JP2023148459A - System, method, and program for estimating infiltration/inflow into separate sewer pipes - Google Patents

Abstract

To provide a technology that increases accuracy of estimating an occurrence location of infiltration/inflow into separate sewer pipes.SOLUTION: An infiltration/inflow estimation system that estimates infiltration/inflow that occurs in a plurality of areas during rainy weather includes: acquisition means for acquiring the amount of rainfall for each area at each time; measurement means for measuring flow-in amounts of sewage flowing into a sewage treatment plant from a plurality of areas at each time; calculation means for calculating a difference between flow-in amounts during sunny weather and flow-in amounts during rainy weather as a total amount of infiltration/inflow, among the flow-in amounts; means for grasping flow-in amounts on weekdays and holidays/national holidays among the flow-in amounts; means for determining a total amount of rainfall in each area by adding the amount of rainfall in each area; means for calculating a total amount of infiltration/inflow at each time within a specific time after the start of rainfall; and means for determining a value for specifying the amount of infiltration/inflow in each area on the basis of the total amount of infiltration/inflow for each of weekdays and holidays/national holidays, the total amount of rainfall in each area, and a time relation before and after the rainfall to estimate an area where the infiltration/inflow occurs from the value.SELECTED DRAWING: Figure 1

Description

The present invention relates to a technique for estimating the location of rainwater intrusion into a separate sewer pipe.

Rainwater collected on the ground by rainfall flows into rivers following various routes. Patent Document 1 discloses a system for associating rainfall information with river water rise, and obtaining information for predicting flood damage. In addition, rainwater flows not only into rivers but also into separate sewer pipes, which are not originally intended to collect rainwater, increasing the total amount of water that must be treated at sewage treatment facilities. Patent Document 2 discloses a system for estimating from which area infiltration water, which was originally not expected, is coming from.

JP2020-085441A Patent No. 5574769

In order to understand where unknown water is occurring, it is necessary to collect and analyze the buried state of pipes, operation data of sewage treatment plants, flow rate measurement data for investigation, etc., and narrow down the locations where unknown water is occurring. Research requires a lot of effort, time, and cost. For example, it is necessary to install meters to measure the flow rate at multiple points along a sewer pipe. In the estimation method described in Patent Document 2, it is difficult to increase the estimation accuracy, and there is room for improvement.

The present invention has been made in view of the above-mentioned circumstances, and its purpose is to provide a technique for increasing the accuracy of estimating the location where water intruding into a separate sewer pipe occurs.

An infiltration water estimation system according to one aspect of the present invention includes:
An infiltration water estimation system that estimates infiltration water that occurs in multiple areas during rainy days,
Acquisition means for acquiring the amount of rainfall for each area at each time;
Measuring means for measuring the amount of sewage flowing into the sewage treatment plant from the plurality of areas at each time;
Calculating means for calculating the difference between the amount of inflow on a sunny day and the amount of inflow on a rainy day as a total amount of infiltration water, of the amount of inflow;
Means for grasping the inflow amount on weekdays and holidays and holidays among the inflow amount;
Means for calculating the total amount of rainfall in each area by integrating the amount of rainfall in each area;
means for calculating the total amount of infiltrated water at each time within a specific time after the start of rainfall;
A value that specifies the amount of infiltrated water in each area is determined from the total amount of infiltrated water for each weekday, holiday, and holiday, total rainfall in each area, and the time relationship before and after rainfall, and the area where infiltrated water occurs is estimated from this value. means and
This is a system for estimating water intrusion into a separate sewer pipe.

A method for estimating infiltration water according to one aspect of the present invention includes:
A method for estimating infiltration water that occurs in multiple areas during rainy days, the method comprising:
an acquisition step of acquiring the amount of rainfall for each area at each time;
a measurement step of measuring the amount of sewage flowing into the sewage treatment plant from the plurality of areas at each time;
A calculation step of calculating the difference between the inflow amount on a sunny day and the inflow amount on a rainy day as the total amount of infiltration water among the inflow amounts;
Of the inflow amount, determining the inflow amount on weekdays and weekends and holidays;
A step of accumulating the amount of rainfall in each area and calculating the total amount of rainfall in each area;
a step of calculating the total amount of infiltrated water at each time within a specific time after the start of rain;
A process of determining the value that specifies the infiltrating water in each area from the total amount of infiltrating water for each weekday, holiday, and public holiday, the total amount of rainfall in each area, and the time relationship before and after rainfall, and estimating the area where flooding will occur from this value. and,
This is a method for estimating water intrusion into a separate sewer pipe.

A program according to one aspect of the present invention is
A program that operates on a computer on an infiltration water estimation system that estimates infiltration water that occurs in multiple areas during rainy days,
an acquisition step of acquiring the amount of rainfall for each area at each time;
a measurement step of measuring the amount of sewage flowing into the sewage treatment plant from the plurality of areas at each time;
A calculation step of calculating the difference between the inflow amount on a sunny day and the inflow amount on a rainy day as the total amount of infiltration water among the inflow amounts;
Of the inflow amount, determining the inflow amount on weekdays and weekends and holidays;
A step of accumulating the amount of rainfall in each area and calculating the total amount of rainfall in each area;
a step of calculating the total amount of infiltrated water at each time within a specific time after the start of rain;
A process of determining the value that specifies the infiltrating water in each area from the total amount of infiltrating water for each weekday, holiday, and public holiday, the total amount of rainfall in each area, and the time relationship before and after rainfall, and estimating the area where flooding will occur from this value. and,
This is a program for estimating water infiltration into separate sewer pipes, which allows a computer to execute the following.

Further, the present invention can also be understood as a computer-readable recording medium on which the above program is recorded non-temporarily. Note that each of the above means and processes can be combined to the extent possible to constitute the present invention.

According to the present invention, it is possible to provide a technique that increases the accuracy of estimating the location where water intrudes into a separate sewer pipe.

FIG. 1 is an explanatory diagram of an infiltration water estimation system according to a first embodiment. FIG. 2 is a diagram showing the relationship between the amount of rainfall and the amount of infiltrated water. FIG. 3 is a block diagram showing the configuration of the processing device. FIG. 4 is a functional block diagram of the intrusion water estimation system according to the first embodiment. FIG. 5 is an explanatory diagram of rainfall amount data set as dummy data. FIG. 6 is a diagram showing the ranking of a plurality of processing sections. FIG. 7 is a schematic diagram of a predetermined target area divided into meshes. FIG. 8 is a flowchart showing an example of the process flow of the intrusion water estimation system according to the first embodiment. FIG. 9 is a diagram showing the correspondence between the amounts of direct intrusion water and indirect infiltration water and the total amount of infiltration water. FIG. 10 is a functional block diagram of the intrusion water estimation system according to the second embodiment. FIG. 11 is a flowchart illustrating an example of the processing flow of the infiltration water estimation system according to the second embodiment.

Hereinafter, embodiments will be described with reference to the drawings. The embodiment shown below is one aspect of this application, and does not limit the scope of rights of this application.

<First embodiment>
FIG. 1 is an explanatory diagram of an infiltration water estimation system according to a first embodiment. The intrusion water estimation system 10 is a system that includes a processing device 1 and estimates intrusion water that occurs in a plurality of areas during rainy weather. The infiltration water estimation system 10 assumes a separate sewer system in which wastewater and rainwater flow down separate pipes. The sewage pipe 2 has a sewage pipe 3 through which sewage flows and a rainwater pipe 4 through which rainwater flows. Sewage generated from homes, businesses, etc. in multiple areas flows through sewage pipes 3 and flows into a sewage treatment facility (sewage treatment plant) 5. The wastewater that has flowed into the sewage treatment facility 5 is treated within the sewage treatment facility 5 and discharged into a river or the like. Rainwater flows through the rainwater pipe 4 and is directly discharged into a river or the like. In separate sewer systems, wastewater is discharged to a sewage treatment plant and rainwater is discharged directly into rivers or the sea. Since sewage and rainwater are collected through separate pipes, the water quality of the river is protected and is an excellent method from both an environmental and sanitary standpoint, and in recent years, separate systems have been increasingly adopted.

When the weather is sunny, only sewage flows through the sewage pipe 3 and flows into the sewage treatment facility 5. In rainy weather, in addition to sewage, rainwater that should not originally be combined may flow into the sewage pipe 3 and then flow into the sewage treatment facility 5. When the wastewater pipe 3 is damaged, rainwater that has entered the soil flows into the wastewater pipe 3 from the damaged part of the wastewater pipe 3, and the rainwater is mixed into the wastewater flowing through the wastewater pipe 3. Infiltration water from this damaged area is defined as indirect infiltration water. Furthermore, if the rainwater pipe 4 is incorrectly connected to the wastewater pipe 3, rainwater flows from the rainwater pipe 4 into the wastewater pipe 3, and the rainwater mixes with the wastewater flowing through the wastewater pipe 3. The rainwater that has flowed into the sewage pipe 3 flows through the sewage pipe 3 and flows into the sewage treatment facility 5. In this specification, rainwater that has flowed into the wastewater pipe 3 is referred to as infiltrated water. This infiltrated water is also called unknown water. Rainwater that infiltrates from the rainwater pipe 4 into the wastewater pipe 3 due to incorrect connection or the like is defined as direct infiltration water. In a separate sewer system, since rainwater is separated, unintended rainwater can flow into the sewer pipes, exceeding the treatment capacity of the sewage treatment plant and being discharged into rivers, etc. without being sufficiently treated. Become. The purpose of this system is to estimate the areas where these infiltrated waters occur.

The observation device 6 observes the amount of rainfall in a plurality of areas. The processing device 1 acquires rainfall data for each area from the observation device 6 in specific time units. The measurement sensor 7 measures the total amount of wastewater flowing into the sewage treatment facility 5 from a plurality of areas. The processing device 1 acquires the amount of inflow of wastewater from the measurement sensor 7.

FIG. 2 is a diagram showing the relationship between the amount of rainfall and the amount of infiltrated water. The vertical axis of the graph shows the amount of water, and the horizontal axis shows the time. Infiltrated water is generated by rainfall, and the amount of infiltrated water (the amount of infiltrated water in rainy weather) is affected by factors such as infiltration through the soil and differences in the time it takes to reach the pipes depending on the rainfall conditions. As shown in FIG. 2, the times of the peak amount of rainfall and the peak amount of infiltrated water do not coincide, and what is characteristic is that infiltrated water enters over time after the start of rainfall. Similarly, intrusion water continues to flow in for some time even after the rain has stopped.

FIG. 3 is a block diagram showing the configuration of the processing device 1. As shown in FIG. The processing device 1 includes a control device 11, a communication interface (IF) device 12, a storage device 13, an input device 14, and a display device 15. The processing device 1 includes hardware resources such as a processor (CPU), memory, and storage. The memory may be RAM. The storage may be a nonvolatile storage device (eg, ROM, flash memory, etc.). The functions of each processing means (functional unit) of the processing device 1 are realized by loading a program stored in a storage into a memory and executing it by a processor. Note that the configuration of the processing device 1 is not limited to these. For example, all or part of the function may be configured with a circuit such as an ASIC or FPGA, or all or part of the function may be executed by a cloud server or other device.

The communication interface device 12 communicates with the observation device 6 and the measurement sensor 7 . Note that the data may be obtained not directly from the observation device 6 or the measurement sensor 7, but via a cloud server or a control device that stores data on the amount of rainfall and total water flow obtained therefrom. The storage device 13 stores various information and various data. The input device 14 may include input devices such as a keyboard, a mouse, operation buttons, and a touch panel. The display device 15 is, for example, a liquid crystal display, a plasma display, an organic EL (Electro Luminescence) display, or the like.

The control device 11 includes a rainfall amount data acquisition means 101, a flow rate measuring means 102, a first inundation amount calculation means 103, a total rainfall amount calculation means 104, a second inundation amount calculation means 105, and an estimation means 106. , has. In the control device 11, not all of the components shown in FIG. 3 are essential, and components of the control device 11 may be added or deleted as appropriate. Further, the components of the control device 11 may be combined as appropriate.

The rainfall data acquisition means 101 acquires rainfall data for each area. For example, the target area is divided into multiple areas. The area of interest may be separated by a mesh. The rainfall data acquisition means 101 may acquire rainfall data for each area at each time (hour). The rainfall amount data for each time is rainfall amount data from a predetermined time (for example, 13:00) to a predetermined time (for example, 14:00). The rainfall amount data acquisition means 101 may acquire rainfall amount data per unit time within a certain period of time from the start of rain for each area. The fixed time is an arbitrary time and can be changed. Further, in this specification, "every time" may be read as "per unit time". The rainfall data acquisition means 101 may directly acquire rainfall data from the observation device 6, or indirectly obtain rainfall data provided by a public organization such as the Japan Meteorological Agency or a private organization. It may also be obtained manually. The rainfall data acquisition means 101 stores the acquired rainfall data in the storage device 13.

The rainfall data acquisition means 101 extracts rainfall data for each day of the week on weekdays from the rainfall data stored in the storage device 13. Further, the rainfall data acquisition means 101 extracts rainfall data on Saturdays, Sundays, and holidays from the rainfall data stored in the storage device 13 as well. The rainfall data acquisition means 101 stores rainfall data for each day of the week on weekdays and rainfall data for weekends and holidays anew in the storage device 13. As a result, rainfall amount data for weekdays, weekends, and holidays are stored in the storage device 13 in a labeled state.

The flow rate measuring means 102 measures the inflow rate of sewage flowing into the sewage treatment facility 5 from a plurality of areas (hereinafter also simply referred to as "sewage inflow rate") based on the inflow rate of sewage measured by the measurement sensor 7. ). The flowing water amount measuring means 102 may acquire the amount of sewage flowing in each time as sewage inflow amount data. The inflow amount of sewage at each time is the inflow amount of sewage from a predetermined time (for example, 13:00) to a predetermined time (for example, 14:00).

The flow rate measuring means 102 acquires data on the amount of sewage flowing in when the amount of sewage flowing in is a steady amount, and data on the amount of sewage flowing in when the amount of sewage flowing in exceeds the steady amount. More specifically, in sunny weather, the sewage flowing into the sewage treatment facility 5 does not contain rainwater, so the amount of sewage flowing in can be defined as a steady amount. On the other hand, in rainy weather, the sewage flowing into the sewage treatment facility 5 contains rainwater, so the amount of sewage flowing in exceeds the steady amount. Since the inflow amount of sewage varies depending on weekdays, weekends, and holidays, the steady amount is set as a value that varies depending on weekdays, weekends, and holidays. This is because the amount of gray water used in people's daily lives differs between weekdays and weekends and holidays.In the same way, industrial wastewater also depends on the operating status of factories and company work, and differs between weekdays and holidays at factories and companies. The focus is on the large difference in usage. The flowing water amount measuring means 102 acquires the amount of sewage flowing in when the amount of sewage flowing in is a steady amount as data on the amount of sewage flowing in on a clear day. The flowing water amount measuring means 102 measures the amount of sewage flowing in from the start of rain, thereby obtaining data on the amount of sewage flowing in during rainy weather. The flow rate measuring means 102 may measure the inflow rate of wastewater at each time during rainy weather. The flow rate measuring means 102 measures the flow rate of sewage within a specific time from the start of rain (until a predetermined time elapses from the start of rain), thereby obtaining data on the flow rate of sewage during rainy weather. good. The flow rate measuring means 102 may measure the inflow rate of wastewater at each time within a specific time from the start of rainfall. The flow rate measuring means 102 stores in the storage device 13 data on the amount of sewage flowing in on a sunny day and data on the amount of sewage flowing on a rainy day.

The flow rate measuring means 102 extracts inflow rate data for each day of the week from the flow rate stored in the storage device 13. The inflow amount data for each day of the week on weekdays includes inflow amount data for each day of the week on a sunny day and inflow amount data for each day of the week on a rainy day. Further, the water flow measuring means 102 extracts inflow data on weekends and holidays from the water flow stored in the storage device 13. The inflow data on Saturdays, Sundays, and holidays includes inflow data during sunny days on Saturdays, Sundays, and holidays, and inflow data during rainy days on Saturdays, Sundays, and holidays. The flow rate measuring means 102 stores the inflow rate data for each day of the week on weekdays and the inflow rate data for weekends and holidays anew in the storage device 13. As a result, the inflow data for each day of the week, weekends, and holidays is stored in the storage device 13 in a labeled state.

The first inundation amount calculation means 103 calculates the difference between the inflow amount of sewage on a sunny day and the inflow amount of sewage on a rainy day as the total amount of infiltration water. The first inundation amount calculating means 103 calculates the difference between the inflow amount of sewage during a clear day in a predetermined period and the inflow amount of sewage in a rainy day in a predetermined period, out of the inflow amount of sewage in a predetermined period. It may be calculated as the total amount of The first inundation amount calculation means 103 stores data on the total amount of infiltration water for a predetermined period in the storage device 13.

The first inundation amount calculation means 103 grasps the inflow amount of sewage on weekdays and the inflow amount of sewage on Saturdays, Sundays, and holidays out of the inflow of sewage. The first inundation amount calculating means 103 calculates the difference between the inflow amount of sewage during sunny weather for each weekday and the inflow amount of sewage during rainy weather for each weekday as the total amount of infiltration for each weekday. You may. The first inundation amount calculating means 103 calculates the difference between the inflow amount of sewage during sunny weather on each weekend and holiday and the inflow amount of sewage during rainy weather on each weekend and holiday as the total amount of infiltration water for each weekend and holiday. good. The first inundation amount calculation means 103 stores in the storage device 13 the total amount of infiltrated water data for each weekday and the total amount of infiltrated water data for each weekend and holiday.

The first inundation amount calculating means 103 may calculate the difference between the inflow amount of sewage at each time in sunny weather and the inflow amount of sewage at each time in rainy weather as the total amount of infiltration water at each time. The first inundation amount calculation means 103 calculates the total amount of infiltration water at each time by comparing the inflow amount of sewage water in sunny weather and the inflow amount of sewage water in rainy weather for the same time period on the same day of the week. Good too. In addition, the first inundation amount calculating means 103 calculates the total amount of infiltration water at each time by comparing the inflow amount of sewage water during sunny days and the inflow amount of sewage water during rainy days for the same time period on holidays. It's okay.

The total rainfall calculation means 104 integrates the amount of rainfall in each area within a specific time, and calculates the total amount of rainfall in each area. The total rainfall calculation means 104 stores total rainfall data in each area in the storage device 13.

The second inundation amount calculation means 105 calculates the total amount of infiltration water at each time within a specific time after the start of rain. The estimation means 106 calculates a value that specifies the amount of infiltrated water in each area from the total amount of infiltrated water on weekdays, weekends, and holidays, the total amount of rainfall in each area, and the time relationship before and after rainfall, and uses the value to determine the occurrence of infiltrated water. Estimate the area. The estimating means 106 estimates from which area out of the plurality of areas the infiltrated water has flowed into the sewage treatment facility 5. The estimating means 106 may estimate one of a plurality of areas as the area where infiltration water is occurring, or estimate two or more of the plurality of areas as the area where infiltration water is occurring. You may. The estimating means 106 may use multiple regression analysis to estimate the area where infiltrated water is occurring.

The estimating unit 106 may estimate the area where infiltrated water occurs using an estimation model learned by deep learning or the like. FIG. 4 is a functional block diagram of the intrusion water estimation system 10 according to the first embodiment. As shown in FIG. 4, by inputting inflow data for each time, weekdays, weekends, and holidays, and rainfall amount data for each time into the generated estimation model, the day-of-week flow rate prediction model 110, estimation is possible. The estimation accuracy of the means 106 is improved. Furthermore, the estimation means 106 may function as an estimation model.

Inflow data for each weekday, weekends, and holidays is stored in the storage device 13 in a labeled state. Inflow data for each day of the week on weekdays and Saturdays, Sundays, and holidays is extracted from the storage device 13, and input into the flow rate prediction model 110 for each day of the week. Total rainfall data for each area is stored in the storage device 13. Rainfall data for each time is extracted from the storage device 13 and input to the day-of-week flow rate prediction model 110. Further, the rainfall amount data for each time is used as rainfall occurrence data for determining the presence or absence of rain at the relevant time. Rainfall occurrence data is also used as a trigger for difference calculations. The result of calculating the difference between the amount of sewage flowing in on a sunny day and the amount of sewage flowing in on a rainy day is input to the day-of-the-week flow rate prediction model 110 . The day-of-week flow rate prediction model 110 performs a process of estimating the amount of infiltrated water.

Dummy data may be applied to the estimation model in order to improve the accuracy of the estimation model. An example of dummy data will be described with reference to FIG. 5. FIG. 5 is an explanatory diagram of rainfall amount data set as dummy data. FIG. 5A shows a state in which the entire target area (total treatment area) is divided into subdivisions (subsections). In the example shown in FIG. 5, the entire processing area is divided into 20 processing subdivisions (areas), but the present invention is not limited to the example shown in FIG. 5, and the entire area may be divided into another number of processing subdivisions. As shown in (b) and (c) of FIG. 5, heavy rainfall with a large amount of rainfall is selected as one of the plurality of processing divisions, and light rainfall with a small amount of rainfall is set in the other processing divisions. In FIG. 5(b), processing section No. Heavy rainfall is set to No. 1, and processing division No. Light rainfall is expected between 2 and 20. In FIG. 5(c), processing section No. 2 is set as heavy rainfall, and processing division No. Light rainfall is expected from 1.3 to 20. From then on, processing division no. For 3 to 20, the process of setting heavy rainfall in one of the plurality of processing divisions and setting light rainfall in the other processing divisions is repeated. In this way, the amount of rainfall set as dummy data is set such that when one of the plurality of processing divisions is selected as a heavy rainfall, the other processing divisions are set as a light rainfall. The amount of rainfall for heavy rainfall is set to be greater than the amount of rainfall for light rainfall. The rainfall duration for heavy rainfall is set shorter than the rainfall duration for light rainfall.

The amount of infiltrated water is calculated by inputting the plurality of dummy data set as described above into the estimation model, and inputting the inflow amount data for each day of the week and the rainfall amount data for each hour into the estimation model. By sequentially performing the process of setting one of the multiple treatment zones to heavy rainfall and the other treatment zones to light rainfall, the amount of infiltration water for all treatment zones is calculated. . The amount of infiltrated water in the treatment subdivision may be the amount of infiltrated water (m ³ /ha) in rainy weather per unit area of the treatment subdivision (drainage area). By calculating and comparing the amount of infiltrated water in a plurality of treatment divisions, the ranking of the amount of inundation in the plurality of treatment divisions is determined.

Figure 6 shows the relationship between the inundation rankings of multiple treatment divisions determined based on the infiltration volume calculated by the estimation model and the inundation rankings of multiple treatment divisions determined based on the infiltration volume in statistical data. It is a diagram. This is a comparison between actual statistical data and estimated results obtained by installing multiple water flow measuring instruments on the flow paths of sewer pipes in a specific region of the Kanto region. Actual statistical data is also used as training data and verification data in machine learning. In Figure 6, a solid line connects the rankings of multiple treatment divisions determined based on the amount of infiltrated water calculated by the estimation model, and a dotted line connects the rankings of multiple treatment divisions determined based on the amount of infiltrated water in statistical data. . As shown in Figure 6, there is almost no difference between the ranking of multiple treatment divisions determined based on the amount of infiltration water calculated by the estimation model and the ranking of multiple treatment divisions determined based on the amount of infiltration water in the statistical data. The result is that there is no. Since there is no large discrepancy between the estimation results calculated by the estimation model and the statistical results, it can be understood that the estimation accuracy of the estimation model is high and the estimation model is valid.

FIG. 7 is a schematic diagram of a predetermined target area divided into meshes. Flowmeters for measuring the flow rate of wastewater flowing through the wastewater pipe 3 are installed at each position indicated by white circles in FIG. By measuring the flow rate of sewage measured by each flow meter, it was actually determined in which of the multiple areas infiltration water occurred. It was confirmed that the area where infiltration water is occurring as estimated by the estimating means 106 and the area where intrusion water is occurring and identified by actual measurement are the same.

FIG. 8 is a flowchart illustrating an example of the process flow of the intrusion water estimation system 10 according to the first embodiment. In S<b>1 , the flow rate measuring means 102 acquires wastewater inflow rate data, and stores the wastewater inflow rate data in the storage device 13 . In S2, the flow rate measuring means 102 extracts inflow rate data for each day of the week from the storage device 13. In S3, the total rainfall calculation means 104 acquires total rainfall data for each area (subdivision) by integrating the amount of rainfall for each area, and stores the total rainfall data for each area in the storage device 13. remember. In S4, the rainfall data acquisition means 101 extracts rainfall amount data for each area at each time from the storage device 13.

In S5, the estimating means 106 inputs the inflow amount data for each day of the week and the rainfall amount data for each time into the day-of-week flow rate prediction model 110. In S6, dummy data is input into the day-of-week flow rate prediction model 110. In S7, the estimating means 106 determines whether application to all processing sections has been completed. If the process of creating dummy data by setting heavy rainfall in one of the plurality of processing divisions and setting light rainfall in the other processing divisions is performed for all processing divisions (S7; YES), Proceed to S8. On the other hand, if uncreated dummy data remains (S7; NO), the process advances to S6.

In S8, the first inundation amount calculating means 103 calculates the difference in the amount of infiltrated water during rainy weather, calculates the total amount of infiltrated water for each day of the week on weekdays, and the total amount of infiltrated water for each weekend and holiday, and stores the data in the storage device. 13. In S8, the estimating means 106 inputs the total amount of infiltrated water data for each day of the week, weekends, and holidays into the day-of-week flow rate prediction model 110. In S9, the estimation means 106 acquires the estimation result of the amount of infiltration water for each treatment division from the day-of-week flow rate prediction model 110.

The estimation means 106 may determine the ranking of the plurality of treatment divisions by comparing the amounts of infiltration water in the plurality of treatment divisions calculated by the day-of-week flow rate prediction model 110. The estimation means 106 compares the amount of infiltrated water in the plurality of treatment divisions with a threshold value. When the amount of infiltration water in at least one of the plurality of treatment divisions is equal to or greater than the threshold value, the estimation means 106 estimates at least one of the plurality of treatment divisions as the treatment division in which infiltration water is occurring. The threshold value is determined in advance by design, experiment, or simulation, and is stored in the storage device 13.

The control device 11 may display on the display device 15 information regarding the amount of infiltrated water in a plurality of treatment divisions, information regarding the treatment division where infiltration water is occurring, and the like. Further, the control device 11 may display information regarding the amount of infiltrated water in a plurality of treatment divisions, information regarding the treatment division where infiltration water is occurring, etc. on an external display device.

According to the infiltration water estimation system 10 according to the first embodiment, the amount of infiltration water generated in the area (treatment division) takes into account the amount of sewage inflow (domestic wastewater amount and industrial wastewater amount) that changes depending on weekdays, holidays, and holidays. Therefore, the amount of infiltrated water in multiple areas can be estimated with high accuracy. Since the area where infiltrated water is occurring can be estimated with high accuracy, it becomes possible to efficiently repair the location where infiltrated water occurs. Since it is sufficient to measure the amount of wastewater flowing into the sewage treatment facility 5, there is no need to set measuring instruments such as flowmeters in a wide area, and costs can be reduced. Furthermore, by applying dummy data that sets heavy rainfall to a specific processing division and light rainfall to other processing divisions, it is possible to improve the accuracy of machine learning in the estimation model.

<Second embodiment>
An infiltration water estimation system according to a second embodiment will be described. In the second embodiment, the same components as in the first embodiment are given the same reference numerals as in the first embodiment, and the description thereof will be omitted as appropriate.

The infiltrated water includes infiltrated water that directly entered the wastewater pipe 3 (hereinafter also referred to as direct infiltrated water), and infiltrated water that indirectly entered the wastewater pipe 3 (hereinafter also referred to as indirect infiltrated water). ) and are included. Directly infiltrating water is, for example, infiltrating water that has unintentionally joined the wastewater pipe 3, or infiltrating water that has flowed into the wastewater pipe 3 due to the rainwater pipe 4 being incorrectly connected to the wastewater pipe 3. Indirect infiltration water is infiltration water that has flowed into the wastewater pipe 3 from a damaged part of the wastewater pipe 3. The arrival time from the start of rainfall until the direct infiltration water reaches the sewage treatment facility 5 is different from the arrival time from the start of the rain until the indirect infiltration water reaches the sewage treatment facility 5. This is based on the assumption that the locations of direct and indirect sewer pipes are approximately the same. Direct infiltration water flows into the sewage treatment facility 5 at a certain time after the start of rain. The indirect infiltration water once enters underground, such as the soil, and stagnates therein, and then flows into the sewage pipe 3. Therefore, the infiltration water that flows into the sewage treatment facility 5 within a certain time after the start of rain contains a large amount of direct infiltration water, and the sewage treatment facility The infiltrated water flowing into No. 5 contains a large amount of indirect infiltrated water.

FIG. 9 is a diagram showing the correspondence between the amounts of direct intrusion water and indirect infiltration water and the total amount of infiltration water. The vertical axis in FIG. 9 indicates the amount of infiltrated water, and the horizontal axis in FIG. 9 indicates time. The solid line L1 in FIG. 9 shows the total amount of infiltrating water, the solid line L2 in FIG. 9 shows the amount of direct intruding water, and the dotted line L3 in FIG. 9 shows the amount of indirect invading water. The total amount of infiltrated water is the sum of the amount of direct infiltrated water and the amount of indirect infiltrated water. As shown in FIG. 9, the amount of direct infiltration water is larger than the amount of indirect infiltration water until a predetermined time T1, but after the predetermined time T1, the amount of indirect infiltration water becomes larger than the amount of direct infiltration water. The predetermined time T1 is, for example, a certain time after the start of rain. Further, after the predetermined time T1, the time when the value of the direct inundation amount L2 becomes 0 is the time when the rain has almost ended.

The arrival time from the start of rain until the direct infiltration water reaches the sewage treatment facility 5 is shorter than the arrival time from the start of the rain until the indirect infiltration water reaches the sewage treatment facility 5. For example, if the total amount of infiltrated water suddenly decreases after a certain period of time after the start of rain, it can be said that the ratio of the amount of direct infiltrated water to the total amount of infiltrated water is large. For example, if the total amount of infiltrated water gradually decreases after a certain period of time after the start of rain, it can be said that the ratio of the amount of indirect infiltrated water to the total amount of infiltrated water is large.

The estimating means 106 estimates whether the infiltrated water during the rainfall and in the specific period after the rain is direct infiltrated water or indirect infiltrated water based on the temporal change in the total amount of infiltrated water during the rain and during the specific period after the rain. The estimation means 106 calculates the ratio of the amount of direct infiltration water to the total amount of infiltration water during and after rainfall, and the ratio of the amount of direct infiltration water to the total amount of infiltration water during and after rainfall, based on the time change in the total amount of infiltration water during and during specific periods after rainfall. The ratio of the amount of indirect intrusion water to the total amount of infiltration water in a later specific period may be estimated. The estimation means 106 may estimate the ratio of the amount of direct infiltration water and the ratio of the amount of indirect infiltration water using the day-of-week flow rate prediction model 110. The estimation means 106 estimates whether the infiltrated water during a specific period of time during and after rainfall is direct infiltrated water or indirect infiltrated water based on the ratio of the amount of direct infiltrated water and the ratio of the amount of indirect infiltrated water. good.

Processing performed by the intrusion water estimation system 10 according to the second embodiment will be described with reference to FIGS. 10 and 11. FIG. 10 is a functional block diagram of the intrusion water estimation system 10 according to the second embodiment. As shown in FIG. 10, in the intrusion water estimation system 10 according to the second embodiment, estimation processing for direct intrusion water and indirect intrusion water is added compared to the intrusion water estimation system 10 according to the first embodiment. There is.

FIG. 11 is a flowchart showing an example of the process flow of the intrusion water estimation system 10 according to the second embodiment. In S11 to S19 shown in FIG. 11, the same processing as S1 to S9 shown in FIG. 8 is performed. In S20, the estimating means 106 estimates the ratio of the amount of direct infiltrated water and the ratio of the amount of indirect infiltrated water based on the temporal change in the total amount of infiltrated water during and during a specific period after the rain. In S20, the estimating means 106 estimates whether the infiltrated water during a specific period of time during and after rainfall is direct infiltrated water or indirect infiltrated water, based on the ratio of the amount of direct infiltrated water and the ratio of the amount of indirect infiltrated water. do. The control device 11 may display, on the display device 15, information indicating that the infiltrated water during and during a specific period after the rain is direct infiltrated water or indirect infiltrated water. Further, the control device 11 may display on the external display device information indicating that the infiltrated water during and during a specific period after the rain is direct infiltrated water or indirect infiltrated water. The estimation process may use any of statistical processing, multivariate analysis, and machine learning such as deep learning.

According to the infiltration water estimation system 10 according to the second embodiment, as in the first embodiment, areas (treatment divisions) are created in consideration of the amount of sewage (domestic wastewater amount and industrial wastewater amount) that changes depending on weekdays, holidays, and public holidays. In order to estimate the amount of infiltrated water that occurs in multiple areas, it is possible to estimate the amount of infiltrated water in multiple areas with high accuracy. Since the area where infiltrated water is occurring can be estimated with high accuracy, it becomes possible to efficiently repair the location where infiltrated water occurs. Since it is sufficient to measure the amount of wastewater flowing into the sewage treatment facility 5, there is no need to set measuring instruments such as flowmeters in a wide area, and costs can be reduced. Furthermore, by applying dummy data that sets heavy rainfall to a specific processing division and light rainfall to other processing divisions, it is possible to improve the accuracy of machine learning in the estimation model.

According to the infiltration water estimation system 10 according to the second embodiment, it is possible to grasp the ratio of the amount of direct infiltration water and the ratio of the amount of indirect intrusion water to the total amount of infiltration water during and during a specific period after rainfall. . According to the infiltration water estimation system 10 according to the second embodiment, it is possible to understand that intrusion water during a specific period of time during and after rainfall is direct infiltration water or indirect infiltration water. This makes it easy to narrow down the locations where the infiltrated water occurs in the area where the infiltrated water occurs, and it becomes possible to repair the locations where the infiltrated water occurs more efficiently.

<Modified example>
An infiltration water estimation system 10 according to a modification will be described. The storage device 13 may store history information on construction of the wastewater pipe 3. The storage device 13 is an example of a storage section. The history information of the construction of the wastewater pipe 3 includes the location and time of the construction of the wastewater pipe 3 in each area. The history information of the construction of the wastewater pipe 3 may further include a summary of the construction of the wastewater pipe 3. The first inundation amount calculation means 103 calculates the total amount of infiltration water at each time within a predetermined period. The first inundation amount calculating means 103 detects changes in the total amount of infiltration water at each time within a predetermined period. For example, if the difference between the total amount of infiltrated water at the first time within the predetermined period and the total amount of infiltrated water at the second time consecutive to the first time within the predetermined period is equal to or greater than the threshold value, then the predetermined period of time is The total amount of infiltrated water at the second time point may change.

The first inundation amount calculating means 103 stores changes in the total amount of infiltration water at each time within a predetermined period in the storage device 13 in association with construction history information. If the total amount of infiltration water at the second time within the predetermined period changes, and the time of construction of the sewage pipe 3 and the second time within the predetermined period coincide or are similar, the first inundation amount calculation The means 103 may store a change in the total amount of infiltrated water at a second time within a predetermined period in the storage device 13 in association with the construction history information.

The storage device 13 may store soil change information. The soil change information includes the position where the soil change occurred in each area and the time when the soil change occurred. The soil change information may further include information regarding the cause of the soil change. The causes of soil changes include, for example, typhoons, heavy rain, and river flooding. The first inundation amount calculation means 103 stores changes in the total amount of infiltrated water at each time within a predetermined period in the storage device 13 in association with soil change information. For example, if the total amount of infiltration water changes at the second time within a predetermined period, and the time when soil change occurs coincides with or is similar to the second time within the predetermined period, the first inundation amount The calculation means 103 may store a change in the total amount of infiltrated water at a second time within a predetermined period in the storage device 13 in association with the soil change information.

The above process may be performed by the second water inundation amount calculation means 105 or may be performed by another calculation means different from the first water inundation amount calculation means 103. The control device 11 may display on the display device 15 information regarding changes in the total amount of infiltrated water at each time within a predetermined period and construction history information associated with changes in the total amount of infiltrated water. The control device 11 may display on the display device 15 information regarding changes in the total amount of infiltrated water at each time within a predetermined period and soil change information associated with changes in the total amount of infiltrated water. Further, the control device 11 may display this information on an external display device.

According to the infiltration water estimation system 10 according to the modified example, it is possible to grasp the extent to which construction of the sewage pipe 3 and soil changes affect changes in the total amount of infiltration water. If the total amount of infiltrated water increases, there is a possibility that infiltrated water is occurring at the location where the sewer pipe 3 is being constructed or where soil changes have occurred. By understanding the location of sewage pipe 3 construction and the location where soil changes have occurred, it becomes easier to narrow down the locations where infiltrated water is occurring in the area where infiltrated water is occurring, and it is possible to repair the locations where infiltrated water is occurring. This can be done even more efficiently.

Each of the processes described above may be regarded as a method (infiltration water estimation method) executed by a computer. Moreover, you may consider it as a program (infiltration water estimation program) for making a computer perform each process demonstrated above. Furthermore, the program may be provided to the computer through a network or from a computer-readable recording medium that holds data non-temporarily.

1... Processing device 2... Sewage pipe 3... Sewage pipe 4... Storm drain 5... Sewage treatment facility 6... Observation device 7... Measurement sensor 10... Infiltration water estimation system 11...Control device 12...Communication interface device 13...Storage device 14...Input device 15...Display device 101...Rainfall data acquisition means 102...Flow rate measuring means 103. ...First inundation amount calculation means 104...Total rainfall amount calculation means 105...Second inundation amount calculation means 106...Estimation means 110...Flow rate prediction model by day of the week

Claims (8)

An infiltration water estimation system that estimates infiltration water that occurs in multiple areas during rainy days,
Acquisition means for acquiring the amount of rainfall for each area at each time;
Measuring means for measuring the amount of sewage flowing into the sewage treatment plant from the plurality of areas at each time;
Calculating means for calculating the difference between the amount of inflow on a sunny day and the amount of inflow on a rainy day as a total amount of infiltration water, of the amount of inflow;
Means for grasping the inflow amount on weekdays and holidays and holidays among the inflow amount;
Means for calculating the total amount of rainfall in each area by integrating the amount of rainfall in each area;
means for calculating the total amount of infiltrated water at each time within a specific time after the start of rainfall;
A value that specifies the amount of infiltrated water in each area is determined from the total amount of infiltrated water for each weekday, holiday, and holiday, total rainfall in each area, and the time relationship before and after rainfall, and the area where infiltrated water occurs is estimated from this value. means and
A system for estimating water intrusion into a separate sewer pipe, characterized by comprising: 2. The estimation means applies dummy data simulating rainfall in a specific area to the estimation model for estimating the area where the infiltration water occurs. Infiltration water estimation system. The amount of rainfall set as the dummy data is determined by dividing the entire treatment area into small sections, and when selecting one category that will experience heavy rainfall with a large amount of rainfall, The system for estimating water infiltration into a separate sewer pipe according to claim 2, characterized in that the system is set so that there is little rainfall. Based on temporal changes in the total amount of infiltrated water during and after rainfall during a specific period, it can be estimated whether the infiltrated water is coming from a damaged part of a separate sewer pipe, or whether the infiltrated water is coming from unintended rainwater confluence or incorrect connection of pipes. The system for estimating water intrusion into a separate sewer pipe according to any one of claims 1 to 3. 5. The system for estimating water intrusion into a separate sewer pipe according to any one of claims 1 to 4, wherein the amount of water intrusion is the amount of water intrusion per unit area of the drainage area during rainy weather. A storage unit that stores at least one of construction history information including the location and timing of construction of the separate sewer pipe in each area, and soil change information including the location where soil change occurred and the time when soil change occurred in each area. and,
Calculating the total amount of infiltrating water at each time within a predetermined period, and storing the change in the total amount of infiltrating water at each time in the predetermined period in correspondence with at least one of the construction history information and the soil change information. a means of remembering,
6. The system for estimating water infiltration into a separate sewer pipe according to any one of claims 1 to 5. A method for estimating infiltration water that occurs in multiple areas during rainy days, the method comprising:
an acquisition step of acquiring the amount of rainfall for each area at each time;
a measurement step of measuring the amount of sewage flowing into the sewage treatment plant from the plurality of areas at each time;
A calculation step of calculating the difference between the inflow amount on a sunny day and the inflow amount on a rainy day as the total amount of infiltration water among the inflow amounts;
Of the inflow amount, determining the inflow amount on weekdays and weekends and holidays;
A step of accumulating the amount of rainfall in each area and calculating the total amount of rainfall in each area;
a step of calculating the total amount of infiltrated water at each time within a specific time after the start of rain;
A process of determining the value that specifies the infiltrating water in each area from the total amount of infiltrating water for each weekday, holiday, and public holiday, the total amount of rainfall in each area, and the time relationship before and after rainfall, and estimating the area where flooding will occur from this value. and,
A method for estimating water infiltration into a separate sewer pipe, the method comprising: A program that operates on a computer on an infiltration water estimation system that estimates infiltration water that occurs in multiple areas during rainy days,
an acquisition step of acquiring the amount of rainfall for each area at each time;
a measurement step of measuring the amount of sewage flowing into the sewage treatment plant from the plurality of areas at each time;
A calculation step of calculating the difference between the inflow amount on a sunny day and the inflow amount on a rainy day as the total amount of infiltration water among the inflow amounts;
Of the inflow amount, determining the inflow amount on weekdays and weekends and holidays;
A step of accumulating the amount of rainfall in each area and calculating the total amount of rainfall in each area;
a step of calculating the total amount of infiltrated water at each time within a specific time after the start of rain;
A process of determining the value that specifies the infiltrating water in each area from the total amount of infiltrating water for each weekday, holiday, and public holiday, the total amount of rainfall in each area, and the time relationship before and after rainfall, and estimating the area where flooding will occur from this value. and,
A program for estimating water infiltration into separate sewer pipes to be executed by a computer.

Images