Scheduling method and system based on water supply status of water supply pump group

Abstract

The present application relates to the technical field of water supply scheduling, and in particular to a scheduling method and system based on the water supply status of a water supply pump group. The method includes: inputting the water supply status of the water supply pump group at the observation point in the water supply path into a corrosion prediction model, predicting the corrosion increment of the observation point, taking the sum of the corrosion increment and the initial corrosion as the real-time corrosion of each observation point, and taking the maximum value of the real-time corrosion as the path state of the water supply path; constructing a scheduling matrix and calculating the target, the target value evaluates the scheduling effect from two aspects: the water quality parameters received from the water use point meet the water quality requirements, and the path state variance of each water supply path after the water supply scheduling, updating the scheduling matrix, and realizing water supply scheduling according to the scheduling matrix when the target value takes the minimum value. Through the technical solution of the present application, it is possible to monitor the pipeline status in the water supply network to prevent the occurrence of pipeline network leakage.

Description

Technical Field

[0001] The present application relates to the technical field of water supply scheduling, and in particular to a scheduling method and system based on the water supply status of a water supply pump group. Background Art

[0002] Water resources are an indispensable material resource in people's daily lives. Water resources are consumed in all aspects of life, production, farming, etc. In order to meet people's demand for water resources, water resources need to be dispatched and transported from various water storage points to various water use points through water supply pipelines.

[0003] At present, the patent application document with publication number CN118211814A discloses a method and system for optimizing the scheduling of water supply networks based on data analysis, wherein the method includes: dividing the water supply network into multiple target areas, deploying multiple groups of detection points on the water supply network in the target areas, and collecting water supply data, water pressure data, flow data and water quality data of the target areas in real time; obtaining historical water consumption data and population data in the target areas and inputting them into a pre-trained predictive water consumption model, and outputting the predicted water consumption of the target areas; comparing the predicted water consumption with the preset water supply, and if If the predicted water consumption is greater than the preset water supply, the water supply in the current target area is judged to be insufficient, and the water supply in the target area with insufficient water supply is adjusted according to the water supply scheduling strategy; otherwise, the water supply in the current target area is judged to be sufficient; the water supply quality index of the target area after the water supply adjustment is calculated based on the water pressure data, flow data, and water quality data, the water supply quality index is combined with the actual water consumption change data to obtain the water supply abnormality, the water supply abnormality is compared with the water supply abnormality threshold interval, and the current target area status is judged as water supply abnormality, water supply normal or pipe network failure according to the comparison result.

[0004] However, although the above method can dynamically adjust the water supply scheduling strategy according to the water supply quality index and the degree of water supply abnormality, and timely discover potential pipe network leakage, in the process of water supply scheduling, the monitoring of the pipeline status in the water supply network is ignored, and the pipe network leakage cannot be prevented. Summary of the invention

[0005] In order to solve the technical problem of being unable to prevent pipe network leakage, the present application provides a scheduling method and system based on the water supply status of a water supply pump group, which can monitor the status of pipelines in the water supply network to prevent pipe network leakage.

[0006] In a first aspect of the present application, a scheduling method based on the water supply status of a water supply pump group is provided, the scheduling method comprising: inputting the water supply status of the water supply pump group at the observation point in the water supply path into a corrosion prediction model, predicting the corrosion increment of the observation point, taking the sum of the corrosion increment and the initial corrosion as the real-time corrosion of each observation point, and taking the maximum value of the real-time corrosion as the path state of the water supply path, the water supply status being a time series of water quality parameters and working parameters of the water supply pump group; constructing a scheduling matrix, and calculating a target value, the scheduling matrix including the water supply volume of any water storage point and each water use point, the target value for:

[0007] ; is the number of water storage points, is the number of water use points, For water storage point water quality parameters, For water storage point To the water point The water supply, From each water storage point to the water use point The water supply, For water point Average water quality parameters, is the number of water supply paths, For water supply path Real-time corrosion degree, is the Pearson correlation coefficient between water quality parameters and corrosion increment, For water supply path Water quality parameters of the connected water storage point, To find the sign of the variance; update the scheduling matrix under the constraints of water storage capacity and water consumption, and realize water supply scheduling based on the scheduling matrix when the target value takes the minimum value.

[0008] Through the technical solution provided by the present application, the water supply network includes multiple water supply paths, and each water supply path is provided with multiple observation points; for any water supply path, the time series of the working parameters of the water supply pump group and the water quality parameters of each observation point are input into the corrosion prediction model to obtain the corrosion increment of the observation point, and further the sum of the corrosion increment and the initial corrosion is used as the real-time corrosion of each observation point, and the maximum value of the real-time corrosion is used as the path state of the water supply path, so as to realize real-time monitoring of the pipeline state in the water supply network; further, a scheduling matrix is ​​constructed and the target value is calculated, and the target value evaluates the effect of water supply scheduling from two aspects: whether the water quality parameters received from the water use point meet the water quality requirements, and the path state variance of each water supply path after water supply scheduling, the scheduling matrix is ​​continuously updated, and water supply scheduling is realized according to the scheduling matrix when the target value takes the minimum value, so as to avoid large differences in path states between water supply paths, which may lead to pipeline leakage.

[0009] In one embodiment, the water quality parameter includes at least one of pH value, hardness, conductivity, chloride ion concentration and dissolved oxygen.

[0010] Water quality parameters can affect the corrosion degree of pipelines by affecting the electrochemical corrosion process, resulting in changes in the path state of the water supply path. Using water quality parameters as input to the corrosion prediction model can accurately predict the corrosion increment.

[0011] In one embodiment, the corrosion prediction model is a recurrent neural network, which extracts time series features from the time series of water quality parameters and working parameters to obtain water quality time series features and working time series features, and regresses the multidimensional data composed of the water quality time series features and the working time series features into corrosion degree increments.

[0012] In one embodiment, the training method of the corrosion prediction model includes: taking the time series of water quality parameters and working parameters between any two moments as a group of training samples, and taking the increase in the measured corrosion degree between the two moments as the label value of the training sample; after inputting the training sample into the corrosion prediction model, taking the mean square error function between the output result and the label value as the loss function to update the corrosion prediction model; iteratively updating the corrosion prediction model until the loss function is less than the set value, completing the training.

[0013] The trained corrosion prediction model can learn the mapping relationship between the time series of water quality parameters and working parameters and the corrosion increment. Using the trained corrosion prediction model, only the water quality parameters transmitted by the sensors deployed in the pipeline and the working parameters of the water supply pump group are needed to accurately predict the corrosion increment inside the pipeline, thereby realizing accurate monitoring of the pipeline status.

[0014] In one embodiment, the water storage constraint satisfies: ; is the number of water use points, For water storage point To the water point The water supply, For water storage point The water storage capacity; the water consumption constraint satisfies: ; is the number of water storage points, For water storage point To the water point The water supply, For water point of water consumption.

[0015] The water storage capacity constraint can ensure that the amount of water provided by the water storage point does not exceed the water storage capacity of the water storage point; the water consumption constraint can ensure that the amount of water received by the water use point can meet the water consumption of the water use point.

[0016] In one embodiment, the scheduling matrix is OK A matrix of columns, is the number of water use points, is the number of water storage points; in the dispatch matrix, the response to the water storage point With water point There is a water supply path between OK The values ​​in the column are the water storage points To the water point The water supply, in response to the water storage point With water point There is no water supply path between OK The value of the column is 0.

[0017] In one embodiment, the method for calculating the Pearson correlation coefficient between the water quality parameter and the corrosion increment includes: collecting the historical sequence of water quality parameters at any observation point and the corrosion increment history sequence ; Pearson correlation coefficient between water quality parameters and corrosion increment for: , is the historical series of water quality parameters and the corrosion increment history sequence The covariance of is the historical series of water quality parameters The standard deviation of Corrosion increment history sequence The standard deviation of .

[0018] Pearson correlation coefficient It can reflect the influence of water quality parameters on the corrosion increment through the Pearson correlation coefficient. By multiplying it with the water quality parameters, the corrosion increment can be predicted, and then the path state of the water supply path after water supply scheduling is realized according to the scheduling matrix can be obtained.

[0019] In a second aspect of the present application, a scheduling system based on the water supply status of a water supply pump group is provided, comprising a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a scheduling method based on the water supply status of a water supply pump group according to the first aspect of the present application is implemented.

[0020] The technical solution of this application has the following beneficial technical effects:

[0021] Through the technical solution provided by the present application, the water supply network includes multiple water supply paths, and each water supply path is provided with multiple observation points; for any water supply path, the time series of the working parameters of the water supply pump group and the water quality parameters of each observation point are input into the corrosion prediction model to obtain the corrosion increment of the observation point, and further the sum of the corrosion increment and the initial corrosion is used as the real-time corrosion of each observation point, and the maximum value of the real-time corrosion is used as the path state of the water supply path, so as to realize real-time monitoring of the pipeline state in the water supply network; further, a scheduling matrix is ​​constructed and the target value is calculated, and the target value evaluates the effect of water supply scheduling from two aspects: whether the water quality parameters received from the water use point meet the water quality requirements, and the path state variance of each water supply path after water supply scheduling, the scheduling matrix is ​​continuously updated, and water supply scheduling is realized according to the scheduling matrix when the target value takes the minimum value, so as to avoid large differences in path states between water supply paths, which may lead to pipeline leakage. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present application will become easy to understand. In the accompanying drawings, several embodiments of the present application are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0023] Figure 1 is a flow chart of a scheduling method based on the water supply status of a water supply pump group according to an embodiment of the present application;

[0024] Figure 2 It is a structural block diagram of a scheduling system based on the water supply status of a water supply pump group according to an embodiment of the present application. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0026] It should be understood that when the terms "first", "second", etc. are used in the claims, specification and drawings of the present application, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the specification and claims of the present application indicate the presence of the described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or their collections.

[0027] According to the first aspect of the present application, the present application provides a scheduling method based on the water supply status of a water supply pump group, which is used to supply water resources from a water storage point to a water use point along a water supply path in a water supply network. The water supply network includes a water storage point, a water use point, and a water supply path connecting the water storage point and the water use point, wherein the water use point can be an enterprise, a resident, or a farm, and the water supply path is a water supply pipeline connecting the water storage point and the water use point. To ensure that water resources can be successfully supplied to the water use point, multiple water supply pump groups need to be deployed along the water supply pipeline; at the same time, in order to facilitate the monitoring of the degree of corrosion of the water supply pipeline, multiple observation points are deployed along the water supply path. Specifically, each water supply pump group on the water supply path can be used as an observation point.

[0028] Figure 1 FIG. 1 is a flow chart of a scheduling method based on the water supply status of a water supply pump group according to an embodiment of the present application. Figure 1 As shown, the scheduling method based on the water supply status of the water supply pump group includes steps S101 to S103, which are described in detail below.

[0029] S101, input the water supply status of the water supply pump group at the observation point in the water supply path into the corrosion prediction model, predict the corrosion increment of the observation point, take the sum of the corrosion increment and the initial corrosion degree as the real-time corrosion degree of each observation point, and take the maximum value of the real-time corrosion degree as the path state of the water supply path. The water supply status is a time series of water quality parameters and working parameters of the water supply pump group.

[0030] In one embodiment, for any observation point on the water supply path in the water supply network, the water quality parameters in the water supply pipeline are collected using sensors deployed at the observation point. Different water quality parameters can affect the corrosion degree of the pipeline by affecting the electrochemical corrosion process. The water quality parameters include pH value and hardness. Furthermore, the working parameters of the water supply pump group include head, speed and flow rate. The working parameters of the water supply pump group will affect the water pressure in the water supply pipeline, thereby affecting the impact force of water on the inner wall of the water supply pipeline, thereby affecting the corrosion degree of the pipeline. Therefore, the time series of water quality parameters and working parameters in a time period is used as the water supply state of the water supply pump group at the observation point, which is used to predict the corrosion increment of the pipeline corrosion degree at the observation point within the time period.

[0031] In other embodiments, the water quality parameter includes at least one of pH, hardness, conductivity, chloride ion concentration, and dissolved oxygen.

[0032] In one embodiment, the corrosion prediction model is a recurrent neural network, which extracts time series features from the time series of water quality parameters and working parameters to obtain water quality time series features and working time series features, and regresses the multidimensional data composed of the water quality time series features and the working time series features into corrosion increments. Further, the sum of the corrosion increment and the initial corrosion is taken as the real-time corrosion of each observation point, and the initial corrosion is the measured corrosion of the observation point at the starting time in the water supply state.

[0033] For example, workers regularly inspect and maintain the water supply network. The observation point A was inspected and the measured corrosion degree of the observation point A was obtained; at time When, the moment To time The time series of water quality parameters and working parameters of observation point A are input into the corrosion prediction model to obtain the time The corrosion increment of observation point A; at this time, the initial corrosion degree of observation point A is The measured corrosion degree will be The measured corrosion degree plus the corrosion degree increment can be obtained at the observation point A at the time Real-time corrosion rate.

[0034] In one embodiment, in order to ensure that the corrosion prediction model can output accurate corrosion increments, the corrosion prediction model needs to be trained. Specifically, the training method of the corrosion prediction model includes: taking the time series of water quality parameters and working parameters between any two moments as a set of training samples, and taking the increase in the measured corrosion degree at the two moments as the label value of the training sample; after the training sample is input into the corrosion prediction model, the mean square error function between the output result and the label value is used as the loss function to update the corrosion prediction model; iteratively updating the corrosion prediction model until the loss function is less than the set value, the training is completed. Among them, the set value is 0.01.

[0035] In this way, the real-time corrosion degree of each observation point in the water supply path is obtained, and the maximum value of the real-time corrosion degree of the observation point in the water supply path is used as the path state of the water supply path. The larger the path state, the greater the possibility of pipe network leakage in the path state. Through the same method, the path state of each water supply path can be obtained, and the state monitoring of the water supply path in the water supply network can be realized.

[0036] S102, constructing a scheduling matrix and calculating a target value, wherein the scheduling matrix includes the water supply of any water storage point and each water use point.

[0037] In one embodiment, the scheduling matrix is OK A matrix of columns, is the number of water use points, is the number of water storage points; With water point There is a water supply path between OK The values ​​in the column are the water storage points To the water point The water supply, in response to the water storage point With water point There is no water supply path between them. OK The value of the column is 0. Among them, the water supply is greater than or equal to 0.

[0038] In the scheduling matrix, in order to ensure that the amount of water provided by the water storage point does not exceed the water storage capacity of the water storage point, it is necessary to set a water storage capacity constraint, which satisfies: ; is the number of water use points, For water storage point To the water point The water supply, For water storage point of water storage capacity.

[0039] At the same time, in order to ensure that the amount of water received by the water point can meet the water demand of the water point, it is necessary to set a water consumption constraint, which satisfies: ; is the number of water storage points, For water storage point To the water point The water supply, For water point of water consumption.

[0040] In this way, the scheduling matrix can accurately reflect the water supply scheduling relationship between each water storage point and each water use point in the water supply network.

[0041] In one embodiment, a target value of the scheduling matrix is ​​calculated, and the target value is used to reflect the effect of implementing water supply scheduling according to the scheduling matrix.

[0042] On the one hand, due to the different types of water use at different water points, the water quality requirements of the water points are different; for example, when the water point is for drinking water for residents, the water quality requirements are higher, and when the water point is for industrial production water, the water quality requirements are lower than those for drinking water for residents. Therefore, the water quality parameters received by each water point are calculated based on the scheduling matrix, and then it is determined whether the received water quality parameters meet the water quality requirements of each water point. If the water quality parameters received by each water point meet the water quality requirements of each water point, the effect of water supply scheduling is better.

[0043] Specifically, the water quality parameters of different water storage points are known information. The water quality parameters received are , is the water consumption point in the dispatch matrix The sum of the water supply received from each water storage point, For water storage point To the water point The water supply, For water storage point The water quality parameters of the water points in the historical time period Average water quality parameters As a water point Water quality requirements, calculate water use points The absolute value of the difference between the received water quality parameters and the water quality requirements is used to obtain the water use point water quality deviation to determine the water use point Whether the received water quality parameters meet the water quality requirements. Water quality deviation at each water point as part of the target value.

[0044] On the other hand, due to the differences in the path states of different water supply paths, during water supply scheduling, the water quality parameters in the water supply path will affect the corrosion degree of the pipeline, and then affect the path state; in order to prevent further corrosion of the water supply path with poor path state, it is necessary to ensure that after the water supply scheduling is implemented according to the scheduling matrix, the variance of the path state between all water supply paths is small.

[0045] Specifically, for the water supply path , which is connected to a water storage point and a water consumption point, flowing through the water supply path The water quality parameters are equal to the water quality parameters of the connected water storage point. According to the Pearson correlation coefficient between the water quality parameters and the corrosion increment, it can be predicted that after the water supply scheduling is realized according to the scheduling matrix, the water supply path The path status is ,in, For water supply path Real-time corrosion degree, is the Pearson correlation coefficient between water quality parameters and corrosion increment, For water supply path The water quality parameters of the connected water storage points; the number of water supply paths in the water supply network is recorded as , then after the water supply scheduling is realized according to the scheduling matrix, the variance of the path states among all water supply paths is .

[0046] In summary, the target value of the scheduling matrix can be obtained. for:

[0047] ; is the number of water storage points, is the number of water use points, For water storage point water quality parameters, For water storage point To the water point The water supply, From each water storage point to the water use point The water supply, For water point Average water quality parameters, is the number of water supply paths, For water supply path Real-time corrosion degree, is the Pearson correlation coefficient between water quality parameters and corrosion increment, For water supply path Water quality parameters of the connected water storage point, To find the sign of the variance.

[0048] Among them, when the water quality parameters received by the water use point meet the water quality requirements and the path state variance of each water supply path after water supply scheduling is small, the target value The smaller the value of is, the better the effect of water supply scheduling is.

[0049] In one embodiment, the method for calculating the Pearson correlation coefficient between the water quality parameter and the corrosion increment includes: collecting the historical sequence of water quality parameters at any observation point and the corrosion increment history sequence , Pearson correlation coefficient between water quality parameters and corrosion increment for: , is the historical series of water quality parameters and the corrosion increment history sequence The covariance of is the historical series of water quality parameters The standard deviation of Corrosion increment history sequence The standard deviation of .

[0050] It can be understood that when the water quality parameters include pH value and hardness, the Pearson correlation coefficient between the water quality parameters and the corrosion increment is It also includes two values, the Pearson correlation coefficient It can reflect the influence of pH value and hardness on the corrosion increment through the Pearson correlation coefficient. Multiplying with water quality parameters can predict the corrosion increment, and then obtain the water supply path after water supply scheduling is realized according to the scheduling matrix. The path status.

[0051] In this way, the target value of the scheduling matrix is ​​calculated from two aspects: the water quality parameters received at the water use point meet the water quality requirements, and the path state variance of each water supply path after water supply scheduling. The scheduling effect of the scheduling matrix is ​​evaluated to avoid large differences in path states between water supply paths, which may lead to pipeline leakage.

[0052] S103, updating the scheduling matrix under the constraints of water storage capacity and water consumption, and realizing water supply scheduling according to the scheduling matrix when the target value takes the minimum value.

[0053] In one embodiment, under the constraints of water storage capacity and water consumption, an optimization algorithm is used to continuously update the scheduling matrix, obtain the scheduling matrix corresponding to when the target value takes the minimum value, and implement water supply scheduling based on the scheduling matrix when the target value takes the minimum value, so as to ensure the effect of water supply scheduling and avoid large differences in path states between water supply paths, thereby preventing pipe network leakage.

[0054] In another embodiment, during the water supply scheduling process, the water consumption of the water use points will change. At this time, it is necessary to adjust the water supply between any water storage point and each water use point to meet the water resource demand of the water use point. Therefore, before constructing the scheduling matrix, the scheduling method also includes: monitoring the water consumption of each water use point, responding to the change in the water consumption of any water use point, and constructing the scheduling matrix based on the actual water supply of any water storage point and each water use point. Otherwise, it is not necessary to adjust the water supply between any water storage point and each water use point.

[0055] The above introduces the technical principle and implementation details of the scheduling method based on the water supply status of the water supply pump group of the present application through specific embodiments. Through the technical solution provided by the present application, the water supply network includes multiple water supply paths, and each water supply path is provided with multiple observation points; for any water supply path, the time series of the working parameters and water quality parameters of the water supply pump group at each observation point are input into the corrosion prediction model to obtain the corrosion increment of the observation point, and further the sum of the corrosion increment and the initial corrosion is used as the real-time corrosion of each observation point, and the maximum value of the real-time corrosion is used as the path state of the water supply path, so as to realize the real-time monitoring of the pipeline state in the water supply network; further, the scheduling matrix is ​​constructed and the target value is calculated. The target value evaluates the effect of water supply scheduling from two aspects: whether the water quality parameters received from the water use point meet the water quality requirements, and the path state variance of each water supply path after water supply scheduling, and continuously updates the scheduling matrix, and realizes water supply scheduling according to the scheduling matrix when the target value takes the minimum value, so as to avoid the large difference in path state between water supply paths, which leads to leakage in the pipeline network.

[0056] According to the second aspect of the present application, the present application also provides a scheduling system based on the water supply status of a water supply pump group. Figure 2is a structural block diagram of a scheduling system based on the water supply status of a water supply pump group according to an embodiment of the present application. Figure 2 As shown, the system 50 includes a processor and a memory, the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the scheduling method based on the water supply status of the water supply pump group according to the first aspect of the present application is implemented. The system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, whose settings and functions are known in the art, so they are not repeated here.

[0057] In the present application, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. For example, a computer-readable storage medium may be any suitable magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of a device or accessible or connectable to a device. Any application or module described in this application may be implemented using computer-readable / executable instructions that may be stored or otherwise maintained by such a computer-readable medium.

[0058] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0059] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be construed as limiting the scope of the patent application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent application shall be subject to the attached claims.

Claims

1. A scheduling method based on the water supply status of a water supply pump group, characterized in that: The scheduling method comprises: The water supply status of the water supply pump group at the observation point in the water supply path is input into the corrosion prediction model, the corrosion increment of the observation point is predicted, the sum of the corrosion increment and the initial corrosion degree is taken as the real-time corrosion degree of each observation point, and the maximum value of the real-time corrosion degree is taken as the path status of the water supply path, and the water supply status is the time series of water quality parameters and working parameters of the water supply pump group; Construct a dispatch matrix and calculate the target value. The dispatch matrix includes the water supply of any water storage point and each water use point. The target value for: ; is the number of water storage points, is the number of water use points, For water storage point water quality parameters, For water storage point To the water point The water supply, From each water storage point to the water use point The water supply, For water point Average water quality parameters, is the number of water supply paths, For water supply path Real-time corrosion degree, is the Pearson correlation coefficient between water quality parameters and corrosion increment, For water supply path Water quality parameters of the connected water storage point, To find the sign of variance; Update the dispatch matrix under the constraints of water storage and water consumption, and realize water supply dispatch according to the dispatch matrix when the target value takes the minimum value; The corrosion prediction model is a recurrent neural network; the corrosion prediction model extracts time series features of water quality parameters and working parameters to obtain water quality time series features and working time series features, and regresses multidimensional data composed of water quality time series features and working time series features into corrosion degree increments.

2. The scheduling method based on the water supply status of the water supply pump group according to claim 1 is characterized in that: The water quality parameter includes at least one of pH value, hardness, conductivity, chloride ion concentration and dissolved oxygen.

3. The scheduling method based on the water supply status of the water supply pump group according to claim 1 is characterized in that: The training methods for the corrosion prediction model include: The time series of water quality parameters and working parameters between any two moments are taken as a group of training samples, and the increase of the measured corrosion degree at the two moments is taken as the label value of the training sample; After the training samples are input into the corrosion prediction model, the mean square error function between the output result and the label value is used as the loss function to update the corrosion prediction model; The corrosion prediction model is updated iteratively until the loss function is less than the set value, and the training is completed.

4. The scheduling method based on the water supply status of the water supply pump group according to claim 1 is characterized in that: The water storage constraint satisfies: ; is the number of water use points, For water storage point To the water point The water supply, For water storage point water storage capacity; The water consumption constraint satisfies: ; is the number of water storage points, For water storage point To the water point The water supply, For water point of water consumption.

5. The scheduling method based on the water supply status of the water supply pump group according to claim 1 is characterized in that: The scheduling matrix is OK A matrix of columns, is the number of water use points, is the number of water storage points; In the dispatch matrix, the response to the water storage point With water point There is a water supply path between OK The values ​​in the column are the water storage points To the water point The water supply, in response to the water storage point With water point There is no water supply path between OK The value of the column is 0.

6. The scheduling method based on the water supply status of the water supply pump group according to claim 1 is characterized in that: The calculation method of the Pearson correlation coefficient between water quality parameters and corrosion increment includes: Collect historical series of water quality parameters at any observation point and the corrosion increment history sequence ; Pearson correlation coefficient between water quality parameters and corrosion increment for: , is the historical series of water quality parameters and the corrosion increment history sequence The covariance of is the historical series of water quality parameters The standard deviation of Corrosion increment history sequence The standard deviation of .

7. The scheduling method based on the water supply status of a water supply pump group according to any one of claims 1 to 6, characterized in that: Before constructing the scheduling matrix, the scheduling method further includes: Monitor the water consumption of each water point, respond to changes in water consumption at any water point, and build a scheduling matrix based on the actual water supply of any water storage point and each water point.

8. A dispatching system based on the water supply status of a water supply pump group, characterized in that: The method comprises a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a scheduling method based on the water supply status of a water supply pump group according to any one of claims 1 to 7 is implemented.

Images