テーブル１０００は、汚泥圧入ポンプ１３０に関する実測値を記録するテーブルである。汚泥圧入ポンプ実測テーブルは、フィールドとして、運転日時６０１と、汚泥圧入ポンプ実測消費電力量１００１と、実測圧入圧力８１２と、汚泥圧入ポンプ実測回転数１００２と、を有する。 [Sludge injection pump actual measurement table]
FIG. 10 is an explanatory diagram showing an example of a sludge injection pump actual measurement table. The sludge injection pump actual measurement table 1000 is a table for recording actual measurement values regarding the sludge injection pump 130 . The sludge injection pump actual measurement table has, as fields, an operation date and time 601, a sludge injection pump actual power consumption 1001, an actual injection pressure 812, and a sludge injection pump actual rotation speed 1002.
　汚泥圧入ポンプ実測消費電力量１００１は、運転日時６０１において汚泥圧入ポンプ１３０が消費した電力量の実測値であり、不図示の電力量計により検出される。 The sludge injection pump measured power consumption 1001 is the measured value of the power consumed by the sludge injection pump 130 at the operating date and time 601, and is detected by a power meter (not shown).
　汚泥圧入ポンプ実測回転数１００２は、運転日時６０１における汚泥圧入ポンプ１３０の回転数の実測値であり、汚泥圧入ポンプ１３０により検出される。 The actually measured rotation speed of the sludge injection pump 1002 is the actual measurement value of the rotation speed of the sludge injection pump 130 at the operating date and time 601 and is detected by the sludge injection pump 130 .
　管理サーバ１０１は、汚泥圧入ポンプ実測テーブル１０００を用いて、汚泥圧入ポンプ消費電力量［ｋＷｈ］を予測する関数ｆ３を生成する（下記式（８）を参照。）。 The management server 101 uses the sludge injection pump actual measurement table 1000 to generate a function f3 for predicting the sludge injection pump power consumption [kWh] (see formula (8) below).
汚泥圧入ポンプ消費電力量［ｋＷｈ］
＝ｆ３（圧入圧力、汚泥圧入ポンプ回転数、運転時間）…（８） Sludge injection pump power consumption [kWh]
= f3 (injection pressure, sludge injection pump rotation speed, operating time) (8)
　管理サーバ１０１は、上記式（８）の左辺に運転日時６０１ごとの汚泥圧入ポンプ実測消費電力量１００１を正解データとして入力し、上記式（８）の右辺に運転日時６０１ごとの実測圧入圧力８１２、汚泥圧入ポンプ実測回転数１００２および運転時間を学習データとして入力し、機械学習により、関数ｆ４を回帰式として生成する。なお、運転時間は、連続する運転日時６０１の値の時間間隔である。 The management server 101 inputs the measured power consumption 1001 of the sludge injection pump for each operation date and time 601 to the left side of the above equation (8) as correct data, and the measured injection pressure 812 for each operation date and time 601 to the right side of the above equation (8). , the actually measured number of rotations of the sludge injection pump 1002 and the operation time are input as learning data, and the function f4 is generated as a regression equation by machine learning. It should be noted that the operating time is a time interval between consecutive values of the operating date and time 601 .
　［フロック形成槽実測テーブル］
　図１１は、フロック形成槽実測テーブルの一例を示す説明図である。フロック形成槽実測テーブル１１００は、フロック形成槽１５０に関する実測値を記録するテーブルである。フロック形成槽実測テーブル１１００は、フィールドとして、運転日時６０１と、フロック形成槽実測消費電力量１１０１と、急速撹拌機実測回転数１１０２と、緩速撹拌機実測回転数１１０３と、実測形成フロック性状６１０と、を有する。 [Floc formation tank measurement table]
FIG. 11 is an explanatory diagram showing an example of a flocculation tank actual measurement table. The flocculation tank actual measurement table 1100 is a table for recording the measured values regarding the flocculation tank 150 . The floc formation tank actual measurement table 1100 includes, as fields, an operation date and time 601, a floc formation tank measured power consumption 1101, a rapid agitator actual measurement rotational speed 1102, a slow agitator actual rotational speed 1103, and an actual floc formation property 610. and have
　フロック形成槽実測消費電力量１１０１は、運転日時６０１においてフロック形成槽１５０が消費した電力量の実測値であり、不図示の電力量計により検出される。 The flocculation tank measured power consumption 1101 is the measured value of the power consumed by the flocculation tank 150 at the operating date and time 601, and is detected by a power meter (not shown).
　急速撹拌機実測回転数１１０２は、運転日時６０１において実測された急速撹拌機１５１の回転数の実測値であり、モータ１５３で検出される。 The measured rapid stirrer rotation speed 1102 is the measured value of the rotation speed of the rapid stirrer 151 actually measured at the operating date and time 601 and is detected by the motor 153 .
　緩速撹拌機実測回転数１１０３は、運転日時６０１において実測された緩速撹拌機１５２の回転数の実測値であり、モータ１５４で検出される。 The measured rotation speed of the slow stirrer 1103 is the rotation speed of the slow stirrer 152 actually measured at the operating date and time 601 , and is detected by the motor 154 .
　管理サーバ１０１は、フロック形成槽実測テーブル１１００を用いて、フロック形成槽消費電力量［ｋＷｈ］を予測する関数ｆ５を生成する（下記式（９）を参照。）。 The management server 101 uses the flocculation tank actual measurement table 1100 to generate a function f5 for predicting the power consumption [kWh] of the flocculation tank (see formula (9) below).
フロック形成槽消費電力量［ｋＷｈ］
＝ｆ５（急速撹拌機回転数、緩速撹拌機回転数、形成フロック性状、運転時間）…（９） Floc formation tank power consumption [kWh]
= f5 (speed of rapid stirrer, speed of slow stirrer, properties of flocs formed, operation time) (9)
　管理サーバ１０１は、上記式（９）の左辺に運転日時６０１ごとのフロック形成槽実測消費電力量１１０１を正解データとして入力し、上記式（９）の右辺に、運転日時６０１ごとの急速撹拌機実測回転数１１０２、緩速撹拌機実測回転数１１０３および運転時間を学習データとして入力し、機械学習により、関数ｆ５を回帰式として生成する。なお、運転時間は、連続する運転日時６０１の値の時間間隔である。 The management server 101 inputs the actual power consumption 1101 of the flocculation tank for each operating date and time 601 to the left side of the above equation (9) as correct data, and inputs the rapid stirrer power consumption for each operating date and time 601 to the right side of the above equation (9). The actually measured number of rotations 1102, the actually measured number of rotations 1103 of the slow stirrer, and the operation time are inputted as learning data, and the function f5 is generated as a regression equation by machine learning. It should be noted that the operating time is a time interval between consecutive values of the operating date and time 601 .
　［脱水機実測テーブル］
　図１２は、脱水機実測テーブルの一例を示す説明図である。脱水機実測テーブル１２００は、脱水機１６０に関する実測値を記録するテーブルである。脱水機実測テーブル１２００は、フィールドとして、運転日時６０１と、脱水機実測消費電力量１２０１と、脱水機駆動機実測回転数８１１と、実測付与背圧レベル８１３と、実測形成フロック性状６１０と、時間当たり処理量７０５と、を有する。 [Dehydrator measurement table]
FIG. 12 is an explanatory diagram showing an example of a dehydrator actual measurement table. The dehydrator actual measurement table 1200 is a table for recording actual measurement values regarding the dehydrator 160 . The dehydrator actual measurement table 1200 includes, as fields, an operation date and time 601, a dehydrator actual power consumption 1201, a dehydrator drive actual rotation speed 811, an actual applied back pressure level 813, an actual formed floc property 610, a time per throughput 705;
　脱水機実測消費電力量１２０１は、運転日時６０１において脱水機が消費した電力量の実測値であり、不図示の電力量計により検出される。 The dehydrator measured power consumption 1201 is the measured value of the power consumed by the dehydrator at the operating date and time 601, and is detected by a power meter (not shown).
　管理サーバ１０１は、脱水機実測テーブル１２００を用いて、脱水機消費電力量［ｋＷｈ］を予測する関数ｆ６を生成する（下記式（１０）を参照。）。 The management server 101 uses the dehydrator actual measurement table 1200 to generate a function f6 for predicting the dehydrator power consumption [kWh] (see formula (10) below).
脱水機消費電力量［ｋＷｈ］
＝ｆ６（脱水機駆動機回転数、付与背圧レベル、形成フロック性状、時間当たり処理量、運転時間）…（１０） Dehydrator power consumption [kWh]
= f6 (rotation speed of dehydrator driving machine, applied back pressure level, properties of flocs formed, throughput per hour, operating time) (10)
　管理サーバ１０１は、上記式（１０）の左辺に運転日時６０１ごとの脱水機実測消費電力量１２０１を正解データとして入力し、上記式（１０）の右辺に、運転日時６０１ごとの脱水機実測消費電力量１２０１、脱水機駆動機実測回転数８１１、実測付与背圧レベル８１３、実測形成フロック性状６１０、時間当たり処理量７０５および運転時間を学習データとして入力し、機械学習により、関数ｆ６を回帰式として生成する。なお、運転時間は、連続する運転日時６０１の値の時間間隔である。 The management server 101 inputs the measured power consumption of the dehydrator 1201 for each operating date and time 601 to the left side of the above equation (10) as correct data, and inputs the measured dehydrator power consumption for each operating date and time 601 to the right side of the above equation (10). Electric energy 1201, dehydrator drive actually measured rotation speed 811, actually measured applied back pressure level 813, actually measured formed floc property 610, throughput per hour 705 and operating time are input as learning data, and the function f6 is calculated by machine learning as a regression equation. Generate as It should be noted that the operating time is a time interval between consecutive values of the operating date and time 601 .
　［脱水汚泥移送ポンプ実測テーブル］
　図１３は、脱水汚泥移送ポンプ実測テーブルの一例を示す説明図である。脱水汚泥移送ポンプ実測テーブル１３００は、脱水汚泥移送ポンプ１７０に関する実測値を記録するテーブルである。脱水汚泥移送ポンプ実測テーブル１３００は、フィールドとして、運転日時６０１と、脱水汚泥移送ポンプ実測消費電力量１３０１と、実測脱水汚泥性状８０２と、脱水汚泥移送ポンプ実測回転数１３０２と、実測吐出圧力１３０３と、を有する。 [Dewatered sludge transfer pump actual measurement table]
FIG. 13 is an explanatory diagram showing an example of a dehydrated sludge transfer pump actual measurement table. The dehydrated sludge transfer pump actual measurement table 1300 is a table for recording actual measurement values relating to the dehydrated sludge transfer pump 170 . The dewatered sludge transfer pump actual measurement table 1300 includes, as fields, an operation date and time 601, a dewatered sludge transfer pump actually measured power consumption 1301, an actually measured dewatered sludge property 802, a dewatered sludge transfer pump actually measured rotation speed 1302, and an actually measured discharge pressure 1303. , has
　脱水汚泥移送ポンプ実測消費電力量１３０１は、運転日時６０１において脱水汚泥移送ポンプ１７０が消費した電力量の実測値であり、不図示の電力量計により検出される。 The dehydrated sludge transfer pump measured power consumption 1301 is the measured value of the power consumed by the dehydrated sludge transfer pump 170 at the operating date and time 601, and is detected by a power meter (not shown).
　脱水汚泥移送ポンプ実測回転数１３０２は、運転日時６０１における脱水汚泥移送ポンプ１７０の回転数の実測値であり、脱水汚泥移送ポンプ１７０により検出される。 The actual measurement rotation speed 1302 of the dehydrated sludge transfer pump is the actual measurement value of the rotation speed of the dewatered sludge transfer pump 170 at the operating date and time 601 and is detected by the dewatered sludge transfer pump 170 .
　実測吐出圧力１３０３は、運転日時６０１において脱水汚泥移送ポンプ１７０が脱水汚泥ホッパー１８０に脱水汚泥１６７Ｂを吐出する吐出圧力の実測値であり、圧力計１７１によって検出される。 The measured discharge pressure 1303 is the measured value of the discharge pressure at which the dewatered sludge transfer pump 170 discharges the dehydrated sludge 167B to the dewatered sludge hopper 180 at the operating date and time 601, and is detected by the pressure gauge 171.
　管理サーバ１０１は、脱水汚泥移送ポンプ実測テーブル１３００を用いて、脱水汚泥移送ポンプ消費電力量［ｋＷｈ］を予測する関数ｆ７を生成する（下記式（１１）を参照。）。 The management server 101 uses the dewatered sludge transfer pump actual measurement table 1300 to generate a function f7 for predicting the power consumption [kWh] of the dewatered sludge transfer pump (see formula (11) below).
脱水汚泥移送ポンプ消費電力量［ｋＷｈ］
＝ｆ７（脱水汚泥性状、脱水汚泥移送ポンプ回転数、運転時間）…（１１） Dewatered sludge transfer pump power consumption [kWh]
= f7 (dewatered sludge property, dewatered sludge transfer pump rotation speed, operating time) (11)
　管理サーバ１０１は、上記式（１１）の左辺に運転日時６０１ごとの脱水汚泥移送ポンプ実測消費電力量１３０１を正解データとして入力し、上記式（１１）の右辺に運転日時６０１ごとの実測脱水汚泥性状８０２、脱水汚泥移送ポンプ実測回転数１３０２、および運転時間を学習データとして入力し、機械学習により、関数ｆ７を回帰式として生成する。なお、運転時間は、連続する運転日時６０１の値の時間間隔である。 The management server 101 inputs the measured power consumption 1301 of the dehydrated sludge transfer pump for each operation date and time 601 to the left side of the above equation (11) as correct data, and the measured dehydrated sludge for each operation date and time 601 to the right side of the above equation (11). The properties 802, the actual rotation speed 1302 of the dehydrated sludge transfer pump, and the operation time are input as learning data, and the function f7 is generated as a regression equation by machine learning. It should be noted that the operating time is a time interval between consecutive values of the operating date and time 601 .
　また、管理サーバ１０１は、実測脱水汚泥量テーブル９００および脱水汚泥移送ポンプ実測テーブル１３００を用いて、汚泥移送ポンプ吐出圧力を予測する関数ｆ９を生成する（下記式（１２）を参照。）。 The management server 101 also uses the measured dehydrated sludge amount table 900 and the dehydrated sludge transfer pump actual measurement table 1300 to generate a function f9 for predicting the sludge transfer pump discharge pressure (see formula (12) below).
汚泥移送ポンプ吐出圧力＝ｆ８（脱水汚泥性状、脱水汚泥量）…（１２） Sludge transfer pump discharge pressure = f8 (dewatered sludge property, dehydrated sludge amount) (12)
　管理サーバ１０１は、上記式（１２）の左辺に運転日時６０１ごとの実測吐出圧力１３０３を正解データとして入力し、上記式（１２）の右辺に運転日時６０１ごとの実測脱水汚泥性状８０２および実測脱水汚泥量９０２を学習データとして入力し、機械学習により、関数ｆ８を回帰式として生成する。 The management server 101 inputs the measured discharge pressure 1303 for each operation date and time 601 to the left side of the above equation (12) as correct data, and the right side of the above equation (12) for each operation date and time 601 The actually measured dewatered sludge property 802 and the actually measured dewatered The sludge amount 902 is input as learning data, and a function f8 is generated as a regression equation by machine learning.
　［運転員実測テーブル］
　図１４は、運転員実測テーブルの一例を示す説明図である。運転員実測テーブル１４００は、運転員に関する実測値を記録するテーブルである。運転員実測テーブル１４００は、フィールドとして、運転日９０１と、人数１４０１と、実労働時間１４０２と、を有する。 [Operator measurement table]
FIG. 14 is an explanatory diagram showing an example of an operator actual measurement table. The operator actual measurement table 1400 is a table for recording actual measurement values relating to operators. The operator actual measurement table 1400 has, as fields, an operating date 901, a number of persons 1401, and an actual working hours 1402. FIG.
　人数１４０１は、運転日９０１に汚泥処理システム１０２の運転に従事した運転員数である。実労働時間１４０２は、運転日９０１に汚泥処理システム１０２の運転に従事した運転員の労働時間である。人数１４０１および実労働時間１４０２は、たとえば、不図示の労務管理システムから取得される。 The number of people 1401 is the number of operators engaged in the operation of the sludge treatment system 102 on the operating day 901. The actual working hours 1402 are the working hours of operators engaged in the operation of the sludge treatment system 102 on the operating day 901 . The number of people 1401 and actual working hours 1402 are acquired from, for example, a labor management system (not shown).
　［メンテナンス管理テーブル］
　図１５は、メンテナンス管理テーブルの一例を示す説明図である。メンテナンス管理テーブル１５００は、汚泥処理システム１０２のメンテナンス頻度を管理するテーブルである。メンテナンス管理テーブル１５００は、フィールドとして、運転期間１５０１と、メンテナンス回数１５０２と、を有する。 [Maintenance management table]
FIG. 15 is an explanatory diagram of an example of a maintenance management table. The maintenance management table 1500 is a table for managing maintenance frequency of the sludge treatment system 102 . The maintenance management table 1500 has operation period 1501 and maintenance frequency 1502 as fields.
　運転期間１５０１は、汚泥処理システム１０２が運転した一定の連続日数であり、当該連続日数の開始日および終了日で規定される。一定の連続日数は、たとえば、１ケ月、３か月、６か月、１年などである。 The operation period 1501 is a fixed number of consecutive days during which the sludge treatment system 102 has been operated, and is defined by the start date and end date of the consecutive days. The constant number of consecutive days is, for example, one month, three months, six months, one year, or the like.
　メンテナンス回数１５０２は、運転期間１５０１において実施された汚泥処理システム１０２のメンテナンスの回数である。 The number of times of maintenance 1502 is the number of times of maintenance of the sludge treatment system 102 performed during the operation period 1501 .
　管理サーバ１０１は、メンテナンス管理テーブル１５００を用いて、メンテナンス頻度［回／運転期間］を予測する関数ｆ９を含む回帰式を生成する（下記式（１３）を参照。）。 The management server 101 uses the maintenance management table 1500 to generate a regression equation including a function f9 that predicts the maintenance frequency [times/operating period] (see equation (13) below).
メンテナンス頻度［回／運転期間］＝ｆ９（形成フロック性状（または流入汚泥性状），脱水汚泥性状）×機器運転時間…（１３） Maintenance frequency [times/operating period] = f9 (formed floc property (or inflow sludge property), dehydrated sludge property) x equipment operating time (13)
　管理サーバ１０１は、上記式（１３）の左辺に運転期間１５０１ごとのメンテナンス回数１５０２を正解データとして入力し、上記式（１３）の右辺に、運転期間１５０１ごとの運転日時６０１の実測形成フロック性状６１０の実測値、運転期間１５０１ごとの運転日時６０１の実測脱水汚泥性状８０２の実測値、および運転期間１５０１ごとの機器運転時間を学習データとして入力し、機械学習により、関数ｆ９を含む回帰式を生成する。 The management server 101 inputs the number of times of maintenance 1502 for each operation period 1501 to the left side of the above equation (13) as correct data, and inputs the actual measurement formation floc property of the operation date and time 601 for each operation period 1501 to the right side of the above equation (13). 610, the measured dewatered sludge property 802 at the operating date and time 601 for each operating period 1501, and the equipment operating time for each operating period 1501 are input as learning data, and a regression equation including the function f9 is calculated by machine learning. Generate.
　なお、機器運転時間は、下記式（１４）により、運転期間１５０１ごとに算出される。 It should be noted that the equipment operating time is calculated for each operating period 1501 by the following formula (14).
機器運転時間［ｈ］＝計画処理対象汚泥量［ｍ３／日］÷時間当たり処理量［ｍ３／ｈ］×運転日数［日］…（１４） Equipment operating time [h] = Planned amount of sludge to be treated [m 3 /day] ÷ Treatment amount per hour [m 3 /h] × Operating days [day] (14)
　過去の計画処理対象日の各々の計画処理対象汚泥量［ｍ３／日］は、当該日の時間当たり処理量［ｍ３／ｈ］の代表値（平均値、中央値、最大値、最小値、または最頻値のいずれか）に、当該日の（汚泥処理終了時刻－汚泥処理開始時刻）を乗じた値となる。 The planned treatment target sludge volume [m 3 / day] for each planned treatment target day in the past is the representative value (average value, median value, maximum value, minimum value , or mode) multiplied by (sludge treatment end time - sludge treatment start time) of the day.
　また、機器運転時間［ｈ］は、単純に、運転期間１５０１における稼働日数に１日当たりの稼働時間を乗じた値でもよい。 Also, the device operating time [h] may simply be a value obtained by multiplying the number of operating days in the operating period 1501 by the operating time per day.
　［汚泥流入出収支テーブル］
　図１６は、汚泥流入出収支テーブルの一例を示す説明図である。汚泥流入出収支テーブル１６００は、汚泥処理システム１０２の汚泥流入出収支を管理するテーブルである。汚泥流入出収支テーブル１６００は、フィールドとして、運転日時６０１と、実測流入汚泥量１６０１と、実測流出汚泥量１６０２と、実測水位１６０３と、を有する。 [Sludge inflow and outflow balance table]
FIG. 16 is an explanatory diagram showing an example of a sludge inflow/outflow balance table. The sludge inflow/outflow balance table 1600 is a table for managing the sludge inflow/outflow balance of the sludge treatment system 102 . The sludge inflow balance table 1600 has, as fields, an operation date 601, a measured inflow sludge amount 1601, a measured outflow sludge amount 1602, and a measured water level 1603.
　実測流入汚泥量１６０１は、運転日時６０１における水処理システムから汚泥貯留槽１２１への汚泥１２０の流入量の実測値である。当該実測値は、たとえば、運転日時６０１において流量計１２４によって検出された汚泥流量の代表値に当該運転日時６０１の時間間隔を乗じた値である。 The measured inflow sludge amount 1601 is the measured value of the inflow amount of sludge 120 from the water treatment system to the sludge storage tank 121 at the operation date and time 601 . The measured value is, for example, a value obtained by multiplying the representative value of the sludge flow rate detected by the flowmeter 124 at the operating date and time 601 by the time interval of the operating date and time 601 .
　実測流出汚泥量１６０２は、運転日時６０１における汚泥貯留槽からの汚泥の流出量の実測値である。当該実測値は、たとえば、運転日時６０１において流量計１３１によって検出された汚泥流量の代表値に当該運転日時６０１の時間間隔を乗じた値である。 The measured outflow sludge amount 1602 is the measured value of the outflow amount of sludge from the sludge storage tank at the operation date and time 601 . The measured value is, for example, a value obtained by multiplying the representative value of the sludge flow rate detected by the flowmeter 131 at the operating date and time 601 by the time interval of the operating date and time 601 .
　実測水位１６０３は、運転日時６０１における汚泥貯留槽１２１の水位の実測値であり、水位計１２２により検出される。 The measured water level 1603 is the measured value of the water level of the sludge storage tank 121 at the operating date and time 601 and is detected by the water level gauge 122 .
　また、管理サーバ１０１は、汚泥流入出収支テーブル１６００を用いて、今後ｔ時間の汚泥流出入収支を予測する関数ｆ１０を生成する（下記式（１５）、（１６）を参照。）。 The management server 101 also uses the sludge inflow/outflow balance table 1600 to generate a function f10 that predicts the sludge inflow/outflow balance for the next t hours (see formulas (15) and (16) below).
今後ｔ時間の汚泥流出入収支
＝ｆ１０（流入汚泥量，計画処理対象汚泥量，ｔ）…（１５） Sludge inflow/outflow balance for t hours from now on = f10 (amount of inflow sludge, amount of planned treatment target sludge, t) (15)
流入汚泥量＝ｆ１１（ｔ時間前の流入汚泥性状）…（１６） Amount of inflow sludge = f11 (property of inflow sludge before t hours) (16)
　管理サーバ１０１は、上記式（１６）の左辺に運転日時６０１ごとの実測流入汚泥量１６０１を正解データとして入力し、上記式（１６）の右辺に運転日時６０１よりもｔ時間前の運転日時６０１における流入汚泥性状（運転日時６０１のｔ時間前に実測された、実測流入汚泥性状テーブル６００における上流プロセス運転条件６０２、水温６０３、ｐＨ６０４、電気伝導度６０５、汚泥濃度６０６、含水率６０７、天候６０８、季節６０９）を学習データとして入力し、機械学習により、流入汚泥量を予測する関数ｆ１１を回帰式として生成する。 The management server 101 inputs the measured inflow sludge amount 1601 for each operation date and time 601 to the left side of the above equation (16) as correct data, and the operation date and time 601 t hours before the operation date 601 to the right side of the above equation (16) Inflow sludge properties (upstream process operating conditions 602, water temperature 603, pH 604, electrical conductivity 605, sludge concentration 606, water content 607, weather 608 in the actually measured inflow sludge property table 600, measured t hours before the operation date and time 601 , season 609) are input as learning data, and a function f11 for predicting the amount of inflow sludge is generated as a regression equation by machine learning.
　また、管理サーバ１０１は、上記式（１５）の左辺に運転日時６０１ごとの（実測流入汚泥量１６０１－実測流出汚泥量１６０２）を正解データとして入力し、上記式（１６）の右辺に運転日時６０１よりもｔ時間前の運転日時６０１における実測流入汚泥量１６０１および運転日時６０１よりもｔ時間前の計画処理対象汚泥量（上記式（７）で算出）を学習データとして入力し、機械学習により、今後ｔ時間の汚泥流出入収支を予測する関数ｆ１０を回帰式として生成する。 In addition, the management server 101 inputs (actually measured inflow sludge amount 1601−actually measured outflow sludge amount 1602) for each operation date 601 to the left side of the above equation (15) as correct data, and inputs the operation date and time to the right side of the above equation (16). The measured inflow sludge amount 1601 at the operation date and time 601 t hours before 601 and the planned treatment target sludge amount (calculated by the above formula (7)) t hours before the operation date and time 601 are input as learning data, and machine learning , a function f10 for predicting the sludge inflow/outflow balance for t hours from now on is generated as a regression equation.
　［脱水汚泥流入出収支テーブル］
　図１７は、脱水汚泥流入出収支テーブルの一例を示す説明図である。脱水汚泥流入出収支テーブル１７００は、汚泥処理システム１０２の脱水汚泥流入出収支を管理するテーブルである。脱水汚泥流入出収支テーブル１７００は、フィールドとして、運転日時６０１と、実測流入脱水汚泥量１７０１と、実測流出脱水汚泥量１７０２と、を有する。 [Dehydrated sludge inflow and outflow balance table]
FIG. 17 is an explanatory diagram showing an example of a dehydrated sludge inflow/outflow balance table. The dehydrated sludge inflow/outflow balance table 1700 is a table for managing the dehydrated sludge inflow/outflow balance of the sludge treatment system 102 . The dewatered sludge inflow/outflow balance table 1700 has, as fields, an operation date/time 601, a measured inflow dewatered sludge amount 1701, and a measured outflow dehydrated sludge amount 1702.
　実測流入脱水汚泥量１７０１は、運転日時６０１における脱水汚泥ホッパー１８０への脱水汚泥１６７Ｂの流入量の実測値である。当該実測値は、たとえば、運転日時６０１において流量計１６９によって検出された脱水汚泥流量の代表値に当該運転日時６０１の時間間隔を乗じた値である。 The measured inflow dehydrated sludge amount 1701 is the measured value of the inflow amount of the dehydrated sludge 167B into the dewatered sludge hopper 180 at the operation date and time 601 . The measured value is, for example, a value obtained by multiplying the representative value of the dehydrated sludge flow rate detected by the flowmeter 169 at the operating date and time 601 by the time interval of the operating date and time 601 .
　実測流出脱水汚泥量１７０２は、運転日時６０１における脱水汚泥ホッパー１８０からの脱水汚泥１６７Ｂの流出量の実測値である。当該実測値は、たとえば、運転日時６０１において流量計１８２によって検出された脱水汚泥流量の代表値に当該運転日時６０１の時間間隔を乗じた値である。 The measured outflow dewatered sludge amount 1702 is the measured value of the outflow amount of the dewatered sludge 167B from the dewatered sludge hopper 180 at the operation date and time 601. The measured value is, for example, a value obtained by multiplying the representative value of the dehydrated sludge flow rate detected by the flow meter 182 at the operating date and time 601 by the time interval of the operating date and time 601 .
　実測貯留重量１７０３は、運転日時６０１において脱水汚泥ホッパー１８０が貯留する脱水汚泥１６７Ｂの重量の実測値であり、重量センサ１８１により検出される。 The measured stored weight 1703 is the measured value of the weight of the dehydrated sludge 167B stored in the dewatered sludge hopper 180 at the operating date and time 601, and is detected by the weight sensor 181.
　また、管理サーバ１０１は、脱水汚泥流入出収支テーブル１７００を用いて、今後ｔ時間の脱水汚泥流出入収支を予測する関数ｆ１１を生成する（下記式（１７）を参照。）。 The management server 101 also uses the dehydrated sludge inflow balance table 1700 to generate a function f11 that predicts the dehydrated sludge inflow balance for the next t hours (see formula (17) below).
今後ｔ時間の汚泥流出入収支
＝ｆ１２（実測脱水汚泥性状，計画処理対象汚泥量，ｔ）…（１７） Sludge inflow/outflow balance for t hours from now on = f12 (actually measured dehydrated sludge properties, sludge amount to be planned and processed, t) (17)
　管理サーバ１０１は、上記式（１７）の左辺に運転日時６０１ごとの（実測流入脱水汚泥量１７０１－実測流出脱水汚泥量１７０２）を正解データとして入力し、上記式（１７）の右辺に運転日時６０１よりもｔ時間前の運転日時６０１における実測脱水汚泥性状８０２および運転日時６０１よりもｔ時間前の計画処理対象汚泥量（上記式（７）で算出）を学習データとして入力し、機械学習により、流入汚泥量を予測する関数ｆ１２を回帰式として生成する。 The management server 101 inputs (actually measured inflow dehydrated sludge amount 1701 - measured outflow dehydrated sludge amount 1702) for each operation date 601 to the left side of the above equation (17) as correct data, and inputs the operation date and time to the right side of the above equation (17). The measured dewatered sludge property 802 at the operating date and time 601 t hours before 601 and the planned amount of sludge to be treated (calculated by the above formula (7)) at t hours before the operating date and time 601 are input as learning data, and machine learning is performed. , a function f12 for predicting the amount of inflow sludge is generated as a regression equation.
　＜汚泥処理計画策定処理手順＞
　図１８は、管理サーバ１０１による汚泥処理計画策定処理手順例を示すフローチャートである。管理サーバ１０１は、たとえば、ユーザからの入力により、予測条件を取得する（ステップＳ１８０１）。予測条件とは、総合コストの予測に必要なパラメータであり、具体的には、たとえば、予測対象期間、予測対象期間の天候および季節、予測対象期間の運転者の人数、予測対象期間の脱水汚泥の搬出予定時刻５０７である。 <Procedure for formulating a sludge treatment plan>
FIG. 18 is a flow chart showing an example of a sludge treatment planning processing procedure by the management server 101. As shown in FIG. The management server 101 acquires prediction conditions, for example, by input from the user (step S1801). Prediction conditions are parameters necessary for predicting the total cost. Specifically, for example, the forecast period, the weather and season during the forecast period, the number of drivers during the forecast period, and the dewatered sludge during the forecast period. is the scheduled time 507 of unloading.
　予測対象期間は、汚泥処理計画を策定したい期間であり、たとえば、日付が特定される１日（たとえば、翌日）や１週間、１か月である。予測対象期間の最小単位は、運転日時６０１の時間幅と同一の所定時間（たとえば、１０分、３０分、１時間、１日（汚泥処理開始時刻から汚泥処理終了時刻まで））である。 The forecast target period is the period for which you want to formulate a sludge treatment plan, for example, one day (for example, the next day), one week, or one month when the date is specified. The minimum unit of the prediction target period is a predetermined period of time (for example, 10 minutes, 30 minutes, 1 hour, 1 day (from the sludge treatment start time to the sludge treatment end time)) that is the same as the time width of the operation date and time 601 .
　つぎに、管理サーバ１０１は、汚泥処理システム１０２の固定条件を、記憶デバイス２０２から読み出すことにより取得する（ステップＳ１８０２）。固定条件とは、上述した各テーブル３００、４００，５００，６００，７００，８００，９００，１０００，１１００，１２００，１３００，１４００，１５００，１６００，１７００に含まれている固定値であり、たとえば、単価管理テーブル３００、凝集剤テーブル４００、制約条件テーブル５００、フロック形成槽容量７０４が読み込まれる。 Next, the management server 101 acquires the fixed conditions of the sludge treatment system 102 by reading them from the storage device 202 (step S1802). The fixed conditions are fixed values included in each of the tables 300, 400, 500, 600, 700, 800, 900, 1000, 1100, 1200, 1300, 1400, 1500, 1600, and 1700 described above. The unit price management table 300, flocculant table 400, constraint table 500, and flocculation tank capacity 704 are read.
　つぎに、管理サーバ１０１は、予測対象期間のうち未選択でかつ最古の時間帯（以下、対象時間帯という。対象時間帯の時間幅は上述した所定時間。）についてのセンサデータを取得する（ステップＳ１８０３）。具体的には、たとえば、管理サーバ１０１は、対象時間帯と同一時間帯、同一季節、および同一天候の実測値の集合を、実測流入汚泥性状テーブル６００、フロック形成条件テーブル７００、実測脱水汚泥性状テーブル８００、実測脱水汚泥量テーブル９００、汚泥圧入ポンプ実測テーブル１０００、フロック形成槽実測テーブル１１００、脱水機実測テーブル１２００、脱水汚泥移送ポンプ実測テーブル１３００、運転員実測テーブル１４００、メンテナンス管理テーブル１５００、汚泥流入出収支テーブル１６００、脱水汚泥流入出収支テーブル１７００から抽出し、センサデータとして読み込む。 Next, the management server 101 acquires sensor data for an unselected and oldest time slot (hereinafter referred to as a target time slot; the duration of the target time slot is the above-described predetermined time period) in the prediction target period. (Step S1803). Specifically, for example, the management server 101 stores a set of measured values in the same time zone, the same season, and the same weather as the target time zone in the table 600 for the properties of inflowing sludge, the table 700 for floc formation conditions, and the table 700 for the conditions for forming flocs, Table 800, measured dehydrated sludge amount table 900, sludge injection pump actual measurement table 1000, floc forming tank actual measurement table 1100, dehydrator actual measurement table 1200, dehydrated sludge transfer pump actual measurement table 1300, operator actual measurement table 1400, maintenance management table 1500, sludge It is extracted from the inflow/outflow balance table 1600 and the dewatered sludge inflow/outflow balance table 1700 and read as sensor data.
　同一時間帯、同一季節、および同一天候の実測値の集合が複数存在する場合は、管理サーバ１０１は、いずれか１つの実測値の集合を選択する。具体的には、たとえば、管理サーバ１０１は、最も直近の実測値の集合を選択してもよい。また、管理サーバ１０１は、同種の実測値群の平均値の集合を、センサデータとして取得してもよい。 If there are multiple sets of measured values for the same time zone, same season, and same weather, the management server 101 selects any one set of measured values. Specifically, for example, the management server 101 may select a set of the most recent measured values. Also, the management server 101 may acquire a set of average values of the same type of actual measurement values as sensor data.
　つぎに、管理サーバ１０１は、複数の運転条件を設定する（ステップＳ１８０４）。運転条件とは、汚泥処理システム１０２の運転に必要な変動パラメータの集合である。すなわち、運転条件とは、上記式（１）～（１７）の右辺の説明変数群に入力される値の組み合わせの集合である。 Next, the management server 101 sets a plurality of operating conditions (step S1804). Operating conditions are a set of variable parameters required to operate the sludge treatment system 102 . That is, the operating condition is a set of combinations of values input to the explanatory variables on the right side of the above equations (1) to (17).
　具体的には、たとえば、運転条件を構成する説明変数群は、時間当たり処理量、脱水機駆動機回転数、圧入圧力、付与背圧レベル、凝集剤注入率、急速撹拌機回転数、緩速撹拌機回転数、脱水汚泥移送ポンプ回転数、汚泥処理開始時刻、汚泥処理終了時刻である。運転条件となる説明変数群の値の組み合わせは、複数通り設定される。 Specifically, for example, the group of explanatory variables that make up the operating conditions are throughput per hour, dehydrator driving machine rotation speed, injection pressure, applied back pressure level, flocculant injection rate, rapid stirrer rotation speed, slow speed They are the rotation speed of the agitator, the rotation speed of the dehydrated sludge transfer pump, the sludge treatment start time, and the sludge treatment end time. A plurality of combinations of the values of the explanatory variable group that serve as the operating conditions are set.
　つぎに、管理サーバ１０１は、複数の運転条件の各々について、対象時間帯の総合コストＣを算出する（ステップＳ１８０５）。総合コストＣは、たとえば、下記式（１８）により算出される。 Next, the management server 101 calculates the total cost C for the target time period for each of the plurality of operating conditions (step S1805). The total cost C is calculated, for example, by the following formula (18).
総合コストＣ＝脱水汚泥搬出コストＣａ＋脱水コストＣｂ…（１８） Total cost C=dewatered sludge carrying-out cost Ca+dehydration cost Cb (18)
　［脱水汚泥搬出コストＣａ］
　ここで、脱水汚泥搬出コストＣａの詳細について説明する。脱水汚泥搬出コストＣａは、下記式（１９）により算出される。 [Dewatered sludge transport cost Ca]
Here, the details of the dehydrated sludge carrying-out cost Ca will be described. The dehydrated sludge carrying-out cost Ca is calculated by the following formula (19).
脱水汚泥搬出コストＣａ
＝脱水汚泥量［ｔ／日］×(運搬費単価［円／ｔ］＋引取費単価［円／ｔ］)…（１９） Dewatered sludge transport cost Ca
= Amount of dehydrated sludge [t/day] x (unit transportation cost [yen/t] + unit price of collection cost [yen/t]) (19)
　運搬費単価３０２および引取費単価３０３は固定値であり、ステップＳ１８０２で取得された値が代入される。 The transportation cost unit price 302 and the pick-up cost unit price 303 are fixed values, and the values obtained in step S1802 are substituted.
　脱水汚泥量［ｔ／日］の予測値は、上記式（６）により算出される。上記式（６）の右辺の脱水汚泥性状［ｔ／ｍ３］の予測値は、上記式（５）により算出される。上記式（５）の右辺の形成フロック性状の予測値は、上記式（４）により算出される。 The predicted value of the amount of dehydrated sludge [t/day] is calculated by the above formula (6). The predicted value of the dehydrated sludge property [t/m 3 ] on the right side of the above formula (6) is calculated by the above formula (5). The predicted value of the formed floc property on the right side of the above equation (5) is calculated by the above equation (4).
　すなわち、管理サーバ１０１は、対象時間帯のセンサデータとして取得した、流入汚泥性状（上流プロセス運転条件６０２、水温６０３、ｐＨ６０４、電気伝導度６０５、汚泥濃度６０６、含水率６０７、天候６０８、季節６０９）の実測値と、フロック形成条件と、を、上記式（４）の右辺に代入する。フロック形成条件のうち、凝集剤注入率７０１、急速撹拌機回転数７０２、緩速撹拌機回転数７０３、および時間当たり処理量７０５は運転条件、フロック形成槽容量７０４は固定値として代入される。これにより、形成フロック性状の予測値が算出され、上記式（５）に代入される。 That is, the management server 101 acquires the inflow sludge properties (upstream process operating conditions 602, water temperature 603, pH 604, electrical conductivity 605, sludge concentration 606, water content 607, weather 608, season 609, acquired as sensor data in the target time period). ) and the floc formation conditions are substituted into the right side of the above equation (4). Of the flocculation conditions, the coagulant injection rate 701, the rapid stirrer rotation speed 702, the slow stirrer rotation speed 703, and the throughput per hour 705 are assigned as operating conditions, and the flocculation tank capacity 704 is assigned as a fixed value. As a result, the predicted value of the properties of the flocs formed is calculated and substituted into the above equation (5).
　また、管理サーバ１０１は、運転条件である脱水機運転条件８０１（脱水機駆動機回転数、圧入圧力、付与背圧レベル）を上記式（５）に代入する。これにより、脱水汚泥性状の予測値が算出され、上記式（６）に代入される。 In addition, the management server 101 substitutes the dehydrator operating conditions 801 (dehydrator driving machine rotation speed, injection pressure, applied back pressure level), which are operating conditions, into the above equation (5). As a result, the predicted value of the dehydrated sludge property is calculated and substituted into the above equation (6).
　また、計画処理対象汚泥量［ｍ３／日］の予測値は、上記式（７）により算出される。上記式（７）の右辺の時間当たり処理量［ｍ３／ｈ］、汚泥処理終了時刻および汚泥処理開始時刻は、運転条件である。これにより、計画処理対象汚泥量［ｍ３／日］の予測値が算出され、上記式（６）に代入される。 Moreover, the predicted value of the planned amount of sludge to be treated [m 3 /day] is calculated by the above formula (7). The processing amount per hour [m 3 /h], the sludge treatment end time, and the sludge treatment start time on the right side of the above equation (7) are operating conditions. As a result, the predicted value of the planned amount of sludge to be treated [m 3 /day] is calculated and substituted into the above equation (6).
　また、上記式（６）の脱水プロセス運転条件には、運転条件である脱水機運転条件８０１と、運転条件および固定値であるフロック形成条件（凝集剤注入率７０１、急速撹拌機回転数７０２、緩速撹拌機回転数７０３、フロック形成槽容量７０４および時間当たり処理量７０５）と、が代入される。これにより、上記式（１９）において脱水汚泥量［ｔ／日］の予測値が算出される。 Further, the dehydration process operating conditions of the above formula (6) include dehydrator operating conditions 801 which are operating conditions, and floc formation conditions which are operating conditions and fixed values (coagulant injection rate 701, rapid stirrer rotation speed 702, Slow stirrer rpm 703, flocculation tank capacity 704 and throughput per hour 705) are substituted. Thereby, the predicted value of the amount of dewatered sludge [t/day] is calculated in the above equation (19).
　［脱水コストＣｂ］
　ここで、脱水コストＣｂの詳細について説明する。脱水コストＣｂは、下記式（２０）により算出される。 [Dehydration cost Cb]
Here, the details of the dehydration cost Cb will be described. The dehydration cost Cb is calculated by the following formula (20).
脱水コストＣｂ
＝凝集剤コストＣｂ１＋機器駆動コストＣｂ２＋運転員人件費Ｃｂ３＋機器メンテナンス費Ｃｂ４…（２０） Dehydration cost Cb
= flocculant cost Cb1 + equipment driving cost Cb2 + operator personnel cost Cb3 + equipment maintenance cost Cb4 (20)
　　［凝集剤コストＣｂ１］
　凝集剤コストＣｂ１は、下記式（２１）により算出される。 [Flocculant cost Cb1]
The coagulant cost Cb1 is calculated by the following formula (21).
凝集剤コストＣｂ１＝薬品単価［円／ｋｇ］×凝集剤注入率［ｍｇ／Ｌ］×時間当たり処理量［ｍ３／ｈ］×単位換算係数（固定値）…（２１） Coagulant cost Cb1 = chemical unit price [yen/kg] x coagulant injection rate [mg/L] x processing amount per hour [m 3 /h] x unit conversion factor (fixed value) (21)
　薬品単価４０１および単位換算係数は固定値であり、ステップＳ１８０２で取得された値が代入される。また、管理サーバ１０１は、運転条件である凝集剤注入率７０１および時間当たり処理量［ｍ３／ｈ］を、上記式（２１）に代入することにより、凝集剤コストＣｃの予測値を算出する。 The drug unit price 401 and the unit conversion factor are fixed values, and the values obtained in step S1802 are substituted. In addition, the management server 101 calculates the predicted value of the coagulant cost Cc by substituting the coagulant injection rate 701 and the throughput per hour [m 3 /h], which are the operating conditions, into the above equation (21). .
　　［機器駆動コストＣｂ２］
　機器駆動コストＣｂ２は、下記式（２２）により算出される。 [Equipment driving cost Cb2]
The device driving cost Cb2 is calculated by the following formula (22).
機器駆動コスト［円］＝電力消費量［ｋＷｈ］×電気代単価［円／ｋＷｈ］…（２２） Equipment driving cost [yen] = power consumption [kWh] x unit price of electricity [yen/kWh] (22)
　電気代単価３０５は固定値であり、ステップＳ１８０２で取得された値が代入される。電力消費量［ｋＷｈ］の予測値は、下記式（２３Ａ）により算出される。 The electricity bill unit price 305 is a fixed value, and the value obtained in step S1802 is substituted. The predicted value of power consumption [kWh] is calculated by the following formula (23A).
電力消費量［ｋＷｈ］＝汚泥圧入ポンプ消費電力量［ｋＷｈ］＋フロック形成槽消費電力量［ｋＷｈ］＋脱水機消費電力量［ｋＷｈ］＋脱水汚泥移送ポンプ消費電力量［ｋＷｈ］…（２３Ａ） Power consumption [kWh] = Power consumption of sludge injection pump [kWh] + Power consumption of floc forming tank [kWh] + Power consumption of dehydrator [kWh] + Power consumption of dehydrated sludge transfer pump [kWh] (23A)
　汚泥圧入ポンプ消費電力量［ｋＷｈ］の予測値は、上記式（８）により算出される。上記式（８）の右辺の説明変数群のうち、圧入圧力は、運転条件で規定された値である。運転時間も、運転条件である汚泥処理開始時刻と汚泥処理終了時刻との差分により算出される値である。管理サーバ１０１は、対象時間帯のセンサデータとして取得した、汚泥圧入ポンプ実測回転数１００２の実測値を上記式（８）に代入して、汚泥圧入ポンプ消費電力量［ｋＷｈ］の予測値を算出する。 The predicted value of the sludge injection pump power consumption [kWh] is calculated by the above formula (8). Among the group of explanatory variables on the right side of the above equation (8), the injection pressure is a value defined by the operating conditions. The operating time is also a value calculated from the difference between the sludge treatment start time and the sludge treatment end time, which are operating conditions. The management server 101 calculates the predicted value of the sludge injection pump power consumption [kWh] by substituting the measured value of the sludge injection pump actual rotation speed 1002 acquired as the sensor data for the target time period into the above equation (8). do.
　フロック形成槽消費電力量［ｋＷｈ］の予測値は、上記式（９）により算出される。上記式（９）の右辺の説明変数群のうち、急速撹拌機回転数および緩速撹拌機回転数は、運転条件で規定された値である。運転時間も、運転条件である汚泥処理開始時刻と汚泥処理終了時刻との差分により算出される値である。 The predicted value of the flocculation tank power consumption [kWh] is calculated by the above formula (9). Of the group of explanatory variables on the right side of the above equation (9), the rapid stirrer rotation speed and the slow stirrer rotation speed are values defined by the operating conditions. The operating time is also a value calculated from the difference between the sludge treatment start time and the sludge treatment end time, which are operating conditions.
　一方、形成フロック性状の予測値は、上記式（４）により算出される。すなわち、管理サーバ１０１は、対象時間帯のセンサデータとして取得した、流入汚泥性状（上流プロセス運転条件６０２、水温６０３、ｐＨ６０４、電気伝導度６０５、汚泥濃度６０６、含水率６０７、天候６０８、季節６０９）の実測値と、フロック形成条件（凝集剤注入率７０１、急速撹拌機回転数７０２、緩速撹拌機回転数７０３、フロック形成槽容量７０４および時間当たり処理量７０５）を、上記式（４）の右辺に代入する。 On the other hand, the predicted value of the properties of the flocs formed is calculated by the above formula (4). That is, the management server 101 acquires the inflow sludge properties (upstream process operating conditions 602, water temperature 603, pH 604, electrical conductivity 605, sludge concentration 606, water content 607, weather 608, season 609, acquired as sensor data in the target time period). ) and flocculation conditions (coagulant injection rate 701, rapid stirrer rotation speed 702, slow stirrer rotation speed 703, flocculation tank capacity 704, and throughput per hour 705) are calculated by the above formula (4). to the right side of .
　これにより、形成フロック性状の予測値が算出され、上記式（９）に代入される。このようにして、管理サーバ１０１は、汚泥圧入ポンプ消費電力量［ｋＷｈ］の予測値を算出する。 As a result, the predicted value of the properties of the flocs formed is calculated and substituted into the above formula (9). Thus, the management server 101 calculates the predicted value of the sludge injection pump power consumption [kWh].
　脱水機消費電力量［ｋＷｈ］の予測値は、上記式（１０）により算出される。上記式（１０）の右辺の説明変数群のうち、脱水機駆動機回転数、付与背圧レベルおよび時間当たり処理量は、運転条件で規定された値である。運転時間も、運転条件である汚泥処理開始時刻と汚泥処理終了時刻との差分により算出される値である。形成フロック性状は、フロック形成槽消費電力量［ｋＷｈ］の場合と同様、上記式（４）により算出され、上記式（１０）に代入される。このようにして、管理サーバ１０１は、脱水機消費電力量［ｋＷｈ］の予測値を算出する。 The predicted value of the dehydrator power consumption [kWh] is calculated by the above formula (10). Of the group of explanatory variables on the right side of the above equation (10), the rotation speed of the dehydrator driving machine, the applied back pressure level, and the throughput per hour are values defined by the operating conditions. The operating time is also a value calculated from the difference between the sludge treatment start time and the sludge treatment end time, which are operating conditions. The properties of flocs formed are calculated by the above formula (4) and substituted into the above formula (10), as in the case of the floc formation tank power consumption [kWh]. In this way, the management server 101 calculates the predicted value of the dehydrator power consumption [kWh].
　脱水汚泥移送ポンプ消費電力量［ｋＷｈ］の予測値は、上記式（１１）により算出される。上記式（１１）の右辺の説明変数群のうち脱水汚泥移送ポンプ回転数は、運転条件で規定された値である。運転時間も、運転条件である汚泥処理開始時刻と汚泥処理終了時刻との差分により算出される値である。 The predicted value of the power consumption [kWh] of the dewatered sludge transfer pump is calculated by the above formula (11). Of the group of explanatory variables on the right side of the above equation (11), the rotation speed of the dewatered sludge transfer pump is a value defined by the operating conditions. The operating time is also a value calculated from the difference between the sludge treatment start time and the sludge treatment end time, which are operating conditions.
　脱水汚泥性状は、上記式（５）により算出される。上記式（５）中の形成フロック性状は、上記式（４）により算出され、上記式（５）に代入される。また、管理サーバ１０１は、運転条件である脱水機運転条件８０１（脱水機駆動機回転数、圧入圧力、付与背圧レベル）を上記式（５）に代入する。このようにして、管理サーバ１０１は、脱水汚泥移送ポンプ消費電力量［ｋＷｈ］の予測値を算出する。 The dehydrated sludge properties are calculated by the above formula (5). The properties of flocs formed in the formula (5) are calculated by the formula (4) and substituted into the formula (5). In addition, the management server 101 substitutes the dehydrator operating conditions 801 (dehydrator driving machine rotation speed, injection pressure, applied back pressure level), which are operating conditions, into the above equation (5). Thus, the management server 101 calculates the predicted value of the power consumption [kWh] of the dehydrated sludge transfer pump.
　　［運転員人件費Ｃｂ３］
　１日当たりの運転員人件費は、下記式（２３Ｂ）により算出される。 [Operator personnel cost Cb3]
The operator personnel cost per day is calculated by the following formula (23B).
１日当たりの運転員人件費［円］＝人件費単価［円／人／ｈ］×人数［人］×労働時間［ｈ］…（２３Ｂ） Operator labor cost per day [yen] = labor cost unit price [yen/person/h] x number of people [person] x working hours [h] (23B)
　人件費単価３０１は固定値であり、ステップＳ１８０２で取得された値が上記式（２３Ｂ）に代入される。人数［人］は、ステップＳ１８０１で取得された予測条件の値であり、上記式（２３Ｂ）に代入される。 The personnel cost unit price 301 is a fixed value, and the value obtained in step S1802 is substituted into the above formula (23B). The number of people [people] is the value of the prediction condition acquired in step S1801, and is substituted into the above equation (23B).
　労働時間［ｈ］の予測値は、下記式（２４）により算出される。 The predicted value of working hours [h] is calculated by the following formula (24).
労働時間＝計画処理対象汚泥量［ｍ３／日］×時間当たり処理量［ｍ３／ｈ］…（２４） Working hours = Planned amount of sludge to be treated [m 3 /day] × amount of treatment per hour [m 3 /h] (24)
　上記式（２４）の時間当たり処理量［ｍ３／ｈ］は、運転条件である。また、計画処理対象汚泥量［ｍ３／日］の予測値は、上記式（７）により算出される。上記式（７）の右辺の時間当たり処理量［ｍ３／ｈ］、汚泥処理終了時刻および汚泥処理開始時刻は、運転条件である。これにより、計画処理対象汚泥量［ｍ３／日］の予測値が算出され、上記式（２４）に代入される。 The throughput per hour [m 3 /h] in the above formula (24) is an operating condition. Moreover, the predicted value of the planned amount of sludge to be treated [m 3 /day] is calculated by the above equation (7). The processing amount per hour [m 3 /h], the sludge treatment end time, and the sludge treatment start time on the right side of the above equation (7) are operating conditions. As a result, the predicted value of the planned amount of sludge to be treated [m 3 /day] is calculated and substituted into the above equation (24).
　管理サーバ１０１は、上記式（２３Ｂ）で算出された１日当たりの運転員人件費を対象時間帯の時間幅（所定時間）で割ることにより、対象時間帯の運転員人件費Ｃｂ３を算出する。 The management server 101 calculates the operator personnel cost Cb3 for the target time period by dividing the operator personnel cost per day calculated by the above formula (23B) by the time span (predetermined time) of the target time period.
　　［機器メンテナンス費Ｃｂ４］
　運転期間における機器メンテナンス費は、下記式（２５）により算出される。 [Equipment maintenance cost Cb4]
The equipment maintenance cost during the operation period is calculated by the following formula (25).
運転期間における機器メンテナンス費［円］
＝メンテナンス単価［円／回］×メンテナンス頻度（回／運転期間）…（２５） Equipment maintenance cost during operation period [yen]
= maintenance unit price [yen/time] x maintenance frequency (time/operation period) (25)
　メンテナンス単価３０４は固定値であり、ステップＳ１８０２で取得された値が上記式（２５）に代入される。 The maintenance unit price 304 is a fixed value, and the value obtained in step S1802 is substituted into the above formula (25).
　メンテナンス頻度（回／運転期間）の予測値は、上記式（１３）により算出される。 The predicted value of maintenance frequency (times/operating period) is calculated by the above formula (13).
　上記式（１３）の右辺の説明変数群のうち、形成フロック性状の予測値は、上記式（４）により算出される。すなわち、管理サーバ１０１は、対象時間帯のセンサデータとして取得した、流入汚泥性状（上流プロセス運転条件６０２、水温６０３、ｐＨ６０４、電気伝導度６０５、汚泥濃度６０６、含水率６０７、天候６０８、季節６０９）の実測値と、運転条件および固定値であるフロック形成条件（凝集剤注入率７０１、急速撹拌機回転数７０２、緩速撹拌機回転数７０３、フロック形成槽容量７０４および時間当たり処理量７０５）とを、上記式（４）の右辺に代入する。 Among the group of explanatory variables on the right side of Equation (13) above, the predicted value of the properties of the flocs formed is calculated by Equation (4) above. That is, the management server 101 acquires the inflow sludge properties (upstream process operating conditions 602, water temperature 603, pH 604, electrical conductivity 605, sludge concentration 606, water content 607, weather 608, season 609, acquired as sensor data in the target time period). ), operating conditions, and flocculation conditions that are fixed values (coagulant injection rate 701, rapid stirrer rotation speed 702, slow stirrer rotation speed 703, flocculation tank capacity 704, and throughput per hour 705). to the right side of the above equation (4).
　また、上記式（１３）の右辺の説明変数群のうち、機器運転時間の予測値は、上記式（１４）により算出される。上記式（１４）の時間当たり処理量［ｍ３／ｈ］は、運転条件である。また、計画処理対象汚泥量［ｍ３／日］の予測値は、上記式（７）により算出される。また、上記式（１４）の運転日数は、予測対象期間の日数とする。 Further, among the group of explanatory variables on the right side of Equation (13) above, the predicted value of the appliance operating time is calculated by Equation (14) above. The throughput per hour [m 3 /h] in the above formula (14) is an operating condition. Moreover, the predicted value of the planned amount of sludge to be treated [m 3 /day] is calculated by the above formula (7). Also, the number of operating days in the above formula (14) is the number of days in the prediction target period.
　管理サーバ１０１は、上記式（２５）で算出された、運転期間における機器メンテナンス費［円］を、予測対象期間の日数で割り、かつ、対象時間帯の時間幅（所定時間）で割ることにより、対象時間帯の機器メンテナンス費Ｃｂ４を算出する。 The management server 101 divides the equipment maintenance cost [yen] in the operation period calculated by the above formula (25) by the number of days in the prediction target period and by the time span (predetermined time) of the target time zone. , the equipment maintenance cost Cb4 for the target time period is calculated.
　管理サーバ１０１は、上記式（２０）により、凝集剤コストＣｂ１、機器駆動コストＣｂ２、運転員人件費Ｃｂ３および機器メンテナンス費Ｃｂ４の総和により、対象時間帯の脱水コストＣｂを算出する。そして、管理サーバ１０１は、上記式（１８）により、上記式（１９）で算出した脱水汚泥搬出コストＣａと上記式（２０）で算出した脱水コストＣｂとを加算することにより、対象時間帯の総合コストＣを算出する。 The management server 101 calculates the dehydration cost Cb for the target time period by summing the flocculant cost Cb1, the equipment driving cost Cb2, the operator labor cost Cb3, and the equipment maintenance cost Cb4 according to the above equation (20). Then, the management server 101 adds the dewatered sludge carrying-out cost Ca calculated by the above formula (19) and the dehydration cost Cb calculated by the above formula (20) using the above formula (18). A total cost C is calculated.
　管理サーバ１０１は、ステップＳ１８０５のあと、ステップＳ１８０７で未選択でかつ総コストが最小の運転条件があるか否かを判断する（ステップＳ１８０６）。未選択でかつ総コストが最小の運転条件があれば（ステップＳ１８０６：Ｙｅｓ）、管理サーバ１０１は、未選択でかつ最小総合コストの運転条件を選択する（ステップＳ１８０７）。 After step S1805, the management server 101 determines whether there is an operating condition that has not been selected in step S1807 and has the lowest total cost (step S1806). If there is an unselected operating condition with the lowest total cost (step S1806: Yes), the management server 101 selects an unselected operating condition with the lowest total cost (step S1807).
　そして、管理サーバ１０１は、選択運転条件が下記制約条件（Ａ）～（Ｆ）を遵守しているか否かを判定し、判定結果（遵守または違反）を選択運転条件に関連付けて（ステップＳ１８０８）、ステップＳ１８０６に戻る。ステップＳ１８０７では、未選択でかつ最小総合コストの運転条件を選択しているため、選択運転条件が、下記制約条件（Ａ）～（Ｆ）をすべて順守した時点で、ステップＳ１８０６では、未選択でかつ総コストが最小の運転条件がないことになり（ステップＳ１８０６：Ｎｏ）、ステップＳ１８０９に移行する。これにより、無駄な制約条件の遵守判定を抑制することができる。 Then, the management server 101 determines whether or not the selected operating condition complies with the following constraints (A) to (F), and associates the determination result (observance or violation) with the selected operating condition (step S1808). , the process returns to step S1806. In step S1807, the unselected operating condition with the lowest total cost is selected, so when the selected operating condition complies with all of the following constraints (A) to (F), in step S1806, unselected Moreover, there is no operating condition with the lowest total cost (step S1806: No), and the process proceeds to step S1809. As a result, it is possible to suppress wasteful determination of compliance with the constraint.
　［制約条件（Ａ）］
　管理サーバ１０１は、運転員人件費Ｃｂ３の算出に際し、上記式（２４）で算出した労働時間［ｈ］の予測値が、制約条件テーブル５００における１人当たり最大労働時間５０１以下であるか否かを判定する。１人当たり最大労働時間５０１以下であれば、当該選択運転条件は制約条件（Ａ）を遵守し、そうでなければ制約条件（Ａ）に違反する。 [Constraint (A)]
When calculating the operator labor cost Cb3, the management server 101 checks whether the predicted value of the working hours [h] calculated by the above equation (24) is equal to or less than the maximum working hours 501 per person in the constraint table 500. judge. If the maximum working hours per person is 501 or less, the selected operating condition complies with constraint (A), otherwise it violates constraint (A).
　［制約条件（Ｂ）］
　管理サーバ１０１は、下記式（２６）により、ステップＳ１８０１で取得した脱水汚泥の搬出予定時刻５０７に関する制約を遵守しているか否かを判定する。 [Constraint (B)]
The management server 101 determines whether or not the restrictions on the dewatered sludge scheduled discharge time 507 acquired in step S1801 are complied with using the following formula (26).
対象時間帯の時刻＋（計画処理対象汚泥量－時間当たり処理量×経過処理時間）／時間当たり処理量＜脱水汚泥の搬出予定時刻…（２６） Time of target time zone + (planned amount of sludge to be treated - amount of treatment per hour x elapsed treatment time) / amount of treatment per hour < scheduled time to carry out dewatered sludge ... (26)
　上記式（２６）の左辺のうち、対象時間帯の時刻は、対象時間帯内のある時刻であり、たとえば、対象時間帯内の最古の時刻、最新の時刻でもよい。また、経過処理時間は、対象時間帯において汚泥処理が経過した時間であり、この場合は、対象時間帯の時間幅（所定時間）となる。上記式（２６）を充足していれば、当該選択運転条件は制約条件（Ｂ）を遵守し、そうでなければ制約条件（Ｂ）に違反する。 Of the left side of the above equation (26), the time in the target time period is a certain time in the target time period, and may be, for example, the oldest time or the latest time in the target time period. The elapsed treatment time is the time that the sludge treatment has elapsed in the target time zone, and in this case, it is the time width (predetermined time) of the target time zone. If the above formula (26) is satisfied, the selected operating condition complies with the constraint (B), otherwise the constraint (B) is violated.
　［制約条件（Ｃ）］
　管理サーバ１０１は、対象時間帯における各モータ１５３、１５４、１６６の予測電流値が制約条件テーブル５００の駆動機電流上限値５０２以下であるか否かを判定する。各モータ１５３、１５４、１６６の電流値は、図示しない電流計により運転日時６０１ごとに計測されているものとする。 [Constraint (C)]
The management server 101 determines whether or not the predicted current value of each motor 153 , 154 , 166 in the target time period is equal to or less than the driver current upper limit value 502 of the constraint condition table 500 . It is assumed that the current values of the motors 153, 154, and 166 are measured for each operation date/time 601 by an ammeter (not shown).
　管理サーバ１０１は、たとえば、過去の運転日時６０１ごとのモータ１５３、１５４の電流値と、過去の運転日時６０１ごとのフロック形成槽消費電力量［ｋＷｈ］とを用いて、機械学習により回帰式を作成しておき、当該回帰式に対象時間帯のフロック形成槽消費電力量［ｋＷｈ］を代入することにより、対象時間帯におけるモータ１５３、１５４の予測電流値を算出する。 The management server 101 uses, for example, the current values of the motors 153 and 154 for each past operating date and time 601 and the power consumption [kWh] for each past operating date and time 601 to calculate a regression equation by machine learning. Predicted current values of the motors 153 and 154 in the target time period are calculated by substituting the flocculation tank power consumption [kWh] in the target time period into the regression equation.
　同様に、管理サーバ１０１は、たとえば、過去の運転日時６０１ごとの脱水機駆動機１６６の電流値と、過去の運転日時６０１ごとの脱水機消費電力量［ｋＷｈ］とを用いて、機械学習により回帰式を作成しておき、当該回帰式に対象時間帯の脱水機消費電力量［ｋＷｈ］を代入することにより、対象時間帯における脱水機駆動機１６６の予測電流値を算出する。対象時間帯における各モータ１５３、１５４、１６６の予測電流値がすべて制約条件テーブル５００の駆動機電流上限値５０２以下であれば、当該選択運転条件は制約条件（Ｃ）を遵守し、そうでなければ制約条件（Ｃ）に違反する。 Similarly, the management server 101 uses, for example, the current value of the dehydrator driving machine 166 for each past operation date and time 601 and the dehydrator power consumption [kWh] for each past operation date and time 601 to By creating a regression equation and substituting the dehydrator power consumption [kWh] in the target time period into the regression equation, the predicted current value of the dehydrator driver 166 in the target time period is calculated. If the predicted current values of the motors 153, 154, 166 in the target time period are all equal to or less than the driver current upper limit value 502 of the constraint table 500, the selected operating condition complies with the constraint (C). violates constraint (C).
　［制約条件（Ｄ）］
　管理サーバ１０１は、選択運転条件である汚泥圧入ポンプ１３０の圧入圧力が制約条件テーブル５００の流入圧力上限値５０３以下であるか否かを判断する。また、管理サーバ１０１は、対象時間帯のセンサデータとして取得した脱水汚泥移送ポンプ１７０の実測吐出圧力１３０３が、制約条件テーブル５００の流出圧力上限値５０４以下であるか否かを判断する。選択運転条件の圧入圧力が流入圧力上限値５０３以下でかつ、脱水汚泥移送ポンプ１７０の実測吐出圧力１３０３が流出圧力上限値５０４以下であれば、当該選択運転条件は制約条件（Ｄ）を遵守し、そうでなければ制約条件（Ｄ）に違反する。 [Constraint (D)]
The management server 101 determines whether or not the injection pressure of the sludge injection pump 130 , which is the selected operating condition, is equal to or less than the inflow pressure upper limit value 503 of the constraint condition table 500 . The management server 101 also determines whether or not the measured discharge pressure 1303 of the dehydrated sludge transfer pump 170 acquired as sensor data for the target time period is equal to or less than the outflow pressure upper limit value 504 of the constraint condition table 500 . If the injection pressure of the selected operating condition is equal to or lower than the inflow pressure upper limit value 503 and the actually measured discharge pressure 1303 of the dehydrated sludge transfer pump 170 is equal to or lower than the outflow pressure upper limit value 504, the selected operating condition complies with the constraint (D). , otherwise constraint (D) is violated.
　［制約条件（Ｅ）］
　管理サーバ１０１は、下記式（２７）により、ステップＳ１８０２で取得した制約条件テーブル５００の汚泥貯留槽容量５０５に関する制約を遵守しているか否かを判定する。 [Constraint (E)]
The management server 101 determines whether or not the constraint regarding the sludge storage tank capacity 505 of the constraint condition table 500 acquired in step S1802 is complied with using the following formula (27).
　対象時間帯の水位＋今後ｔ時間の汚泥流出入収支＜汚泥貯留槽容量…（２７） 　Water level in the target time period + sludge inflow and outflow balance for the next t hours < sludge storage tank capacity... (27)
　上記式（２７）の左辺の対象時間帯の水位は、対象時間帯のセンサデータとして取得した実測水位１６０３である。今後ｔ時間の汚泥流出入収支は、上記式（１５）により算出される。上記式（１５）における計画処理対象汚泥量［ｍ３／日］の予測値は、上記式（７）により算出される。上記式（７）の右辺の時間当たり処理量［ｍ３／ｈ］、汚泥処理終了時刻および汚泥処理開始時刻は、選択運転条件である。 The water level in the target time period on the left side of the above equation (27) is the actually measured water level 1603 acquired as the sensor data in the target time period. The sludge inflow/outflow balance for t hours from now on is calculated by the above formula (15). The predicted value of the planned amount of sludge to be treated [m 3 /day] in the above formula (15) is calculated by the above formula (7). The processing amount per hour [m 3 /h], the sludge treatment end time, and the sludge treatment start time on the right side of the above equation (7) are selected operating conditions.
　また、上記式（１５）の流入汚泥量の予測値を算出する上記式（１６）の流入汚泥性状（上流プロセス運転条件６０２、水温６０３、ｐＨ６０４、電気伝導度６０５、汚泥濃度６０６、含水率６０７、天候６０８、季節６０９）の実測値は、ステップＳ１８０３で対象時間帯のセンサデータとして取得されたデータである。上記式（２７）を充足していれば、当該選択運転条件は制約条件（Ｅ）を遵守し、そうでなければ制約条件（Ｅ）に違反する。 In addition, the inflow sludge properties (upstream process operating conditions 602, water temperature 603, pH 604, electrical conductivity 605, sludge concentration 606, water content 607 , weather 608, and season 609) are data acquired as sensor data for the target time period in step S1803. If the above formula (27) is satisfied, the selected operating condition complies with the constraint (E), otherwise the constraint (E) is violated.
　［制約条件（Ｆ）］
　管理サーバ１０１は、下記式（２８）により、ステップＳ１８０２で取得した制約条件テーブル５００の脱水汚泥ホッパー最大許容貯留重量５０６に関する制約を遵守しているか否かを判定する。 [Constraint (F)]
The management server 101 determines whether or not the restriction regarding the dewatered sludge hopper maximum allowable storage weight 506 in the restriction condition table 500 acquired in step S1802 is complied with using the following formula (28).
対象時間帯の貯留重量＋今後ｔ時間の脱水汚泥流出入収支＜最大許容貯留重量…（２８） Storage weight in the target time period + dewatered sludge inflow/outflow balance for the next t hours < maximum allowable storage weight (28)
　上記式（２８）の左辺の対象時間帯の貯留重量は、対象時間帯のセンサデータとして取得した実測貯留重量１７０３である。今後ｔ時間の脱水汚泥流出入収支は、上記式（１７）により算出される。上記式（１７）における実測脱水汚泥性状は、ステップＳ１８０３で対象時間帯のセンサデータとして取得した、実測脱水汚泥性状テーブル８００の実測脱水汚泥性状８０２である。 The storage weight in the target time period on the left side of the above equation (28) is the actually measured storage weight 1703 acquired as the sensor data in the target time period. The dewatered sludge inflow/outflow balance for t hours from now on is calculated by the above equation (17). The measured dehydrated sludge property in the above formula (17) is the measured dehydrated sludge property 802 of the actually measured dewatered sludge property table 800 acquired as the sensor data for the target time period in step S1803.
　上記式（１７）における計画処理対象汚泥量［ｍ３／日］の予測値は、上記式（７）により算出される。上記式（７）の右辺の時間当たり処理量［ｍ３／ｈ］、汚泥処理終了時刻および汚泥処理開始時刻は、選択運転条件である。上記式（２８）を充足していれば、当該選択運転条件は制約条件（Ｆ）を遵守し、そうでなければ制約条件（Ｆ）に違反する。 The predicted value of the planned amount of sludge to be treated [m 3 /day] in the above formula (17) is calculated by the above formula (7). The processing amount per hour [m 3 /h], the sludge treatment end time, and the sludge treatment start time on the right side of the above equation (7) are selected operating conditions. If the above formula (28) is satisfied, the selected operating condition complies with the constraint (F), otherwise the constraint (F) is violated.
　図１９は、運転条件と総合コストＣとの関係を示すグラフである。図１９では、条件４が総合コストＣが最小となる運転条件であるが、制約条件（Ａ）～（Ｆ）を遵守していない。したがって、条件３が、制約条件（Ａ）～（Ｆ）を遵守し、かつ、総合コストＣが最小となる運転条件である。 　Fig. 19 is a graph showing the relationship between the operating conditions and the total cost C. In FIG. 19, condition 4 is the operating condition that minimizes the total cost C, but the constraints (A) to (F) are not complied with. Therefore, condition 3 is the operating condition that complies with the constraints (A) to (F) and minimizes the total cost C.
　図１８に戻り、ステップＳ１８０６において、未選択の運転条件がない場合（ステップＳ１８０６：Ｎｏ）、管理サーバ１０１は、探索終了か否かを判断する（ステップＳ１８０９）。すなわち、未処理の対象時間帯があれば探索終了ではないため（ステップＳ１８０９：Ｎｏ）、ステップＳ１８０３に移行し、未処理の対象時間帯がなければ探索終了であるため（ステップＳ１８０９：Ｙｅｓ）、ステップＳ１８１０に移行する。 Returning to FIG. 18, if there is no unselected operating condition in step S1806 (step S1806: No), the management server 101 determines whether or not the search has ended (step S1809). That is, if there is an unprocessed target time period, the search is not finished (step S1809: No), so the process proceeds to step S1803. The process moves to step S1810.
　管理サーバ１０１は、対象時間帯ごとに汚泥処理計画を策定する（ステップＳ１８１０）。具体的には、たとえば、管理サーバ１０１は、制約条件（Ａ）～（Ｆ）をすべて順守した運転条件の中で総合コストが最小の運転条件（以下、最適運転条件）に基づいて、汚泥処理計画を対象時間帯ごとに策定する。 The management server 101 formulates a sludge treatment plan for each target time zone (step S1810). Specifically, for example, the management server 101, based on the operating conditions (hereinafter referred to as optimum operating conditions) with the lowest overall cost among the operating conditions that comply with all of the constraints (A) to (F), sludge treatment Formulate a plan for each target time period.
　汚泥処理計画とは、対象時間帯における、脱水プロセス運転条件と、計画処理対象汚泥量と、を含む情報である。対象時間帯における計画処理対象汚泥量は、上記式（１７）を用いて算出された対象時間帯における計画処理対象汚泥量［ｍ３／日］の予測値である。 The sludge treatment plan is information including the dehydration process operating conditions and the planned amount of sludge to be treated in the target time zone. The planned amount of sludge to be treated in the target time period is a predicted value of the planned amount of sludge to be treated [m 3 /day] in the target time period calculated using the above formula (17).
　また、脱水プロセス運転条件とは、対象時間帯における、脱水機運転条件と、フロック形成条件である。対象時間帯における脱水機運転条件は、最適運転条件である。対象時間帯におけるフロック形成条件は、最適運転条件である凝集剤注入率７０１、急速撹拌機回転数７０２、緩速撹拌機回転数７０３、および時間当たり処理量７０５と、固定値のフロック形成槽容量７０４である。 Also, the dehydration process operating conditions are the dehydrator operating conditions and floc formation conditions during the target time period. The dehydrator operating conditions in the target time period are the optimum operating conditions. The flocculation conditions in the target time period are the flocculant injection rate 701, the rapid stirrer rotation speed 702, the slow stirrer rotation speed 703, and the throughput per hour 705, which are the optimum operating conditions, and the flocculation tank capacity at a fixed value. 704.
　また、管理サーバ１０１は、対象時間帯ごとに汚泥処理計画から、予測対象期間の各日の汚泥処理開始時刻および汚泥処理終了時刻を特定する。具体的には、たとえば、管理サーバ１０１は、各日の対象時間帯の最古の時間帯の開始時刻を、汚泥処理開始時刻に決定する。また、管理サーバ１０１は、各日の対象時間帯の最新の時間帯の終了時刻を、汚泥処理終了時刻に決定する。 In addition, the management server 101 specifies the sludge treatment start time and sludge treatment end time for each day of the prediction target period from the sludge treatment plan for each target time period. Specifically, for example, the management server 101 determines the start time of the oldest time period of each day as the sludge treatment start time. In addition, the management server 101 determines the end time of the latest time period of the target time period of each day as the sludge treatment end time.
　また、管理サーバ１０１は、対象時間帯ごとに、最適運転条件に対応する総合コストＣ、脱水汚泥搬出コストＣａ、脱水コストＣｂ、凝集剤コストＣｂ１、機器駆動コストＣｂ２、運転員人件費Ｃｂ３、機器メンテナンス費Ｃｂ４を出力対象に設定する。 In addition, the management server 101 stores the total cost C corresponding to the optimum operating condition, the dewatered sludge carrying-out cost Ca, the dehydration cost Cb, the coagulant cost Cb1, the equipment driving cost Cb2, the operator labor cost Cb3, the equipment The maintenance cost Cb4 is set as an output target.
　そして、管理サーバ１０１は、対象時間帯ごとの演算結果（汚泥処理計画、最適運転条件、各種コストのうち少なくとも１つ）を表示可能に出力する（ステップＳ１８１１）。具体的には、たとえば、管理サーバ１０１は、出力デバイス２０４の一例であるディスプレイに表示したり、ネットワーク１０３を介して通信可能な他のコンピュータに表示可能に送信したりする。 Then, the management server 101 outputs the calculation results (at least one of the sludge treatment plan, the optimum operating conditions, and various costs) for each target time period in a displayable manner (step S1811). Specifically, for example, the management server 101 displays the data on a display, which is an example of the output device 204, or transmits data to another computer that can communicate via the network 103 so that the data can be displayed.
　なお、管理サーバ１０１は、図１８の処理を実行しなかった場合の総合コスト、脱水汚泥搬出コスト、脱水コスト、凝集剤コスト、機器駆動コスト、運転員人件費、機器メンテナンス費を算出して、出力対象に設定してもよい。具体的には、たとえば、管理サーバ１０１は、図１８の処理を適用しない場合の運転条件で、脱水汚泥搬出コスト、脱水コスト、凝集剤コスト、機器駆動コスト、運転員人件費、機器メンテナンス費を算出する。これにより、図１８の処理を適用した場合と適用しなかった場合とのコストの比較結果（グラフや表）を表示可能に出力することができる。これにより、運転員はより客観的な観点をもって、出力された運転条件を採択するか否かを判断することが可能となる。 In addition, the management server 101 calculates the total cost, dehydrated sludge carrying-out cost, dehydration cost, coagulant cost, equipment driving cost, operator labor cost, equipment maintenance cost when the processing of FIG. 18 is not executed, It may be set as an output target. Specifically, for example, the management server 101 calculates the dehydrated sludge carrying-out cost, the dehydration cost, the coagulant cost, the device driving cost, the operator labor cost, and the device maintenance cost under the operating conditions when the process of FIG. 18 is not applied. calculate. As a result, it is possible to display and output the cost comparison results (graphs and tables) between the case where the processing of FIG. 18 is applied and the case where the processing is not applied. This enables the operator to judge whether or not to adopt the output operating conditions from a more objective point of view.
　このように、本実施例によれば、管理サーバ１０１は、制約条件（Ａ）～（Ｆ）を満たしつつも総合コストＣで優れている汚泥処理計画を策定する。これによって、運転員は、含水率低減による脱水汚泥搬出コストＣａの低減と脱水コストＣｂの増加との複雑なトレードオフ関係の理解や瞬間的な計算を問われることなく、どの運転条件が最適にあるかを判断できるようになる。 Thus, according to this embodiment, the management server 101 formulates a sludge treatment plan that satisfies the constraints (A) to (F) and is excellent in total cost C. As a result, the operator can determine which operating conditions are optimal without understanding the complex trade-off relationship between the reduction in the dewatered sludge transport cost Ca and the increase in the dewatering cost Cb due to the reduction of the water content and the instantaneous calculation. be able to determine whether there is
　そのため、これまでは様々な事情から総合コストＣの最適点で汚泥処理システム１０２の運転ができていなかったが、より総合コストＣで有利な運転条件で、汚泥処理システム１０２の運転が可能になる。また、誰もが客観的に汚泥処理計画を参照できるようになるため、熟練運転員の経験則に依存する必要性が軽減される。したがって、技術継承が比較的容易になり、持続的なリソース確保の実現に寄与する。また、汚泥搬出費用が削減され、下水処理の経済性が向上する。 Therefore, until now, the sludge treatment system 102 could not be operated at the optimum point of the total cost C due to various circumstances, but the sludge treatment system 102 can be operated under more advantageous operating conditions at the total cost C. . In addition, since anyone can objectively refer to the sludge treatment plan, the need to rely on the rules of thumb of experienced operators is reduced. Therefore, technology inheritance becomes relatively easy, contributing to the realization of sustainable securing of resources. In addition, the cost of carrying out sludge is reduced, improving the economic efficiency of sewage treatment.
　本実施例の汚泥処理管理システム１００は、たとえば、有機系工業廃水処理における脱水プロセス運転維持管理に適用可能である。 The sludge treatment management system 100 of this embodiment can be applied, for example, to the operation and maintenance of the dehydration process in organic industrial wastewater treatment.
　なお、本発明は前述した実施例に限定されるものではなく、添付した特許請求の範囲の趣旨内における様々な変形例及び同等の構成が含まれる。たとえば、前述した実施例は本発明を分かりやすく説明するために詳細に説明したものであり、必ずしも説明した全ての構成を備えるものに本発明は限定されない。また、ある実施例の構成の一部を他の実施例の構成に置き換えてもよい。また、ある実施例の構成に他の実施例の構成を加えてもよい。また、各実施例の構成の一部について、他の構成の追加、削除、または置換をしてもよい。 It should be noted that the present invention is not limited to the above-described embodiments, and includes various modifications and equivalent configurations within the spirit of the attached claims. For example, the above-described embodiments have been described in detail in order to explain the present invention in an easy-to-understand manner, and the present invention is not necessarily limited to those having all the described configurations. Also, part of the configuration of one embodiment may be replaced with the configuration of another embodiment. Moreover, the configuration of another embodiment may be added to the configuration of one embodiment. Moreover, other configurations may be added, deleted, or replaced with respect to a part of the configuration of each embodiment.
　また、前述した各構成、機能、処理部、処理手段等は、それらの一部又は全部を、たとえば集積回路で設計する等により、ハードウェアで実現してもよく、プロセッサがそれぞれの機能を実現するプログラムを解釈し実行することにより、ソフトウェアで実現してもよい。 In addition, each configuration, function, processing unit, processing means, etc. described above may be implemented in hardware, for example, by designing a part or all of them with an integrated circuit, and the processor implements each function. It may be realized by software by interpreting and executing a program to execute.
　各機能を実現するプログラム、テーブル、ファイル等の情報は、メモリ、ハードディスク、ＳＳＤ（Ｓｏｌｉｄ　Ｓｔａｔｅ　Ｄｒｉｖｅ）等の記憶装置、又は、ＩＣ（Ｉｎｔｅｇｒａｔｅｄ　Ｃｉｒｃｕｉｔ）カード、ＳＤカード、ＤＶＤ（Ｄｉｇｉｔａｌ　Ｖｅｒｓａｔｉｌｅ　Ｄｉｓｃ）の記録媒体に格納することができる。 Information such as programs, tables, files, etc. that realize each function is recorded on storage devices such as memory, hard disk, SSD (Solid State Drive), or IC (Integrated Circuit) card, SD card, DVD (Digital Versatile Disc) Can be stored on media.
　また、制御線や情報線は説明上必要と考えられるものを示しており、実装上必要な全ての制御線や情報線を示しているとは限らない。実際には、ほとんど全ての構成が相互に接続されていると考えてよい。 In addition, the control lines and information lines indicate those that are considered necessary for explanation, and do not necessarily indicate all the control lines and information lines necessary for implementation. In practice, it can be considered that almost all configurations are interconnected.

Claims (14)

  1. 　プログラムを実行するプロセッサと、前記プログラムを記憶する記憶デバイスと、を有し、汚泥を処理する汚泥処理システムにアクセス可能な汚泥処理管理装置であって、
    　前記プロセッサは、
    　前記汚泥処理システムを運転する複数の運転条件の各々について、前記運転条件に基づいて、前記汚泥処理システムで前記汚泥を脱水する脱水コストと、前記汚泥処理システムから脱水汚泥を搬出する搬出コストと、を算出し、前記搬出コストと前記脱水コストとを加算した総合コストを算出する算出処理と、
    　前記算出処理によって算出された前記運転条件ごとの総合コストに基づいて、特定の運転条件を決定する決定処理と、
    　前記決定処理によって決定された特定の運転条件を出力する出力処理と、
    　を実行することを特徴とする汚泥処理管理装置。     A sludge treatment management device having a processor for executing a program and a storage device for storing the program, and accessible to a sludge treatment system for treating sludge,
    The processor
    For each of a plurality of operating conditions for operating the sludge treatment system, a dewatering cost for dewatering the sludge in the sludge treatment system, a carrying-out cost for carrying out the dehydrated sludge from the sludge treatment system, and and a calculation process of calculating a total cost by adding the carrying-out cost and the dehydration cost;
    a determination process for determining a specific operating condition based on the total cost for each operating condition calculated by the calculation process;
    an output process for outputting the specific operating conditions determined by the determination process;
    A sludge treatment management device characterized by executing
  2. 　請求項１に記載の汚泥処理管理装置であって、
    　前記プロセッサは、
    　前記複数の運転条件の各々について、前記運転条件で前記汚泥処理システムを運転した場合に前記汚泥処理システムの運転に関する制約条件を遵守するか否かを判定する判定処理を実行し、
    　前記決定処理では、前記プロセッサは、前記制約条件を遵守した運転条件ごとの前記総合コストに基づいて、前記特定の運転条件を決定する、
    　ことを特徴とする汚泥処理管理装置。     The sludge treatment management device according to claim 1,
    The processor
    For each of the plurality of operating conditions, executing a determination process for determining whether or not the constraint conditions regarding the operation of the sludge treatment system are observed when the sludge treatment system is operated under the operating conditions,
    In the determination process, the processor determines the specific operating condition based on the total cost for each operating condition that complies with the constraint.
    A sludge treatment management device characterized by:
  3. 　請求項２に記載の汚泥処理管理装置であって、
    　前記判定処理では、前記プロセッサは、前記複数の運転条件のうち前記総合コストが最小の運転条件について、前記制約条件を遵守するか否かを判定し、
    　前記出力処理では、前記プロセッサは、前記制約条件を遵守する前記総合コストが最小の運転条件を出力する、
    　ことを特徴とする汚泥処理管理装置。     The sludge treatment management device according to claim 2,
    In the determining process, the processor determines whether or not the operating condition with the lowest total cost among the plurality of operating conditions complies with the constraint,
    In the output process, the processor outputs operating conditions with the lowest overall cost that comply with the constraints.
    A sludge treatment management device characterized by:
  4. 　請求項１に記載の汚泥処理管理装置であって、
    　前記運転条件は、前記汚泥処理システム内のフロック形成槽でフロックを形成するための前記フロック形成槽の運転条件である、
    　ことを特徴とする汚泥処理管理装置。     The sludge treatment management device according to claim 1,
    The operating conditions are operating conditions of the flocculation tank for forming flocs in the flocculation tank in the sludge treatment system.
    A sludge treatment management device characterized by:
  5. 　請求項１に記載の汚泥処理管理装置であって、
    　前記運転条件は、前記汚泥処理システム内のフロック形成槽で形成されたフロックを脱水する脱水機の運転条件である、
    　ことを特徴とする汚泥処理管理装置。     The sludge treatment management device according to claim 1,
    The operating conditions are operating conditions of a dehydrator that dewaters flocs formed in a flocculation tank in the sludge treatment system.
    A sludge treatment management device characterized by:
  6. 　請求項２に記載の汚泥処理管理装置であって、
    　前記制約条件は、前記汚泥処理システムを運転する運転員の労働時間を制約する条件である、
    　ことを特徴とする汚泥処理管理装置。     The sludge treatment management device according to claim 2,
    The constraint is a condition that constrains the working hours of an operator who operates the sludge treatment system.
    A sludge treatment management device characterized by:
  7. 　請求項２に記載の汚泥処理管理装置であって、
    　前記制約条件は、前記汚泥処理システムから脱水汚泥を搬出する搬出予定時刻を遵守すべき条件である、
    　ことを特徴とする汚泥処理管理装置。     The sludge treatment management device according to claim 2,
    The constraint is a condition that the scheduled time for carrying out the dehydrated sludge from the sludge treatment system should be observed.
    A sludge treatment management device characterized by:
  8. 　請求項２に記載の汚泥処理管理装置であって、
    　前記制約条件は、前記汚泥処理システムで動作するモータの電流量を制約する条件である、
    　ことを特徴とする汚泥処理管理装置。     The sludge treatment management device according to claim 2,
    The constraint is a condition that limits the current amount of the motor that operates in the sludge treatment system.
    A sludge treatment management device characterized by:
  9. 　請求項２に記載の汚泥処理管理装置であって、
    　前記制約条件は、前記汚泥処理システムにおける系内の圧力を制約する条件である、
    　ことを特徴とする汚泥処理管理装置。     The sludge treatment management device according to claim 2,
    The constraint is a condition that constrains the pressure in the sludge treatment system,
    A sludge treatment management device characterized by:
  10. 　請求項２に記載の汚泥処理管理装置であって、
    　前記制約条件は、前記汚泥処理システムでの前記汚泥の流出入を前記汚泥の貯留槽の容量から制約する条件である、
    　ことを特徴とする汚泥処理管理装置。     The sludge treatment management device according to claim 2,
    The constraint is a condition that restricts the inflow and outflow of the sludge in the sludge treatment system from the capacity of the sludge storage tank,
    A sludge treatment management device characterized by:
  11. 　請求項２に記載の汚泥処理管理装置であって、
    　前記制約条件は、前記汚泥処理システムでの前記脱水汚泥の流出入を前記汚泥の貯留槽の容量から制約する条件である、
    　ことを特徴とする汚泥処理管理装置。     The sludge treatment management device according to claim 2,
    The constraint is a condition that restricts the inflow and outflow of the dehydrated sludge in the sludge treatment system from the capacity of the sludge storage tank,
    A sludge treatment management device characterized by:
  12. 　請求項２に記載の汚泥処理管理装置であって、
    　前記制約条件を入力する画面が表示される
    　ことを特徴とする汚泥処理管理装置。     The sludge treatment management device according to claim 2,
    A sludge treatment management device, characterized in that a screen for inputting the constraint conditions is displayed.
  13. 　請求項１に記載の汚泥処理管理装置であって、
    　前記出力処理では、前記プロセッサは、記決定処理によって決定された特定の運転条件の運転コストと任意の運転条件の運転コストとの比較結果を出力する
    　ことを特徴とする汚泥処理管理装置。     The sludge treatment management device according to claim 1,
    The sludge treatment management device, wherein in the output process, the processor outputs a comparison result between the operating cost under the specific operating condition determined by the determining process and the operating cost under an arbitrary operating condition.
  14. 　プログラムを実行するプロセッサと、前記プログラムを記憶する記憶デバイスと、を有し、汚泥を処理する汚泥処理システムにアクセス可能な汚泥処理管理装置による汚泥処理管理方法であって、
    　前記プロセッサは、
    　前記汚泥処理システムを運転する複数の運転条件の各々について、前記運転条件に基づいて、前記汚泥処理システムで前記汚泥を脱水する脱水コストと、前記汚泥処理システムから脱水汚泥を搬出する搬出コストと、を算出し、前記搬出コストと前記脱水コストとを加算した総合コストを算出する算出処理と、
    　前記算出処理によって算出された前記運転条件ごとの総合コストに基づいて、特定の運転条件を決定する決定処理と、
    　前記決定処理によって決定された特定の運転条件を出力する出力処理と、
    　を実行することを特徴とする汚泥処理管理方法。     A sludge treatment management method using a sludge treatment management device having a processor for executing a program and a storage device for storing the program, and having access to a sludge treatment system for treating sludge,
    The processor
    For each of a plurality of operating conditions for operating the sludge treatment system, a dewatering cost for dewatering the sludge in the sludge treatment system, a carrying-out cost for carrying out the dehydrated sludge from the sludge treatment system, and and a calculation process of calculating a total cost by adding the carrying-out cost and the dehydration cost;
    a determination process for determining a specific operating condition based on the total cost for each operating condition calculated by the calculation process;
    an output process for outputting the specific operating conditions determined by the determination process;
    A sludge treatment management method characterized by executing
PCT/JP2022/017790 2021-06-30 2022-04-14 Sludge treatment management apparatus and sludge treatment management method WO2023276410A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2021-108448 2021-06-30
JP2021108448A JP2023006058A (en) 2021-06-30 2021-06-30 Sludge treatment management device and sludge treatment management method

Publications (1)

Publication Number Publication Date
WO2023276410A1 true WO2023276410A1 (en) 2023-01-05

Family

ID=84692690

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2022/017790 WO2023276410A1 (en) 2021-06-30 2022-04-14 Sludge treatment management apparatus and sludge treatment management method

Country Status (2)

Country Link
JP (1) JP2023006058A (en)
WO (1) WO2023276410A1 (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005288361A (en) * 2004-04-01 2005-10-20 Jfe Engineering Kk System for aiding volume-reduction of sludge
JP2009223386A (en) * 2008-03-13 2009-10-01 Toshiba Corp Biomass effective use support system
JP2015071129A (en) * 2013-10-02 2015-04-16 メタウォーター株式会社 Organic waste energy estimation method and device
JP2015071130A (en) * 2013-10-02 2015-04-16 メタウォーター株式会社 Apparatus and method for treatment of organic waste and control apparatus

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005288361A (en) * 2004-04-01 2005-10-20 Jfe Engineering Kk System for aiding volume-reduction of sludge
JP2009223386A (en) * 2008-03-13 2009-10-01 Toshiba Corp Biomass effective use support system
JP2015071129A (en) * 2013-10-02 2015-04-16 メタウォーター株式会社 Organic waste energy estimation method and device
JP2015071130A (en) * 2013-10-02 2015-04-16 メタウォーター株式会社 Apparatus and method for treatment of organic waste and control apparatus

Also Published As

Publication number Publication date
JP2023006058A (en) 2023-01-18

Similar Documents

Publication Publication Date Title
Hreiz et al. Optimal design and operation of activated sludge processes: State-of-the-art
Abbasi et al. Quality and cost analysis of a wastewater treatment plant using GPS-X and CapdetWorks simulation programs
Belloir et al. Energy benchmarking in wastewater treatment plants: the importance of site operation and layout
Barbu et al. On the evaluation of the global impact of control strategies applied to wastewater treatment plants
JP4906788B2 (en) Monitoring and control system for water and sewage treatment plants
Sid et al. Cost minimization in a full-scale conventional wastewater treatment plant: Associated costs of biological energy consumption versus sludge production
US10988394B2 (en) Cost control of wastewater treatment based on regulatory period
Jenkins Aeration control system design: a practical guide to energy and process optimization
Ozgun et al. Comparative evaluation of cost for preliminary and tertiary municipal wastewater treatment plants in Istanbul
Guerrini et al. Identifying the performance drivers of wastewater treatment plants through conditional order-m efficiency analysis
Fitzsimons et al. Assessing the thermodynamic performance of Irish municipal wastewater treatment plants using exergy analysis: a potential benchmarking approach
Musabandesu et al. Load shifting at wastewater treatment plants: A case study for participating as an energy demand resource
Póvoa et al. Modelling energy costs for different operational strategies of a large water resource recovery facility
Graves et al. Water pollution control using by‐pass piping
Piotrowski et al. Mixed integer nonlinear optimization of biological processes in wastewater sequencing batch reactor
di Cicco et al. Assessing energy performance and critical issues of a large wastewater treatment plant through full-scale data benchmarking
JP5193884B2 (en) Monitoring and control system for water supply facilities
De Ketele et al. Applying performance indices in plantwide modelling for a comparative study of wastewater treatment plant operational strategies
WO2023276410A1 (en) Sludge treatment management apparatus and sludge treatment management method
JP2003245653A (en) Operation supporting method for treatment system, operation supporting method for water treatment system and equipment therefor
Cassidy et al. Improving wastewater treatment plants operational efficiency and effectiveness through an integrated performance assessment system
Samuelsson et al. Cost-efficient operation of a denitrifying activated sludge process
JP2004267865A (en) Support system of water treatment process
JP2006260519A (en) Operation evaluation system and operation evaluation method for water treatment plant
De et al. Allocation of energy in surface water treatment plants for maximum energy conservation

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22832571

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE