Water supply network measuring point pressure prediction method, device, equipment and medium

By using the pipeline network state prediction model and decision flow chart, combined with the current state and influencing factors, we predict the pressure of the water supply pipeline at the next moment, solving the problem of artificial experience dependence in the existing technology, and realizing the pressure prediction of the water supply pipeline network efficient and universal.

CN117333054BActive Publication Date: 2024-11-08NANQI XIANCE (NANJING) HIGH TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202311270701.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-09-27
Publication Date
2024-11-08
Estimated Expiration
2043-09-27

AI Technical Summary

Technical Problem

The pressure prediction of existing water supply pipelines mainly relies on manual experience, lacks universality and wide applicability, making it difficult to achieve accurate and efficient pressure prediction.

Method used

By obtaining the current state data of the water supply pipeline network and parameters affecting the measurement point pressure, input it to the pre-trained pipeline network state prediction model to predict the measurement point pressure at the next moment, use the decision flow diagram and calculation diagram to build the initial model, and use the Sample data and expected data adjust network parameters and optimize prediction models.

Benefits of technology

It realizes convenient, universal and widely applicable forecasts of water supply pipeline pressure, and improves the accuracy and efficiency of pressure prediction.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117333054B_ABST
    Figure CN117333054B_ABST
Patent Text Reader

Abstract

The embodiment of the present invention discloses a method, device, equipment and medium for predicting the pressure of a measuring point in a water supply network. The method comprises: obtaining the current network status data of the water supply network and the parameters affecting the pressure of the measuring point in the water supply network, wherein the current network status data comprises the current measuring point pressure of the water supply network to be tested; inputting the current network status data and the parameters affecting the pressure of the measuring point in the water supply network into a pre-trained network status prediction model to obtain the next network status data of the water supply network to be tested; and determining the next measuring point pressure of the water supply network to be tested based on the next network status data. The technical solution of the embodiment of the present invention realizes a more convenient prediction of the pressure of the water supply network, and improves the universality and wide applicability of the prediction of the pressure of the measuring point in the water supply network.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of data processing technology, and in particular to a method, device, equipment and medium for predicting pressure at a measuring point in a water supply network. Background Art

[0002] Pipeline network pressure is an important indicator that restricts the effective water supply of the tap water system. It is also a core factor that affects the health, maintenance and service life of the pipeline network. At the same time, it is also an important cost item for water companies. Therefore, building a pipeline network pressure simulation system and conducting forward-looking predictions and evaluations of various control schemes will strongly support the digitalization, intelligence and conservation of water companies. Therefore, pipeline network pressure prediction has become crucial. At present, pipeline network pressure prediction is usually carried out manually, which requires reliance on relevant experience and is not universal and widely applicable. Summary of the invention

[0003] The present invention provides a method, device, equipment and medium for predicting the pressure of a water supply network measuring point, so as to realize a more convenient prediction of the pressure of a water supply network, thereby improving the universality and wide applicability of the prediction of the pressure of a water supply network measuring point.

[0004] According to one aspect of the present invention, a method for predicting pressure at a measuring point in a water supply network is provided, the method comprising:

[0005] Acquire current network status data of the water supply network and parameters affecting the pressure of the measuring points of the water supply network, wherein the current network status data includes the current measuring point pressure of the water supply network to be measured;

[0006] Inputting the current pipe network state data and the parameters affecting the pressure of the water supply pipe network measuring point into a pre-trained pipe network state prediction model to obtain the next pipe network state data of the water supply pipe network to be tested;

[0007] Based on the next pipe network status data, the pressure of the next measuring point of the water supply pipe network to be measured is determined.

[0008] Optionally, the method also includes: obtaining multiple sample data and expected data corresponding to each of the sample data, wherein the sample data include the network status data of the water supply network at a certain historical moment and parameters affecting the pressure of the water supply network measuring points, and the expected data is the network status data of the water supply network at the next moment after the certain historical moment; inputting each of the sample data into a pre-constructed initial network status prediction model to obtain the actual output result of the initial network status prediction model for each of the sample data; adjusting the network parameters of the initial network status prediction model according to the expected data and actual output results of each of the sample data to obtain the trained network status prediction model.

[0009] Optionally, the adjusting the network parameters of the initial pipe network state prediction model according to the expected data and actual output results of each of the sample data includes: determining a first data distribution of the initial pipe network state prediction model for the actual output results of each of the sample data; determining a second data distribution of the initial pipe network state prediction model for the expected data of each of the sample data; and adjusting the network parameters of the initial pipe network state prediction model based on the first data distribution and the second data distribution.

[0010] Optionally, adjusting the network parameters of the initial pipe network state prediction model according to the expected data and actual output results of each sample data includes: for each sample data, adjusting the network parameters of the initial pipe network state prediction model according to the expected data and actual output results of the sample data.

[0011] Optionally, the method also includes: obtaining a pre-built pipe network water supply decision flow diagram and a pre-built pipe network water supply calculation diagram; and constructing the initial pipe network state prediction model based on the pre-built pipe network water supply decision flow diagram and the pre-built pipe network water supply calculation diagram.

[0012] Optionally, the method further includes: determining the association relationship between nodes in the pipe network water supply decision flow diagram, and constructing a pipe network water supply calculation diagram based on the association relationship.

[0013] Optionally, the pre-constructed pipe network water supply decision flow graph includes at least one environment state node and at least one decision agent node, and the environment state node includes a current environment state sub-node, an environment state transfer sub-node and a next environment state sub-node.

[0014] According to another aspect of the present invention, a device for predicting pressure at a measuring point in a water supply network is provided. The device comprises:

[0015] A current pipe network status acquisition module, used to acquire the current pipe network status data of the water supply pipe network and the parameters affecting the pressure of the measuring point of the water supply pipe network, wherein the current pipe network status data includes the current measuring point pressure of the water supply pipe network to be measured;

[0016] A next pipe network state obtaining module is used to input the current pipe network state data and the parameters affecting the pressure of the water supply pipe network measuring point into a pre-trained pipe network state prediction model to obtain the next pipe network state data of the water supply pipe network to be tested;

[0017] The next pipe network pressure determination module is used to determine the pressure of the next measuring point of the water supply pipe network to be tested based on the next pipe network status data.

[0018] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0019] at least one processor; and

[0020] a memory communicatively connected to the at least one processor; wherein,

[0021] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the water supply network measuring point pressure prediction method described in any embodiment of the present invention.

[0022] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for predicting pressure at a measuring point in a water supply network as described in any embodiment of the present invention when executed.

[0023] The technical solution of the embodiment of the present invention obtains the current network status data of the water supply network and the parameters affecting the pressure of the water supply network measuring points, wherein the current network status data includes the current measuring point pressure of the water supply network to be tested; inputs the current network status data and the parameters affecting the pressure of the water supply network measuring points into a pre-trained network status prediction model to obtain the next network status data of the water supply network to be tested; and determines the next measuring point pressure of the water supply network to be tested based on the next network status data. The technical solution of the embodiment of the present invention realizes a more convenient prediction of the pressure of the water supply network, and improves the universality and wide applicability of the prediction of the pressure of the water supply network measuring points.

[0024] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0026] Figure 1 A schematic diagram of a flow chart of a method for predicting pressure at a measuring point in a water supply network provided in the first embodiment of the present invention;

[0027] Figure 2 A pipe network water supply decision flow chart of a water supply pipe network measuring point pressure prediction method provided in the first embodiment of the present invention;

[0028] Figure 3 A schematic diagram of the structure of a water supply network measuring point pressure prediction device provided in the second embodiment of the present invention;

[0029] Figure 4 A schematic diagram of the structure of an electronic device provided in Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0030] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0031] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0032] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and relevant provisions.

[0033] Embodiment 1

[0034] Figure 1 A flow chart of a method for predicting pressure at a measuring point in a water supply network provided in Example 1 of the present invention. This embodiment is applicable to situations where pressure of a water supply network is predicted. The method can be executed by a pressure prediction device for predicting pressure at a measuring point in a water supply network. The pressure prediction device for predicting pressure at a measuring point in a water supply network can be implemented in the form of hardware and / or software. The pressure prediction device for predicting pressure at a measuring point in a water supply network can be configured in an electronic device such as a computer or a server.

[0035] like Figure 1 As shown, the method of this embodiment includes:

[0036] S110. Acquire current network status data of the water supply network and parameters affecting the pressure of measuring points of the water supply network, wherein the current network status data includes the current pressure of the measuring points of the water supply network to be measured.

[0037] Among them, the current network status data can be understood as the status data of the water supply network at the current moment. The water supply network to be tested can be understood as the water supply network that needs to perform pressure prediction. The current network status data may include the current measuring point pressure. The current measuring point pressure can be understood as the pressure value of the water supply network measuring point at the current moment. The parameters affecting the pressure of the water supply network measuring point can be understood as data that have an impact on the pressure of the water supply network measuring point. Optionally, the parameters affecting the pressure of the water supply network measuring point may include but are not limited to user water use habit data, network structure, material and electromechanical system performance. In an embodiment of the present invention, the parameters affecting the pressure of the water supply network measuring point can be set according to actual conditions and are not specifically limited here.

[0038] In the embodiment of the present invention, the current measuring point pressure of the water supply network to be tested is obtained by collecting the measuring point pressure of the water supply network to be tested at the current moment based on a collecting device (such as a pressure sensor), that is, obtaining the current measuring point pressure.

[0039] S120: Input the current pipe network state data and the parameters affecting the pressure of the water supply pipe network measuring point into a pre-trained pipe network state prediction model to obtain the next pipe network state data of the water supply pipe network to be tested.

[0040] The next pipe network state data can be understood as the state data of the water supply pipe network to be tested at the next moment after the current moment. The pipe network state prediction module can be understood as being used to obtain the next pipe network state data of the water supply pipe network to be tested based on the current pipe network state data and the parameters affecting the pressure of the water supply pipe network measuring point.

[0041] Specifically, after obtaining the current network status data and the parameters that affect the pressure of the water supply network measuring points, the current network status data and the parameters that affect the pressure of the water supply network measuring points can be input into the pre-trained network status prediction model to obtain the output result of the network status prediction model, that is, the next network status data of the water supply network to be tested.

[0042] In an embodiment of the present invention, the method further includes: obtaining a plurality of sample data and expected data corresponding to each of the sample data. The sample data may include the network status data of the water supply network at a certain historical moment and the parameters affecting the pressure of the water supply network measuring point. The expected data may be the network status data of the water supply network at the next moment of the certain historical moment. After obtaining the sample data and the expected data corresponding to the sample data, each of the sample data may be input into a pre-constructed initial network status prediction model to obtain the actual output result of the initial network status prediction model for each of the sample data. Then, the network parameters of the initial network status prediction model may be adjusted according to the expected data and the actual output result of each of the sample data to obtain the trained network status prediction model. The initial network status prediction model may be understood as a pre-constructed initial network model for testing the network pressure. In an embodiment of the present invention, the training of the initial network status prediction model may adopt a regression training method.

[0043] On the basis of the above embodiment, the method further includes: obtaining a training set, wherein the training set includes a large amount of historical state trajectory data. In an embodiment of the present invention, each piece of historical state trajectory data may be a sequence consisting of a series of states in a continuous period including a start state and an end state. In an embodiment of the present invention, a pipe network state prediction model constructed based on a decision flow diagram, i.e., a pipe network environment model, may include a water use prediction module, an intelligent decision module, and a state transfer module.

[0044] In an embodiment of the present invention, the training model can be specifically that for each historical state trajectory data, training can be started from the starting state of the trajectory data. That is, the pipeline state at the starting moment in the trajectory can be input into the pipeline environment model to obtain the pipeline network prediction state at the next moment of the starting moment in the trajectory. Then, the pipeline network environment model parameters can be optimized based on the pipeline network prediction state at the next moment of the starting moment in the trajectory and the historical real pipeline network state; based on this, the pipeline network prediction state at the next moment of the starting moment in the trajectory can be further input into the pipeline environment model to obtain the pipeline network prediction state at the next moment of the next moment of the starting moment in the trajectory. Thus, the pipeline network prediction state at the next moment of the next moment of the starting moment in the trajectory and the historical real pipeline network state can be used to optimize the pipeline network environment model parameters. That is, the predicted pipeline network prediction state is used as input each time to continue to predict the subsequent state. The prediction is terminated by continuous deduction until the terminal state is obtained. For a trajectory with a length of N, N-1 predictions will be made from the starting state to reach the terminal state. This enables the model to be trained once using all the trajectories in the training set, which is called one epoch.

[0045] It is understandable that in practical applications, a training process usually requires multiple iterations to learn more information from the data and make the model converge to a better state. Therefore, continuous training can be performed until the loss of the model no longer decreases to obtain a trained pipeline environment model.

[0046] After the model training is completed, the status data at the current moment can be input into the pipe network environment model to obtain the status data at the next moment. In this way, the status data after a period of time can be deduced.

[0047] In an embodiment of the present invention, the method also includes: obtaining a pre-constructed pipe network water supply decision flow diagram and a pre-constructed pipe network water supply calculation diagram; and constructing the initial pipe network state prediction model based on the pre-constructed pipe network water supply decision flow diagram and the pre-constructed pipe network water supply calculation diagram.

[0048] Among them, the pipe network water supply decision flow diagram can be a decision diagram constructed based on the pipe network water supply business characteristics. The pipe network water supply decision flow diagram can be used to characterize the decision relationship between different business parameter characteristics at each time point. In an embodiment of the present invention, the input and output of the data flow in the pipe network water supply decision flow diagram cannot form a loop, that is, the structure of the pipe network water supply decision flow diagram conforms to the structure of a directed acyclic graph. The pipe network water supply decision flow diagram includes multiple business nodes. In an embodiment of the present invention, each business node in the pipe network water supply decision flow diagram can represent the decision process used to calculate the parameters of the node, and the connection between each business node represents the data flow direction.

[0049] In an embodiment of the present invention, the nodes in the pipe network water supply decision flow diagram may include: weather and holiday nodes, current water consumption nodes, current operating factor nodes, current measuring point pressure nodes, non-operating factor nodes, next water consumption nodes, next operating factor nodes, next measuring point pressure nodes, water consumption prediction nodes, intelligent decision nodes and state transfer nodes.

[0050] Among them, the weather and holiday nodes may include date information, the maximum temperature value of the day corresponding to the date information, the minimum temperature value of the day corresponding to the date information, and the precipitation of the day corresponding to the date information, and the date information is at least one data belonging to holidays. The current water consumption node can be the total water consumption of the pipeline network at the current moment and the regional water consumption and other data related to water consumption; or, it can be the total water consumption of the pipeline network in the current period and the regional water consumption and other data related to water consumption. Among them, the current period can be the period between the current moment and the moment of a preset time before the current moment. Among them, the preset time can be set according to actual needs, and is not specifically limited here, for example, 1 day, 7 days or 30 days.

[0051] Among them, the current operation factor node may include data that immediately causes changes in the pipeline network due to the operation of the pipeline network dispatcher at the current moment or in the current period, such as the outlet pressure of the pump station in the pipeline network, the outlet flow of the pump station, the activation of the pipeline network valve, etc. The current measuring point pressure node may include the pressure data of each measuring point in the pipeline network at the current moment or in the current period. Non-operational factors may include data including the structure and material of the pipeline network. The next water consumption node may include data related to water consumption such as the total water consumption of the pipeline network at the next moment and the regional water consumption. The next operation factor node may include data that immediately causes changes in the pipeline network due to the operation of the pipeline network dispatcher at the next moment, such as the outlet pressure of the pump station in the pipeline network, the outlet flow of the pump station, the activation of the pipeline network valve, etc. The next measuring point pressure node may include the pressure data of each measuring point in the pipeline network at the next moment.

[0052] Among them, the water consumption prediction node can be used to predict the water consumption of the pipeline network at the next moment according to the data included in the current water consumption node and the data included in the weather and holiday nodes, that is, to predict the data included in the next water consumption node. Among them, the data included in the current water consumption node can be the water consumption data at the current moment; or, it can be the water consumption data in the current time period. The intelligent decision node can be used to simulate the state change of the operation factor node directly caused by the operation of the pipeline network dispatcher. Specifically, the data in the next operation factor node can be inferred based on the data included in the current water consumption node and the data included in the current measuring point pressure node, the data included in the current operation factor node, and the data included in the next water consumption node. The state transfer node can be used to predict the data included in the next measuring point pressure node based on the data included in the current water consumption node and the data included in the current measuring point pressure node, the data included in the current operation factor node, the data included in the non-operation factor node, the data included in the next water consumption node, and the data included in the next operation factor node, that is, to predict the measuring point pressure information of the pipeline network at the next moment.

[0053] It should be noted that, in the embodiment of the present invention, the water consumption prediction node and the intelligent decision-making node can be configured according to actual needs. In the case where the water consumption prediction node and the intelligent decision-making node are not configured, the data included in the corresponding node can be obtained by other means (such as manual detection or expert prediction, etc.). In other words, if there is accurate future water consumption information, that is, the data included in the next water consumption node, the water consumption prediction module can be disabled, and accurate future water consumption data can be used; if there is accurate future operation factor information (such as known pump room and valve scheduling instructions for a period of time in the future), that is, the data included in the next operation factor node, the intelligent decision-making module can be disabled, and accurate future operation information can be used.

[0054] The pipe network water supply calculation diagram may include the association relationship between the nodes in the pipe network water supply decision flow diagram. The pipe network water supply calculation diagram may be obtained by determining the association relationship between the nodes in the pipe network water supply decision flow diagram, and constructing the pipe network water supply calculation diagram based on the association relationship. Specifically, based on the business characteristics bound to each business node in the pipe network water supply decision flow diagram and the data flow information between the business nodes, the pipe network water supply calculation diagram is constructed (see Figure 2 In an embodiment of the present invention, based on the business features bound to each business node in the pipe network water supply decision flow diagram and the data flow information between the business nodes, a pipe network water supply calculation diagram is constructed, which may include: based on the business features bound to each business node in the target decision flow diagram and the data flow information between the business nodes, the target decision flow diagram can be converted into a calculation diagram that can be directly used in environmental modeling, that is, a pipe network water supply calculation diagram.

[0055] As an optional embodiment of the present invention, the adjusting the network parameters of the initial pipe network state prediction model according to the expected data and the actual output results of each sample data may include: for each sample data, adjusting the network parameters of the initial pipe network state prediction model according to the expected data and the actual output results of the sample data.

[0056] As an optional embodiment of the present invention, the adjusting the network parameters of the initial pipe network state prediction model according to the expected data and the actual output results of each of the sample data may include: determining a first data distribution of the initial pipe network state prediction model for the actual output results of each of the sample data; determining a second data distribution of the initial pipe network state prediction model for the expected data of each of the sample data; after obtaining the first data distribution and the second data distribution, the network parameters of the initial pipe network state prediction model may be adjusted based on the first data distribution and the second data distribution.

[0057] The first data distribution can be understood as the data distribution of the actual output results of the initial pipe network state prediction model for each of the sample data. The second data distribution can be understood as the data distribution of the expected data of the initial pipe network state prediction model for each of the sample data.

[0058] In an embodiment of the present invention, based on the first data distribution and the second data distribution, the network parameters of the initial pipe network status prediction model are adjusted. The network parameters of the model can be adjusted based on the overall data prediction situation to enhance the prediction capability of the pipe network status prediction model.

[0059] S130: Determine the pressure of the next measuring point of the water supply network to be measured based on the next network status data.

[0060] The next measuring point pressure can be understood as the pressure value of the water supply network measuring point to be measured at the next moment after the current moment. In the embodiment of the present invention, after obtaining the next pipe network status data, the next pipe network status data can be analyzed and processed to obtain the next measuring point pressure of the water supply network to be measured.

[0061] The technical solution of the embodiment of the present invention obtains the current network status data of the water supply network and the parameters affecting the pressure of the water supply network measuring points, wherein the current network status data includes the current measuring point pressure of the water supply network to be tested; the current network status data and the parameters affecting the pressure of the water supply network measuring points are input into a pre-trained network status prediction model to obtain the next network status data of the water supply network to be tested; based on the next network status data, the next measuring point pressure of the water supply network to be tested is determined. The technical solution of the embodiment of the present invention realizes a more convenient prediction of the pressure of the water supply network, and improves the universality and wide applicability of the prediction of the pressure of the water supply network measuring points.

[0062] Embodiment 2

[0063] Figure 3 This is a schematic diagram of the structure of a water supply network measuring point pressure prediction device provided in the second embodiment of the present invention. Figure 3 As shown, the device includes: a current pipe network state acquisition module 210, a next pipe network state acquisition module 220 and a next pipe network pressure prediction module 230.

[0064] Among them, the current network state acquisition module 210 is used to obtain the current network state data of the water supply network and the parameters affecting the pressure of the water supply network measuring points, wherein the current network state data includes the current measuring point pressure of the water supply network to be tested; the next network state acquisition module 220 is used to input the current network state data and the parameters affecting the pressure of the water supply network measuring points into the pre-trained network state prediction model to obtain the next network state data of the water supply network to be tested; the next network pressure determination module 230 is used to determine the next measuring point pressure of the water supply network to be tested based on the next network state data.

[0065] The technical solution of the embodiment of the present invention obtains the current network status data of the water supply network and the parameters affecting the pressure of the water supply network measuring points, wherein the current network status data includes the current measuring point pressure of the water supply network to be tested; inputs the current network status data and the parameters affecting the pressure of the water supply network measuring points into a pre-trained network status prediction model to obtain the next network status data of the water supply network to be tested; and determines the next measuring point pressure of the water supply network to be tested based on the next network status data. The technical solution of the embodiment of the present invention realizes a more convenient prediction of the pressure of the water supply network, and improves the universality and wide applicability of the prediction of the pressure of the water supply network measuring points.

[0066] Optionally, the device further comprises a model training module; wherein the model training module is used to:

[0067] Acquire multiple sample data and expected data corresponding to each of the sample data, wherein the sample data includes the network status data of the water supply network at a certain historical moment and parameters affecting the pressure of the water supply network measuring points, and the expected data is the network status data of the water supply network at the next moment after the certain historical moment;

[0068] Input each of the sample data into a pre-built initial pipe network state prediction model to obtain an actual output result of the initial pipe network state prediction model for each of the sample data;

[0069] The network parameters of the initial pipe network state prediction model are adjusted according to the expected data and the actual output results of each of the sample data to obtain the trained pipe network state prediction model.

[0070] Optionally, the model training module includes a first parameter adjustment unit, wherein the first parameter adjustment unit is used to:

[0071] Determine a first data distribution of an actual output result of the initial pipe network state prediction model for each of the sample data;

[0072] Determine a second data distribution of expected data of the initial pipe network state prediction model for each of the sample data;

[0073] Based on the first data distribution and the second data distribution, network parameters of the initial pipe network state prediction model are adjusted.

[0074] Optionally, the model training module includes a second parameter adjustment unit, wherein the second parameter adjustment unit is used to:

[0075] For each sample data, the network parameters of the initial pipe network state prediction model are adjusted according to the expected data and the actual output result of the sample data.

[0076] Optionally, the device further comprises an initial model building module; the initial model building module is used to:

[0077] Obtain a pre-built pipe network water supply decision flow diagram and a pre-built pipe network water supply calculation diagram;

[0078] Based on the pre-constructed pipe network water supply decision flow diagram and the pre-constructed pipe network water supply calculation diagram, the initial pipe network state prediction model is constructed.

[0079] Optionally, the device further comprises a pipe network water supply calculation diagram construction module, the pipe network water supply calculation diagram construction module being used to:

[0080] Determine the association relationship between the nodes in the pipe network water supply decision flow diagram, and construct the pipe network water supply calculation diagram based on the association relationship.

[0081] Optionally, the pre-constructed pipe network water supply decision flow graph includes at least one environment state node and at least one decision agent node, and the environment state node includes a current environment state sub-node, an environment state transfer sub-node and a next environment state sub-node.

[0082] The water supply network measuring point pressure prediction device provided in the embodiment of the present invention can execute the water supply network measuring point pressure prediction method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0083] It is worth noting that the various units and modules included in the above-mentioned water supply network measuring point pressure prediction device are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific name of each functional unit is only for the convenience of distinguishing each other, and is not used to limit the protection scope of the embodiment of the present invention.

[0084] Embodiment 3

[0085] Figure 4 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0086] like Figure 4As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0087] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0088] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The processor 11 executes the various methods and processes described above, such as a water supply network measuring point pressure prediction method.

[0089] In some embodiments, the water supply network measuring point pressure prediction method can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the water supply network measuring point pressure prediction method described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to execute the water supply network measuring point pressure prediction method in any other appropriate manner (for example, by means of firmware).

[0090] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0091] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0092] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0093] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0094] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0095] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0096] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0097] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for predicting pressure at a measuring point in a water supply network, characterized in that: include: Acquire the current network status data of the water supply network and the parameters affecting the pressure of the measuring point of the water supply network, wherein the current network status data includes the current measuring point pressure of the water supply network to be measured, and the parameters affecting the pressure of the measuring point of the water supply network refer to the data that have an impact on the pressure of the measuring point of the water supply network; The current pipe network state data and the parameters affecting the pressure of the water supply pipe network measuring point are input into a pre-trained pipe network state prediction model to obtain the next pipe network state data of the water supply pipe network to be tested, wherein the pipe network state prediction model is obtained by adjusting and training the network parameters of the initial pipe network state prediction model based on multiple sample data and expected data corresponding to each of the sample data, and the initial pipe network state prediction model includes a pre-constructed pipe network water supply decision flow diagram and a pre-constructed pipe network water supply calculation diagram, and the nodes in the pre-constructed pipe network water supply decision flow diagram include weather and holiday nodes, current water consumption nodes, current operating factor nodes, current measuring point pressure nodes, non-operating factor nodes, next water consumption nodes, next operating factor nodes, next measuring point pressure nodes, water consumption prediction nodes, intelligent decision nodes, and state transfer nodes; Determining the pressure of the next measuring point of the water supply network to be tested based on the next pipe network state data; Wherein, the method further comprises: Obtain a pre-built pipe network water supply decision flow diagram and a pre-built pipe network water supply calculation diagram, wherein the pre-built pipe network water supply decision flow diagram includes at least one environment state node and at least one decision agent node, the environment state node includes a current environment state sub-node, an environment state transfer sub-node and a next environment state sub-node, the pipe network water supply decision flow diagram is a decision diagram constructed based on the pipe network water supply business characteristics, and the pipe network water supply decision flow diagram is used to characterize the decision relationship between different business parameter characteristics at each time point; Based on the pre-constructed pipe network water supply decision flow diagram and the pre-constructed pipe network water supply calculation diagram, construct the initial pipe network state prediction model; Wherein, the method further comprises: Determine the association relationship between the nodes in the pipe network water supply decision flow diagram, and construct the pipe network water supply calculation diagram based on the association relationship.

2. The method according to claim 1, characterized in that The method further comprises: Acquire multiple sample data and expected data corresponding to each of the sample data, wherein the sample data includes the network status data of the water supply network at a certain historical moment and parameters affecting the pressure of the water supply network measuring points, and the expected data is the network status data of the water supply network at the next moment after the certain historical moment; Input each of the sample data into a pre-built initial pipe network state prediction model to obtain an actual output result of the initial pipe network state prediction model for each of the sample data; The network parameters of the initial pipe network state prediction model are adjusted according to the expected data and the actual output results of each of the sample data to obtain the trained pipe network state prediction model.

3. The method according to claim 2, characterized in that The adjusting of the network parameters of the initial pipe network state prediction model according to the expected data and the actual output results of each sample data includes: Determine a first data distribution of an actual output result of the initial pipe network state prediction model for each of the sample data; Determine a second data distribution of expected data of the initial pipe network state prediction model for each of the sample data; Based on the first data distribution and the second data distribution, network parameters of the initial pipe network state prediction model are adjusted.

4. The method according to claim 2, characterized in that: The adjusting of the network parameters of the initial pipe network state prediction model according to the expected data and the actual output results of each sample data includes: For each sample data, the network parameters of the initial pipe network state prediction model are adjusted according to the expected data and the actual output result of the sample data.

5. A water supply network measuring point pressure prediction device, characterized in that: include: A current pipe network status acquisition module, used to acquire the current pipe network status data of the water supply pipe network and the parameters affecting the pressure of the water supply pipe network measuring point, wherein the current pipe network status data includes the current measuring point pressure of the water supply pipe network to be measured, and the parameters affecting the pressure of the water supply pipe network measuring point refer to the data that have an impact on the pressure of the water supply pipe network measuring point; A next pipe network state obtaining module is used to input the current pipe network state data and the parameters affecting the pressure of the water supply pipe network measuring point into a pre-trained pipe network state prediction model to obtain the next pipe network state data of the water supply pipe network to be tested, wherein the pipe network state prediction model is obtained by adjusting and training the network parameters of the initial pipe network state prediction model based on multiple sample data and expected data corresponding to each of the sample data, and the initial pipe network state prediction model includes a pre-constructed pipe network water supply decision flow diagram and a pre-constructed pipe network water supply calculation diagram, and the nodes in the pre-constructed pipe network water supply decision flow diagram include weather and holiday nodes, current water consumption nodes, current operating factor nodes, current measuring point pressure nodes, non-operating factor nodes, next water consumption nodes, next operating factor nodes, next measuring point pressure nodes, water consumption prediction nodes, intelligent decision nodes, and state transfer nodes; A next pipe network pressure determination module, used to determine the pressure of the next measuring point of the water supply pipe network to be tested based on the next pipe network state data; Initial model building modules for: Obtain a pre-built pipe network water supply decision flow diagram and a pre-built pipe network water supply calculation diagram, wherein the pre-built pipe network water supply decision flow diagram includes at least one environment state node and at least one decision agent node, the environment state node includes a current environment state sub-node, an environment state transfer sub-node and a next environment state sub-node, the pipe network water supply decision flow diagram is a decision diagram constructed based on the pipe network water supply business characteristics, and the pipe network water supply decision flow diagram is used to characterize the decision relationship between different business parameter characteristics at each time point; Based on the pre-constructed pipe network water supply decision flow diagram and the pre-constructed pipe network water supply calculation diagram, construct the initial pipe network state prediction model; The water supply calculation diagram construction module is used to: Determine the association relationship between the nodes in the pipe network water supply decision flow diagram, and construct the pipe network water supply calculation diagram based on the association relationship.

6. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the water supply network measuring point pressure prediction method described in any one of claims 1-4.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the water supply network measuring point pressure prediction method according to any one of claims 1 to 4 when executed.