CN109814510B - Sewage treatment lift pump optimal scheduling control method based on incoming water prediction - Google Patents
Sewage treatment lift pump optimal scheduling control method based on incoming water prediction Download PDFInfo
- Publication number
- CN109814510B CN109814510B CN201910098325.0A CN201910098325A CN109814510B CN 109814510 B CN109814510 B CN 109814510B CN 201910098325 A CN201910098325 A CN 201910098325A CN 109814510 B CN109814510 B CN 109814510B
- Authority
- CN
- China
- Prior art keywords
- water level
- sewage
- time
- data
- sewage pool
- Prior art date
- Legal status (The legal status 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 status listed.)
- Active
Links
Images
Landscapes
- Control Of Positive-Displacement Pumps (AREA)
- Feedback Control In General (AREA)
Abstract
The invention discloses an optimal scheduling control method for a sewage treatment lift pump based on incoming water prediction. The method comprises the following steps: establishing a prediction model of the inflow amount of sewage according to historical data of a sewage pool water level database and a local 24-hour precipitation amount database; collecting parameters of a lagoon, including: the maximum water level and the minimum water level allowed by the sewage pool, the rated water discharge amount and the number of the lift pumps and the expected operation time length; monitoring the current water level of the sewage pool in real time, and predicting the incoming sewage amount in the future preset time by establishing a prediction model of the incoming sewage amount by utilizing the current water level; and calculating the number of the lift pumps needing to be started at the corresponding moment by using the prediction result. The intelligent control system disclosed by the invention can be used for intelligently controlling the start and stop of the lifting pump through the control center, realizing the unattended operation of the sewage lifting pump and reducing the labor cost.
Description
The technical field is as follows:
the invention relates to the technical field of sewage treatment, in particular to a dispatching control method for a sewage treatment lift pump.
Background art:
1) with the promotion of economic development and urbanization of China, the demand for urban sewage treatment is increasing day by day. At present, although China makes great progress in the aspect of construction of urban sewage treatment plants, most of the sewage treatment plants have the problems of low automation level, light process management, high energy consumption, high operation and maintenance cost and the like.
2) The on-off working condition of the sewage lifting pump determines the water inflow of the sewage treatment system, the water inflow has important influence on the stability and the energy consumption of the sewage treatment operation, the lifting pump is also a second high-energy-consumption equipment system next to an air blower in the sewage treatment system, the working process of the lifting pump is optimally controlled and managed, and the lifting pump plays an extremely important role and significance in realizing the intelligent management and control, energy saving and cost reduction and unattended operation of a sewage treatment plant.
3) In the actual production process, the urban electricity charging usually implements a peak-valley electricity price policy, i.e. 24 hours a day is divided into two time intervals, wherein the peak interval is from morning to evening, the high charge is implemented, and the valley interval is from night to early morning, and the low charge is implemented. On the premise of ensuring the stability of sewage treatment, more sewage is treated in the valley section through reasonable scheduling of the sewage lifting pump, and the electric charge is saved.
4) When the sewage treatment lift pump is scheduled and controlled, the water level of the sewage pool is ensured not to be too high or too low. The periodic law of urban resident water consumption, the drainage habits of peripheral enterprises and the change of surface water flow permeating into a sewage pipe network are main factors of periodic change or sudden change of the water level of a sewage pool. The effective prediction of the factors can improve the reasonability of automatic scheduling of the sewage treatment lifting pump.
Disclosure of Invention
In order to overcome the defects, the invention aims to provide a sewage treatment lift pump optimal scheduling control algorithm based on sewage inflow prediction, so that the energy consumption cost is reduced while the stable operation of sewage treatment is kept.
In order to achieve the aim, the optimal scheduling control method of the sewage treatment lift pump based on the incoming water prediction comprises the following steps:
establishing a prediction model of the inflow amount of sewage according to historical data of a sewage pool water level database and a local 24-hour precipitation amount database;
collecting parameters of a lagoon, including: the maximum water level and the minimum water level allowed by the sewage pool, the rated water discharge amount and the number of the lift pumps and the expected operation time length;
the current water level of the sewage pool is monitored in real time,
predicting the incoming sewage amount in the future preset time by establishing a prediction model of the incoming sewage amount by utilizing the current water level;
and calculating the number of the lift pumps needing to be started at the corresponding moment by using the prediction result.
Preferably, the model for predicting the water volume of the sewage is constructed according to the following method:
2a) establishing a historical database H of the water level of the sewage pool, and storing samples per minute according to the time sequence to obtain the water level H (t), wherein the span of the historical data is N years;
2b) establishing a local precipitation database R, wherein data come from the actual precipitation per hour measured by a local weather station and are sequentially stored according to a time sequence;
2c) establishing a model for predicting the water level change of the sewage pool by precipitation;
by deltarRepresenting the change value of the water level of the sewage pool caused by precipitation, and the change value of the water level comes within one hour at the moment t
By riAn hourly precipitation amount r representing the hourly precipitation amount at time i, from 3 hours before the time to K hours after the time-3,r-2,r-1,r0,r1,…,rK-1As an input of the BP neural network, a water level change δ per hour within K hours from the present time is setr,0,δr,1,…δr,K-1And as the output of the BP neural network, neurons of the hidden layer and the output layer adopt Sigmoid functions, training samples are constructed from databases H and R, parameters of the BP neural network are obtained through random gradient descent training, and a prediction model of the rainfall on the water level change of the sewage pool is constructed.
Preferably, the optimized scheduling algorithm is as follows:
3a) predicting the water level change rate Q (t) of the sewage pool in a future preset time period through a model based on the current water level, the date of the day, the actual precipitation in the previous 3 hours and the precipitation forecast in the next K hours, wherein t represents time;
3b) according to the policy of differentiated charging of electricity peak valley of local cities in actual production, the method considers the following steps:
A. in the peak section of power utilization, the water level of the sewage treatment tank is kept as high as possible, and the scheduling method comprises the following steps:
B. in the valley section of power utilization, the water level of the sewage treatment tank should be kept at a low water level as much as possible, and the scheduling method comprises the following steps:
in the formula, T is the expected operation time of the lift pump, and the unit is minutes; q is the quotient of the rated displacement of the lift pump divided by the sectional area of the sewage pool, and the unit is meter/minute; n is the number of lift pump openings; h is the current water level of the sewage pool, and the unit is meter; hmaxThe allowable maximum water level of the sewage pool is meter; hminThe lowest allowable water level of the sewage pool is measured in meters; t represents time.
Preferably, the method for predicting the change rate q (t) of the water level of the wastewater tank in the future predetermined time period comprises the following steps:
41) calculating the current water level change rate
Wherein h (t) and h (t-3) are the water level data of the sewage pool at the time t and the time t-3 respectively
42) Calculating the historical reference water level change Q of the current dayd(t)：
Selecting data before the current date and 10 days after the current date from the historical database Q, and data 21 days from the previous date and 10 days after the current date to 10 days after the previous date in the previous year data to form an observation space together, and calculating the average value of each time, namely the average value of the data in the observation space
Wherein Qi,j(t) represents the water level change rate at time t, i.e., before the ith year (0 represents the current year), and j (when j is a negative number, it represents forward progress) when the current date is pushed backward.
43) Calculating the working day correction delta of water level changew(t)：
Each data in Q carries a working day label W, dates with the same label W are selected from Q, and the average value of the data with W being 0 is calculated to obtain QW＝0(t); calculating the average value of the data with W being 1 to obtain QW＝1(t); and calculating the mean value of all dates including working days and non-working days to obtain Qall(t)
Then it is determined that,
44) calculating a rain correction delta for a lift pump during a desired operating timer(t)：
For the current time t, the actually measured rainfall data of the first three hours and the rainfall data of the last K hours of the weather forecast form input data, the input data are sent to a neural network model, and the predicted rainfall correction quantity delta within the K hours is obtainedr(t) of (d). K takes the value CEIL (T/60), which represents an upper integer function. Where T is the desired operating time of the lift pump in minutes.
45) Comprehensively obtaining the prediction result of the water level change:
the liquid level sensor is used for collecting liquid level data and transmitting the liquid level data to the control center, the control center transmits the data to the processing center, and the processing center calculates in real time through the optimization algorithm to obtain the number of the lifting pumps needing to be started at corresponding time and transmits the number of the lifting pumps to the control center. And the control center determines and controls the lift pump needing to be started and closed according to the current starting condition of the lift pump. It has the following advantages:
1. according to the invention, by optimizing the scheduling algorithm, the electricity consumption cost in the sewage treatment process is effectively reduced;
2. the intelligent control system disclosed by the invention can be used for intelligently controlling the start and stop of the lifting pump through the control center, realizing the unattended operation of the sewage lifting pump and reducing the labor cost.
3. The invention supports manual control, automatic control and remote control of starting and stopping of the water pump equipment and supports remote switching control modes.
Description of the drawings:
FIG. 1 is a diagram of a BP neural network model structure
FIG. 2 flow chart for predicting water level change of wastewater tank
FIG. 3 is a flow chart of lift pump operation control
Detailed Description
The invention will be further described with reference to the accompanying drawings.
The method comprises the steps that the liquid level sensor is used for collecting liquid level data and transmitting the liquid level data to the control center, the control center transmits the data to the processing center to carry out prediction and optimization algorithm real-time calculation on the incoming sewage amount, the number of the lifting pumps needing to be started at the corresponding moment is obtained, and the data are transmitted to the control center. And the control center determines and controls the lift pump needing to be started and closed according to the current starting condition of the lift pump. The method of controlling the lift pump to turn on and off is one of automatic control, manual control or remote control. And if the lift pump does not need to be switched, continuously acquiring liquid level data, and performing optimal scheduling calculation at the next moment.
Fig. 1 is a diagram of a BP neural network model architecture. It is a multi-layer feedforward neural network, and the signal is transmitted in the forward direction and the error is propagated in the backward direction. x is the number of1,x2,…xnIs its input data at the input layer, y1,y2,…ymIt is output from the output layer, and 1 hidden layer, w, is arranged in the middleijIs the network weight from the input layer to the hidden layer, wjkIs the network weight from the hidden layer to the output layer.
FIG. 2 is a flow chart of the prediction of the change in the water level in the wastewater tank. Where the solid lines represent the online calculation of the data and the dashed lines represent the storage of the data and the offline calculation of the model. It can be seen that the following steps are included:
(1) data storage and modeling
1a) And establishing a historical database H of the water level of the sewage pool, and storing samples per minute according to the time sequence to obtain the water level H (t), wherein the span of the historical data is N years (N is recommended to be more than or equal to 3). For a sewage pool with constant bottom and upper cross-sectional area, the water inflow amount per unit time is proportional to the water level change per unit time.
1b) And establishing a production water level change rate database Q. Each datum of the differential is obtained by H, namely the water level at the later moment is subtracted by the water level at the former moment. And Q (t) represents the water level change rate of the sewage pool at the t moment in meters per minute. Meanwhile, a weekday label W is added to each data in the database, a label value equal to 0 indicates a non-weekday (double holiday, legal holiday), and a label value equal to 1 indicates a weekday.
1c) And establishing a local precipitation database R, wherein the data come from the actual precipitation per hour measured by a local weather station and are sequentially stored according to the time sequence.
1d) And establishing a model for predicting the water level change of the sewage pool by precipitation.
By deltarRepresenting the change value of the water level of the sewage pool caused by precipitation, and the change value of the water level comes within one hour at the moment t
By riAn hourly precipitation amount r representing the hourly precipitation amount at time i, from 3 hours before the time to K hours after the time-3,r-2,r-1,r0,r1,…,rK-1As an input of the BP neural network, a water level change δ per hour within K hours from the present time is setr,0,δr,1,…δr,K-1As the output of the BP neural network, the hidden layer neuron and the output layer neuron adopt Sigmoid functions to construct training samples from databases H and R, parameters of the BP neural network are obtained through training by a stochastic gradient descent method,and building a prediction model of the precipitation on the water level change of the sewage pool.
(2) Prediction of wastewater tank level change
Predicting the change rate Q (t) of the water level of the sewage pool at the future time t, and firstly using the current water level change rate
Predicting the future water level change rate; obtaining the historical reference water level change rate Q of t time by using a probability statistical methodd(t) predicting future water level change rate based on the empirical data; then the difference of the water level change rule of working day and non-working day is considered, and the correction quantity delta is addedw(t); then according to the real-time data of precipitation before the time t and the precipitation forecast given by the weather station after the time t, the real-time data is sent into a trained neural network to forecast the water level influence delta caused by precipitationr(t) of (d). Last pair of
Qd(t),δw(t),δr(t) performing weighted combination.
The specific implementation mode is as follows:
2a) calculating the current water level change rate
Wherein h (t) and h (t-3) are the water level data of the sewage pool at the time t and the time t-3 respectively
2b) Calculating the historical reference water level change Q of the current dayd(t)：
Selecting data before the current date and 10 days after the current date from the historical database Q, and data 21 days from the previous date and 10 days after the current date to 10 days after the previous date in the previous year data to form an observation space together, and calculating the average value of each time, namely the average value of the data in the observation space
Wherein Qi,j(t) represents the water level change rate at time t, i.e., before the ith year (0 represents the current year), and j (when j is a negative number, it represents forward progress) when the current date is pushed backward.
2c) Calculating the working day correction delta of water level changew(t)：
Each data in Q carries a working day label W, dates with the same label W are selected from Q, and the average value of the data with W being 0 is calculated to obtain QW＝0(t); calculating the average value of the data with W being 1 to obtain QW＝1(t); and calculating the mean value of all dates including working days and non-working days to obtain Qall(t)
Then it is determined that,
2d) calculating a rain correction delta for a lift pump during a desired operating timer(t)：
For the current time t, the actually measured rainfall data of the first three hours and the rainfall data of the last K hours of the weather forecast form input data, the input data are sent to a neural network model, and the predicted rainfall correction quantity delta within the K hours is obtainedr(t) of (d). K takes the value CEIL (T/60), which represents an upper integer function. Where T is the desired operating time of the lift pump in minutes.
2e) Comprehensively obtaining the prediction result of the water level change:
wherein the coefficient alpha1,α2,α3,α4The values of (A) are 0.4, 0.6, 1 and 0.6 in sequence.
Fig. 3 is a flowchart of lift pump operation control. It can be seen that the optimal scheduling method for the sewage treatment lift pump comprises the following steps:
determining the maximum water level and the minimum water level allowed by the sewage pool, the rated water discharge amount and the number of the lift pumps and the expected operation time length, and inputting the maximum water level and the minimum water level, the rated water discharge amount and the number of the lift pumps and the expected operation time length into a processing unit;
and establishing a mathematical model of the sewage inflow amount according to historical data of the sewage pool water level database and the local 24-hour precipitation amount database.
Collecting liquid level data and transmitting the liquid level data to a control unit;
the control unit transmits the liquid level data to the processing unit;
the processing unit calculates and processes the liquid level data through an optimized scheduling algorithm:
5a) firstly, forecasting the actual precipitation in the first 3 hours and the precipitation in the last K hours based on the current water level, the date of the day, and the actual precipitation in the last 3 hours, and forecasting the water level change rate Q (t) of the sewage pool in a period of time in the future through a model.
5b) According to the policy of differentiated charging of electricity peak valley of local cities in actual production, the method considers the following steps:
A. in the peak section of power utilization, the water level of the sewage treatment tank is kept as high as possible, and the scheduling method comprises the following steps:
B. in the valley section of power utilization, the water level of the sewage treatment tank should be kept at a low water level as much as possible, and the scheduling method comprises the following steps:
in the formula, T is the expected operation time of the lift pump, and the unit is minutes; q is the quotient of the rated displacement of the lift pump divided by the sectional area of the sewage pool, and the unit is meter/minute; n is the number of lift pump openings; h is the current water level of the sewage pool, and the unit is meter; hmaxThe allowable maximum water level of the sewage pool is meter; hminThe lowest allowable water level of the sewage pool is measured in meters; t represents time.
Claims (3)
1. A sewage treatment lift pump optimal scheduling control method based on incoming water prediction is characterized by comprising the following steps:
establishing a prediction model of the inflow amount of sewage according to historical data of a sewage pool water level database and a local 24-hour precipitation amount database;
collecting parameters of a lagoon, including: the maximum water level and the minimum water level allowed by the sewage pool, the rated water discharge amount and the number of the lift pumps and the expected operation time length;
the current water level of the sewage pool is monitored in real time,
predicting the incoming sewage amount in the future preset time by establishing a prediction model of the incoming sewage amount by utilizing the current water level;
calculating the number of lift pumps needing to be started at corresponding moment by using the prediction result;
the sewage inflow water quantity prediction model is constructed according to the following method:
2a) establishing a historical database H of the water level of the sewage pool, and storing samples per minute according to the time sequence to obtain the water level H (t), wherein the span of the historical data is N years;
2b) establishing a local precipitation database R, wherein data come from the actual precipitation per hour measured by a local weather station and are sequentially stored according to a time sequence;
2c) establishing a model for predicting the water level change of the sewage pool by precipitation;
by deltarIndicating the change value of the water level of the sewage pool caused by precipitation, and the change value of the water level of the sewage pool within every minute at the moment t
By riAn hourly precipitation amount r representing the hourly precipitation amount at time i, from 3 hours before the time to K hours after the time-3,r-2,r-1,r0,r1,…,rK-1As an input of the BP neural network, a water level change δ per hour within K hours from the present time is setr,0,δr,1,…δr,K-1And as the output of the BP neural network, neurons of the hidden layer and the output layer adopt Sigmoid functions, training samples are constructed from databases H and R, parameters of the BP neural network are obtained through random gradient descent training, and a prediction model of the rainfall on the water level change of the sewage pool is constructed.
2. The incoming water prediction-based optimal scheduling control method for a sewage treatment lift pump according to claim 1, wherein the optimal scheduling control method comprises the following steps:
3a) predicting the water level change rate Q (t) of the sewage pool in a future preset time period through a model based on the current water level, the date of the day, the actual precipitation in the previous 3 hours and the precipitation forecast in the next K hours, wherein t represents time;
3b) according to the policy of differentiated charging of electricity peak valley of local cities in actual production, the method considers the following steps:
A. in the peak section of power utilization, the water level of the sewage treatment tank is kept as high as possible, and the scheduling method comprises the following steps:
B. in the valley section of power utilization, the water level of the sewage treatment tank should be kept at a low water level as much as possible, and the scheduling method comprises the following steps:
in the formula, T is the expected operation time of the lift pump, and the unit is minutes; q is the quotient of the rated displacement of the lift pump divided by the sectional area of the sewage pool, and the unit is meter/minute; n is the number of lift pump openings; h is the current water level of the sewage pool, and the unit is meter; hmaxThe allowable maximum water level of the sewage pool is meter; hminThe lowest allowable water level of the sewage pool is measured in meters; t represents time.
3. The incoming water prediction-based optimal scheduling control method for a wastewater treatment lift pump according to claim 2, wherein the method for predicting the wastewater pool water level change rate q (t) in the predetermined period of time in the future comprises:
41) calculating the current water level change rate
Wherein h (t) and h (t-3) are the water level data of the sewage pool at the time t and the time t-3 respectively;
42) calculating the historical reference water level change Q of the current dayd(t)：
Selecting data before the current date and 10 days after the current date from the historical database Q, and data 21 days from the previous date and 10 days after the current date to 10 days after the previous date in the previous year data to form an observation space together, and calculating the average value of each time, namely the average value of the data in the observation space
Wherein Qi,j(t) represents year i before, 0 represents the current year; pushing the current date backwards by the jth day, wherein if j is a negative number, the current date is pushed forwards; the rate of change of water level at time t;
43) calculating the working day correction delta of water level changew(t)：
Each data in Q carries a workday label W, a label value equal to 0 indicates a non-workday, and a label value equal to 1 indicates a workday; selecting dates with the same W label from Q, and calculating the mean value of the data with W being 0 to obtain QW＝0(t); calculating the average value of the data with W being 1 to obtain QW＝1(t); and calculating the mean value of all dates including working days and non-working days to obtain Qall(t)
Then it is determined that,
44) calculating a rain correction delta for a lift pump during a desired operating timer(t)：
For the current time t, the actually measured rainfall data of the first three hours and the rainfall data of the last K hours of the weather forecast form input data, the input data are sent to a neural network model, and the predicted rainfall correction quantity delta within the K hours is obtainedr(t)(ii) a K takes the value of CEIL (T/60), and CEIL represents an upper integer function; where T is the expected operating time of the lift pump in minutes;
45) comprehensively obtaining the prediction result of the water level change rate of the sewage pool:
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910098325.0A CN109814510B (en) | 2019-01-31 | 2019-01-31 | Sewage treatment lift pump optimal scheduling control method based on incoming water prediction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910098325.0A CN109814510B (en) | 2019-01-31 | 2019-01-31 | Sewage treatment lift pump optimal scheduling control method based on incoming water prediction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109814510A CN109814510A (en) | 2019-05-28 |
| CN109814510B true CN109814510B (en) | 2022-02-22 |
Family
ID=66606099
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910098325.0A Active CN109814510B (en) | 2019-01-31 | 2019-01-31 | Sewage treatment lift pump optimal scheduling control method based on incoming water prediction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109814510B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114542442A (en) * | 2022-03-01 | 2022-05-27 | 陕西新泓水艺环境科技有限公司 | Water treatment lift pump scheduling control method and device, electronic equipment and medium |
| CN115493636A (en) * | 2022-05-23 | 2022-12-20 | 中冶华天工程技术有限公司 | Multi-target drainage pump drainage quantity calculation method based on buffer area |
| CN115124097B (en) * | 2022-07-08 | 2024-05-03 | 陕西新泓水艺环境科技有限公司 | Balanced water inlet control method, device, water inlet device, system and medium |
| CN116700039A (en) * | 2023-08-04 | 2023-09-05 | 山东科能电气设备有限公司 | Control method, system, equipment and medium for urban emergency drainage system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006004097A (en) * | 2004-06-16 | 2006-01-05 | Fuji Electric Systems Co Ltd | Pump controller |
| CN105353711A (en) * | 2015-10-29 | 2016-02-24 | 上海水顿智能科技有限公司 | Intelligent draining scheduling system and method |
| CN106401932A (en) * | 2016-11-03 | 2017-02-15 | 中冶华天工程技术有限公司 | Sewage treatment lift pump running control method |
| CN106597879A (en) * | 2016-11-03 | 2017-04-26 | 中冶华天工程技术有限公司 | Sewage treatment elevator pump optimized scheduling method |
| CN106647244A (en) * | 2016-11-03 | 2017-05-10 | 中冶华天工程技术有限公司 | Sewage treatment lift pump operation system |
-
2019
- 2019-01-31 CN CN201910098325.0A patent/CN109814510B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006004097A (en) * | 2004-06-16 | 2006-01-05 | Fuji Electric Systems Co Ltd | Pump controller |
| CN105353711A (en) * | 2015-10-29 | 2016-02-24 | 上海水顿智能科技有限公司 | Intelligent draining scheduling system and method |
| CN106401932A (en) * | 2016-11-03 | 2017-02-15 | 中冶华天工程技术有限公司 | Sewage treatment lift pump running control method |
| CN106597879A (en) * | 2016-11-03 | 2017-04-26 | 中冶华天工程技术有限公司 | Sewage treatment elevator pump optimized scheduling method |
| CN106647244A (en) * | 2016-11-03 | 2017-05-10 | 中冶华天工程技术有限公司 | Sewage treatment lift pump operation system |
Non-Patent Citations (1)
| Title |
|---|
| 混合BP神经网络在城市污水量预报中的应用;董淑福;《城镇供水》;20130815(第04期);第51-54页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109814510A (en) | 2019-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109814510B (en) | Sewage treatment lift pump optimal scheduling control method based on incoming water prediction | |
| KR101864342B1 (en) | Method for Optimal Water Supply Pump Operation Based on Short-term Water Demand Forecasting Considering Disinfection Performance in Clearwell | |
| CN104318325B (en) | Many basin real-time intelligent water quality prediction methods and system | |
| CN111206647B (en) | Unattended controller and control method for regional booster pump station for urban water supply | |
| CN106765959A (en) | Heat-air conditioner energy-saving control method based on genetic algorithm and depth B P neural network algorithms | |
| CN113536684A (en) | Intelligent cooperative optimization scheduling method for water taking and supplying pump station of water supply plant | |
| CN109886567B (en) | Short-term load prediction method considering somatosensory temperature and radiation intensity | |
| CN111340316B (en) | Intelligent water supply management method and system | |
| CN101858095A (en) | Processing method and device for providing auxiliary dispatching data of water supply network | |
| CN110443418A (en) | Urban water consumption prediction technique based on GA-BP neural network | |
| JP2003027567A (en) | Sewage inflow estimating device and method, and server device | |
| KR100741691B1 (en) | Water Management System and method for Optimal Operation and Control in Wide-area Waterworks using ubiquitous technology | |
| KR101119983B1 (en) | Method for predicting water demand using Group Method of Data Handling algorithm | |
| CN115062904A (en) | Digital water supply pipe network scheduling method and system | |
| CN114610085A (en) | Liquid level control method of secondary water supply tank based on water age | |
| CN115796915A (en) | Electricity price prediction method and system for electricity trading market | |
| CN117432941B (en) | Optimization adjustment method and system for water supply pressure of water plant | |
| JP4399318B2 (en) | Pump control device | |
| CN114542442A (en) | Water treatment lift pump scheduling control method and device, electronic equipment and medium | |
| CN201730136U (en) | Processing device for supplying auxiliary scheduling data of water supply network | |
| CN113487131A (en) | Station network interaction method based on charging demand and energy storage adjustment | |
| CN117217407A (en) | Method, medium and device for pre-evaluating carbon emission of power system | |
| CN113723708B (en) | Urban daily water consumption prediction method based on machine learning | |
| CN105549396B (en) | A kind of city drainage by open canal system control method based on online Dynamic Programming | |
| CN115577905A (en) | Peak regulation energy optimization scheduling method for cascade hydropower station group |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |