Water supply pipeline leakage detection method, device, Internet of Things platform and medium

By recording the information and status data of the water supply pipeline network, using the pipeline leakage model to predict the leakage, combined with the Internet of Things platform, the accuracy and response speed of the water supply pipeline leakage detection in the existing technology is solved, and timely and accurate Leakage detection and positioning meet the needs of complex environments.

CN118623240BActive Publication Date: 2024-12-06E SURFING IOT CO LTD
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
CN202411088406.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-09
Publication Date
2024-12-06
Estimated Expiration
2044-08-09

AI Technical Summary

Technical Problem

The existing water supply pipeline leakage detection methods are low in accuracy and slow in response. They cannot detect early leakage in time, and the transformation cost is high, making it difficult to meet the complex and changing water supply environment and the growing leakage detection needs.

Method used

By recording the information and status data of each pipeline in the water supply pipeline network, using a time series database and pipeline leakage model for leakage prediction, combined with the IoT platform to achieve fast and accurate leakage detection, identify and locate leakage points.

Benefits of technology

It improves the timeliness and accuracy of leak detection in water supply pipelines, meets the complex and changeable water supply environment and the growing leak detection needs, and reduces water resource waste and maintenance pressure.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118623240B_ABST
    Figure CN118623240B_ABST
Patent Text Reader

Abstract

The present application relates to a method, device, Internet of Things platform and medium for detecting leakage in a water supply pipeline, wherein the method comprises: recording the water pipe information of each pipeline in the water supply network into a water pipe information table, and recording the water pipe information of the upstream and downstream pipelines connected to the pipeline into a water pipe association information table; collecting the status data of each pipeline in the water supply network, and storing the status data in a water pipe status table in a time series database; determining the prediction parameters of the current pipeline based on the water pipe information table, the water pipe association information table and the water pipe status table; performing leakage prediction processing based on the prediction parameters through a pipeline leakage model to obtain a leakage degree prediction value; recording the leakage degree prediction value and the prediction parameters in the prediction information table, and performing leakage prediction processing on the next pipeline in the water supply network through the pipeline leakage model until all pipeline predictions in the water supply network are completed to obtain a target prediction information table. The present application improves the timeliness and accuracy of water supply pipeline leakage detection.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of Internet of Things, and in particular to a method, device, Internet of Things platform and medium for detecting leakage in a water supply pipeline. Background Art

[0002] With the growth of global population and the acceleration of urbanization, the rational use and protection of water resources have become increasingly important. As an important part of urban infrastructure, the safe and efficient operation of water supply systems is crucial to protecting residents' lives and economic development. However, water supply pipeline leakage is a common problem, which not only leads to a large waste of water resources, but also may cause serious consequences such as ground subsidence and pipeline rupture, bringing huge economic losses and maintenance pressure to water supply companies.

[0003] Existing methods for detecting water supply pipeline leakage mainly include acoustic detection, ground subsidence monitoring, and zone metering. Acoustic detection relies on the noise generated by leak detection, but is limited by the propagation distance of noise signals and the interference of environmental noise, resulting in low accuracy in detecting water supply pipeline leakage. Although ground subsidence monitoring can detect larger leaks, it has a slow response speed and cannot detect early leaks in time. Zone metering may require large-scale transformation of existing water supply systems, and the adaptability of the system and the feasibility of the transformation need to be considered. Therefore, there is an urgent need for a water supply pipeline leakage detection method to improve the timeliness and accuracy of water supply pipeline leakage detection and meet the complex and changing water supply environment and the growing demand for leakage detection. Summary of the invention

[0004] The purpose of the embodiments of the present application is to propose a water supply pipeline leakage detection method, device, Internet of Things platform and medium to improve the timeliness and accuracy of water supply pipeline leakage detection.

[0005] In order to solve the above technical problems, the present application provides a water supply pipeline leakage detection method, comprising:

[0006] Record the water pipe information of each pipe in the water supply network into a water pipe information table, and record the water pipe information of the upstream pipe and the downstream pipe connected to each pipe into a water pipe association information table;

[0007] Collecting status data of each pipeline in the water supply network, and storing the status data in a water pipe status table of a time series database;

[0008] Determine the prediction parameters of the current pipeline based on the water pipe information table, the water pipe associated information table and the water pipe status table, wherein the prediction parameters are the status data of the current pipeline and the status data of the upstream pipeline and the downstream pipeline connected to the current pipeline;

[0009] Perform leakage prediction processing based on the prediction parameters using the pipeline leakage model to obtain a leakage degree prediction value;

[0010] The predicted value of the leakage degree and the predicted parameters are recorded in a prediction information table, and leakage prediction processing is performed on the next pipeline in the water supply network based on the pipeline leakage model until the prediction of all pipelines in the water supply network is completed, thereby obtaining a target prediction information table.

[0011] In order to solve the above technical problems, the present application provides a water supply pipeline leakage detection device, including:

[0012] A water pipe information recording unit, used to record the water pipe information of each pipe in the water supply network into a water pipe information table, and record the water pipe information of the upstream pipe and the downstream pipe connected to each of the pipes into a water pipe association information table;

[0013] A state data collection unit, used for collecting state data of each of the pipes in the water supply network, and storing the state data in a water pipe state table of a time series database;

[0014] A prediction parameter determination unit, configured to determine a prediction parameter of a current pipeline based on the water pipe information table, the water pipe associated information table, and the water pipe status table, wherein the prediction parameter is status data of the current pipeline and status data of an upstream pipeline and a downstream pipeline connected to the current pipeline;

[0015] A leakage prediction unit, configured to perform leakage prediction processing based on the prediction parameters using the pipeline leakage model to obtain a leakage degree prediction value;

[0016] A target prediction information table generating unit is used to record the leakage degree prediction value and the prediction parameters in the prediction information table, and perform leakage prediction processing on the next pipeline in the water supply network based on the pipeline leakage model, until the prediction of all pipelines in the water supply network is completed, and a target prediction information table is obtained.

[0017] In order to solve the above technical problems, a technical solution adopted by the present invention is: to provide an Internet of Things platform, including one or more processors; a memory for storing one or more programs, so that one or more processors can implement any one of the above-mentioned water supply pipeline leakage detection methods.

[0018] To solve the above technical problems, a technical solution adopted by the present invention is: a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, any one of the above-mentioned water supply pipe leakage detection methods is implemented.

[0019] The embodiment of the present invention provides a method, device, Internet of Things platform and medium for detecting leakage in a water supply pipeline. The method includes: recording the water pipe information of each pipeline in the water supply network into a water pipe information table, and recording the water pipe information of the upstream pipeline and the downstream pipeline connected to each of the pipelines into a water pipe association information table; collecting the status data of each pipeline in the water supply network, and storing the status data in a water pipe status table of a time series database; determining the prediction parameters of the current pipeline based on the water pipe information table, the water pipe association information table and the water pipe status table, wherein the prediction parameters are the status data of the current pipeline and the status data of the upstream pipeline and the downstream pipeline connected to the current pipeline; performing leakage prediction processing based on the prediction parameters through the pipeline leakage model to obtain a leakage degree prediction value; recording the leakage degree prediction value and the prediction parameters into the prediction information table, and performing leakage prediction processing on the next pipeline in the water supply network based on the pipeline leakage model, until all pipelines in the water supply network are predicted, and a target prediction information table is obtained. The embodiment of the present invention records the water pipe information and status information of each pipe in the water supply network, and records the upstream and downstream pipe information corresponding to each pipe. When water supply pipe leakage detection is required, the corresponding prediction parameters can be accurately and quickly obtained from the recorded data table. At the same time, the water supply pipe leakage is predicted for each pipe based on the prediction parameters through the pipe leakage model, so that timely water supply pipe leakage detection is realized, and the leakage point in the water supply pipe can be effectively identified and located, which effectively improves the accuracy of water supply pipe leakage detection and meets the complex and changeable water supply environment and the growing leakage detection needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1 It is a flow chart for implementing the water supply pipeline leakage detection method process provided in the embodiment of the present application;

[0022] Figure 2 is a specific implementation flow chart of step S2 provided in an embodiment of the present application;

[0023] Figure 3 is a specific implementation flow chart of step S3 provided in the embodiment of the present application;

[0024] Figure 4 It is a specific implementation flow chart before step S4 provided in the embodiment of the present application;

[0025] Figure 5 It is a specific implementation flow chart after step S4 provided in the embodiment of the present application;

[0026] Figure 6 It is a specific implementation flow chart after step S5 provided in the embodiment of the present application;

[0027] Figure 7 It is a schematic diagram of a water supply pipeline leakage detection device provided in an embodiment of the present application;

[0028] Figure 8 It is a schematic diagram of the Internet of Things platform provided in an embodiment of the present application. DETAILED DESCRIPTION

[0029] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0030] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0031] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0032] The present invention is described in detail below with reference to the accompanying drawings and embodiments.

[0033] It should be noted that the water supply pipe leakage detection method provided in the embodiment of the present application is generally executed by an Internet of Things platform, and accordingly, the water supply pipe leakage detection device is generally configured in the Internet of Things platform.

[0034] See also Figure 1 , Figure 1 A specific implementation of a water supply pipeline leakage detection method is shown.

[0035] It should be noted that if there are substantially the same results, the method of the present invention is not limited to Figure 1 The process sequence shown is limited to the following steps:

[0036] S1: Record the water pipe information of each pipe in the water supply network into a water pipe information table, and record the water pipe information of the upstream pipe and the downstream pipe connected to each of the pipes into a water pipe association information table.

[0037] Specifically, all pipeline information in the water supply network is managed, that is, the water pipe information of each pipeline in the water supply network needs to be recorded in the water pipe information table of the database, wherein the water pipe information includes mechanism data such as water pipe number, pipe diameter, length, and altitude. Then, the water pipe information of the upstream and downstream pipelines corresponding to each pipeline needs to be recorded in the water pipe association information table of the database. In the embodiment of the present application, by recording the water pipe information of each pipeline and the water pipe information of its corresponding upstream and downstream pipelines, it is convenient to quickly identify the water pipe information of each pipeline in the subsequent process, and it is convenient to locate the corresponding pipeline, thereby improving the efficiency and timeliness of water supply pipeline leakage detection.

[0038] S2: Collecting status data of each pipeline in the water supply network, and storing the status data in a water pipe status table in a time series database.

[0039] In the embodiment of the present application, the status data of each pipeline in the water pipe network is collected at regular intervals, and the status data is reported to the Internet of Things platform, which stores the status data in a water pipe status table in a time series database.

[0040] See also Figure 2 , Figure 2 A specific implementation of step S2 is shown, which is described in detail as follows:

[0041] S21: collecting the status data based on a preset period through the Internet of Things detection device of each pipeline in the water supply network, wherein the status data includes water pipe number, pressure, flow rate, water temperature and water quality;

[0042] S22: Storing the status data in the water pipe status table of the time series database.

[0043] Specifically, an IoT detection device is installed in each pipeline of the water supply network, and the IoT detection device can detect the status data of the pipeline. In an embodiment of the present application, the IoT detection device of each pipeline in the water supply network collects status data based on a preset period, wherein the status data acquired in each period is reported to the IoT platform, and the status data includes water pipe number, pressure, flow rate, water temperature, water quality and other indicator data. The status data is then stored in the water pipe status table of the time series database, and its storage format is water pipe number, second-level timestamp, pressure, flow rate, water temperature, and water quality.

[0044] It should be noted that the preset period is set according to actual conditions and is not limited here. In a specific embodiment, the state data is collected once in a period of 10 minutes.

[0045] S3: Determine the prediction parameters of the current pipeline based on the water pipe information table, the water pipe associated information table and the water pipe status table.

[0046] The prediction parameters are the status data of the current pipeline and the status data of the upstream pipeline and the downstream pipeline connected to the current pipeline.

[0047] Specifically, when water supply pipeline leakage detection is actually needed, it is necessary to traverse the water pipe information table, the water pipe associated information table and the water pipe status table to obtain the status data of the current pipeline and the status data of the upstream and downstream pipelines connected to the current pipeline to obtain prediction parameters.

[0048] See also Figure 3 , Figure 3 A specific implementation of step S3 is shown, which is described in detail as follows:

[0049] S31: Determine whether the current time is within a preset water peak time period. If so, traverse the water pipe information table to obtain the water pipe information of the current pipe, wherein the water pipe information includes pipe number, pipe diameter, length and altitude information.

[0050] Specifically, water supply pipelines are often prone to leakage during the peak water flow period, so the water supply pipelines during the peak water flow period are tested. Of course, the present application can also test water supply pipelines during non-peak water flow periods, directly obtain the prediction parameters for the period, and perform leakage prediction based on the prediction parameters based on the pipeline leakage model to obtain the water supply pipeline leakage detection results for the period.

[0051] The embodiment of the present application detects the water supply pipeline within the water peak time period, so it is first determined whether the current time is within the preset water peak time period. If the current time is within the preset water peak time period, the water pipe information table is traversed to obtain the water pipe information of the current pipe, wherein the water pipe information includes the pipe number, pipe diameter, length and altitude information. If the current time is not within the preset water peak time period, the acquisition of prediction parameters and water supply pipe leakage detection are not performed.

[0052] The preset peak water usage time period is set according to the actual situation and is not limited here. In a specific embodiment, the preset peak water usage time period is between 6:00-8:00 in the morning and / or 6:00-8:00 in the afternoon every day. The peak water usage time period refers to the peak period of water usage.

[0053] S32: Acquire the status data of the current pipeline within a preset time from the water pipe status table according to the pipeline number.

[0054] Specifically, the status data of a current pipeline within a preset time is obtained from the water pipe status table according to the pipeline number, wherein the status data is the water pipe pressure, flow rate, water temperature and water quality. If the status data of the current pipeline cannot be obtained, the next pipeline is obtained from the water supply network as the current pipeline, and step S31 is re-executed.

[0055] It should be noted that the preset time is set according to the actual situation and is not limited here. In a specific embodiment, the state data of the most recent current pipeline within 15 minutes is obtained from the water pipe state table.

[0056] S33: Based on the pipeline number, water pipe information of the upstream pipeline and the downstream pipeline connected to the current pipeline is obtained from the water pipe association information table to obtain upstream pipeline information and downstream pipeline information.

[0057] Specifically, the water pipe information of the upstream pipe and the downstream pipe connected to the current pipe is obtained from the water pipe association information table based on the pipe number, and the upstream pipe information and the downstream pipe information are obtained. If there are multiple upstream pipes and / or downstream pipes in the current pipe, one upstream pipe and one downstream pipe are randomly selected. If there are no upstream pipes and / or downstream pipes in the current pipe, the next pipe is obtained from the water supply network as the current pipe, and the process returns to step S31.

[0058] S34: Acquire the status data of the upstream pipeline and the downstream pipeline connected to the current pipeline within the preset time from the water pipe status table based on the upstream pipeline information and the downstream pipeline information.

[0059] Specifically, the status data of the upstream pipe and the downstream pipe connected to the current pipe within the preset time are obtained from the water pipe status table. In a specific embodiment, the status data of the upstream pipe and the downstream pipe connected to the current pipe most recently within 15 minutes are obtained.

[0060] S4: performing leakage prediction processing based on the prediction parameters using the pipeline leakage model to obtain a leakage degree prediction value.

[0061] Specifically, before implementing step S4, the present application also trains and deploys a pipeline leakage model. The above-obtained prediction parameters are the state data of the current pipeline, the state data of the upstream pipeline, and the state data of the downstream pipeline. The state data are water pipe pressure, flow rate, water temperature, water quality, pipe diameter, length, and altitude information. In the embodiment of the present application, the pipeline leakage model is used to perform leakage prediction processing based on the prediction parameters to obtain a leakage degree prediction value.

[0062] See also Figure 4 , Figure 4 A specific implementation method before step S4 is shown, which is described in detail as follows:

[0063] S41: Acquire historical data of pipeline status within a preset water peak time period, wherein each piece of training data in the historical data of pipeline status includes the leakage degree of the current training pipeline, the status data of the current training pipeline, and the status data of the upstream pipeline and the downstream pipeline corresponding to the current training pipeline;

[0064] S42: loading the training data into the neural network model, taking the leakage degree of the current training pipeline as the prediction value of the model training, and using a cross-validation algorithm to perform model training on the neural network model to obtain a model training prediction result;

[0065] S43: If the accuracy of the prediction result of the model training is lower than the preset value, the parameters of the neural network model are adjusted and the iterative training is re-performed until the accuracy of the new model training prediction result is higher than the preset value, so as to obtain a trained neural network model, and use the trained neural network model as the pipeline leakage model.

[0066] Specifically, historical data of pipeline status within a preset water peak time period is obtained. In a specific embodiment, historical data of pipeline status in the time periods of 6:00-8:00 in the morning and 6:00-8:00 in the afternoon are obtained. Among them, each training data in the historical data of pipeline status includes the leakage degree of the current training pipeline, the status data of the current training pipeline, and the status data of the upstream pipeline and downstream pipeline corresponding to the current training pipeline. The leakage degree can be divided according to different degrees, such as leakage degree 0: no leakage, leakage degree 1: slight leakage (less than 5%), leakage degree 2: moderate leakage (5%~15%), leakage degree 3: severe leakage (>15%).

[0067] Specifically, select machine learning model training software, such as WEKA (Waikato Environment for Knowledge Analysis). In the machine learning model training software, select a neural network algorithm as the training model algorithm, then load the training data into the neural network model, use the leakage degree of the current training pipeline as the prediction value of the model training, and use the cross-validation algorithm to train the neural network model to obtain the model training prediction result. If the accuracy of the model training prediction result is lower than the preset value, adjust the parameters of the neural network model (such as adjusting the model learning rate, hidden layer and other parameters), re-iterate the training until the accuracy of the new model training prediction result is higher than the preset value, obtain the trained neural network model, and use the trained neural network model as the pipeline leakage model.

[0068] It should be noted that the preset value is set according to the actual situation and is not limited here.

[0069] S44: Loading the pipeline leakage model based on an application programming interface of a machine learning development framework.

[0070] S45: Encapsulate the model prediction interface corresponding to the pipeline leakage model.

[0071] Specifically, after the pipeline leakage model is trained, the pipeline leakage model needs to be deployed. Therefore, the embodiment of the present application loads the pipeline leakage model based on the application programming interface of the machine learning development framework, and encapsulates the model prediction interface corresponding to the pipeline leakage model. Therefore, the input parameters of the model prediction interface include the water pipe pressure, flow rate, water temperature, water quality, pipe diameter, length, and altitude information of the current pipeline, upstream pipeline, and downstream pipeline, and the output result is the leakage degree value.

[0072] See also Figure 5 , Figure 5 A specific implementation after step S4 is shown, which is described in detail as follows:

[0073] S4A: Determine whether the predicted value of the leakage degree exceeds a preset threshold value, and obtain a determination result;

[0074] S4B: If the judgment result is that the predicted value of the leakage degree exceeds the preset threshold, an alarm message is generated, and a pipeline leakage alarm is issued based on the alarm message.

[0075] Specifically, it is determined whether the predicted value of the leakage degree exceeds the preset threshold value to obtain a judgment result. If the judgment result is that the predicted value of the leakage degree exceeds the preset threshold value, an alarm message is generated, and a pipeline leakage alarm is issued based on the alarm message. The leakage degree has been divided into different degrees, such as leakage degree 0: no leakage, leakage degree 1: slight leakage (less than 5%), leakage degree 2: moderate leakage (5%~15%), leakage degree 3: severe leakage (>15%). In a specific embodiment, if the predicted value of the leakage degree is a leakage degree of 1 or more (the preset threshold value is 1 or more), an alarm message is generated and an alarm is issued. Furthermore, the leakage degree can be written into the alarm message for alarm, so that the management personnel can perform emergency repair actions to different degrees according to different degrees.

[0076] S5: Based on the leakage degree prediction value and the prediction parameters, the prediction information table is recorded, and based on the pipeline leakage model, the leakage prediction processing is performed on the next pipeline in the water supply network until the prediction of all pipelines in the water supply network is completed, and the target prediction information table is obtained.

[0077] Specifically, the leakage degree prediction value is matched with the prediction parameter one by one and recorded in the prediction information table. After completing the detection of one pipeline, the next pipeline in the water supply network is re-acquired, and leakage prediction processing is performed based on the pipeline leakage model until the prediction of all pipelines in the water supply network is completed, and the target prediction information table is obtained.

[0078] See also Figure 6 , Figure 6 A specific implementation after step S5 is shown, which is described in detail as follows:

[0079] S5A: construct new training data based on the target prediction information table;

[0080] S5B: training the pipeline leakage model using the new training data to obtain a new pipeline leakage model;

[0081] S5C: replacing the pipeline leakage model with the new pipeline leakage model.

[0082] Specifically, the model management personnel can adjust the prediction results in the target prediction information table according to the actual situation, and build new training data based on the adjusted target prediction information table; train the pipeline leakage model with the new training data to obtain a new pipeline leakage model; and replace the pipeline leakage model with the new pipeline leakage model.

[0083] In an embodiment of the present application, the water pipe information of each pipe in the water supply network is recorded in a water pipe information table, and the water pipe information of the upstream pipe and the downstream pipe connected to each of the pipes is recorded in a water pipe association information table; the status data of each pipe in the water supply network is collected, and the status data is stored in a water pipe status table in a time series database; based on the water pipe information table, the water pipe association information table and the water pipe status table, the prediction parameters of the current pipe are determined, wherein the prediction parameters are the status data of the current pipe and the status data of the upstream pipe and the downstream pipe connected to the current pipe; leakage prediction processing is performed based on the prediction parameters through the pipeline leakage model to obtain a leakage degree prediction value; based on the leakage degree prediction value and the prediction parameters, they are recorded in the prediction information table, and based on the pipeline leakage model, leakage prediction processing is performed on the next pipe in the water supply network, until the prediction of all pipes in the water supply network is completed, and a target prediction information table is obtained. The embodiment of the present invention records the water pipe information and status information of each pipe in the water supply network, and records the upstream and downstream pipe information corresponding to each pipe. When water supply pipe leakage detection is required, the corresponding prediction parameters can be accurately and quickly obtained from the recorded data table. At the same time, the water supply pipe leakage is predicted for each pipe based on the prediction parameters through the pipe leakage model, so that timely water supply pipe leakage detection is realized, and the leakage point in the water supply pipe can be effectively identified and located, which effectively improves the accuracy of water supply pipe leakage detection and meets the complex and changeable water supply environment and the growing leakage detection needs.

[0084] Furthermore, the embodiment of the present application is based on the automated water supply network leakage detection process of IoT sensing data collection and neural network leakage prediction, which can greatly improve the detection efficiency of pipeline leakage and reduce water resource waste. The neural network model of the embodiment of the present application combines the detection data and mechanism data of the current pipeline, upstream pipeline and downstream pipeline, which improves the detection accuracy while making the model have better generalization ability and can be quickly applied to leakage detection of pipeline networks in various places.

[0085] Please refer to Figure 7 , as a response to the above Figure 1 The present application provides an embodiment of a water supply pipeline leakage detection device, and the device embodiment is similar to Figure 1 Corresponding to the method embodiment shown, the device can be specifically applied to various Internet of Things platforms.

[0086] like Figure 7 As shown, the water supply pipeline leakage detection device of this embodiment includes: a water pipe information recording unit 61, a state data acquisition unit 62, a prediction parameter determination unit 63, a leakage prediction unit 64 and a target prediction information table generation unit 65, wherein:

[0087] The water pipe information recording unit 61 is used to record the water pipe information of each pipe in the water supply network into the water pipe information table, and record the water pipe information of the upstream pipe and the downstream pipe connected to each of the pipes into the water pipe association information table;

[0088] A state data collection unit 62, used for collecting state data of each of the pipes in the water supply network, and storing the state data in a water pipe state table in a time series database;

[0089] A prediction parameter determination unit 63, configured to determine a prediction parameter of a current pipeline based on the water pipe information table, the water pipe associated information table and the water pipe status table, wherein the prediction parameter is status data of the current pipeline and status data of an upstream pipeline and a downstream pipeline connected to the current pipeline;

[0090] A leakage prediction unit 64 is used to perform leakage prediction processing based on the prediction parameters using the pipeline leakage model to obtain a leakage degree prediction value;

[0091] The target prediction information table generating unit 65 is used to record the leakage degree prediction value and the prediction parameters into the prediction information table, and perform leakage prediction processing on the next pipeline in the water supply network based on the pipeline leakage model until the prediction of all pipelines in the water supply network is completed, thereby obtaining a target prediction information table.

[0092] Furthermore, the state data acquisition unit 62 includes:

[0093] A data collection unit, used to collect the status data based on a preset period through the Internet of Things detection device of each pipeline in the water supply network, wherein the status data includes water pipe number, pressure, flow rate, water temperature and water quality;

[0094] A data storage unit is used to store the status data in the water pipe status table of the time series database.

[0095] Further, the prediction parameter determination unit 63 includes:

[0096] An information table traversal unit, used to determine whether the current time is within a preset water peak time period, and if so, traverse the water pipe information table to obtain the water pipe information of the current pipe, wherein the water pipe information includes pipe number, pipe diameter, length and altitude information;

[0097] A first status data acquisition unit, configured to acquire status data of the current pipeline within a preset time from the water pipe status table according to the pipeline number;

[0098] An upstream and downstream pipeline information acquisition unit, configured to acquire water pipe information of an upstream pipeline and a downstream pipeline connected to the current pipeline from the water pipe association information table based on the pipeline number, and obtain upstream pipeline information and downstream pipeline information;

[0099] The second status data acquisition unit is used to acquire the status data of the upstream pipeline and the downstream pipeline connected to the current pipeline within the preset time from the water pipe status table based on the upstream pipeline information and the downstream pipeline information.

[0100] Furthermore, before the leakage prediction unit 64, the following steps are also included:

[0101] A historical data acquisition unit, used to acquire historical data of pipeline status within a preset water peak time period, wherein each piece of training data in the historical data of pipeline status includes the leakage degree of the current training pipeline, the status data of the current training pipeline, and the status data of the upstream pipeline and the downstream pipeline corresponding to the current training pipeline;

[0102] A model training unit, used to load the training data into a neural network model, use the leakage degree of the current training pipeline as a prediction value for model training, and use a cross-validation algorithm to perform model training on the neural network model to obtain a model training prediction result;

[0103] The training completion unit is used to adjust the parameters of the neural network model if the accuracy of the model training prediction result is lower than the preset value, and re-perform iterative training until the accuracy of the new model training prediction result is higher than the preset value, so as to obtain a trained neural network model, and use the trained neural network model as the pipeline leakage model.

[0104] Furthermore, after the training unit is completed, it also includes:

[0105] A model loading unit, used for loading the pipeline leakage model based on an application programming interface of a machine learning development framework;

[0106] The interface encapsulation unit is used to encapsulate the model prediction interface corresponding to the pipeline leakage model.

[0107] Furthermore, the leakage prediction unit 64 further includes:

[0108] A judgment unit, used to judge whether the predicted value of the leakage degree exceeds a preset threshold value and obtain a judgment result;

[0109] An alarm unit is used to generate an alarm message if the judgment result is that the predicted value of the leakage degree exceeds the preset threshold, and to issue a pipeline leakage alarm based on the alarm message.

[0110] Furthermore, the target prediction information table generating unit 65 further includes:

[0111] A new training data generating unit, used for constructing new training data based on the target prediction information table;

[0112] A new model generation unit, used to train the pipeline leakage model using the new training data to obtain a new pipeline leakage model;

[0113] The model replacement unit is used to replace the pipeline leakage model with the new pipeline leakage model.

[0114] In an embodiment of the present application, the water pipe information of each pipe in the water supply network is recorded in a water pipe information table, and the water pipe information of the upstream pipe and the downstream pipe connected to each of the pipes is recorded in a water pipe association information table; the status data of each pipe in the water supply network is collected, and the status data is stored in a water pipe status table in a time series database; based on the water pipe information table, the water pipe association information table and the water pipe status table, the prediction parameters of the current pipe are determined, wherein the prediction parameters are the status data of the current pipe and the status data of the upstream pipe and the downstream pipe connected to the current pipe; leakage prediction processing is performed based on the prediction parameters through the pipeline leakage model to obtain a leakage degree prediction value; based on the leakage degree prediction value and the prediction parameters, they are recorded in the prediction information table, and based on the pipeline leakage model, leakage prediction processing is performed on the next pipe in the water supply network, until the prediction of all pipes in the water supply network is completed, and a target prediction information table is obtained. The embodiment of the present invention records the water pipe information and status information of each pipe in the water supply network, and records the upstream and downstream pipe information corresponding to each pipe. When water supply pipe leakage detection is required, the corresponding prediction parameters can be accurately and quickly obtained from the recorded data table. At the same time, the water supply pipe leakage is predicted for each pipe based on the prediction parameters through the pipe leakage model, so that timely water supply pipe leakage detection is realized, and the leakage point in the water supply pipe can be effectively identified and located, which effectively improves the accuracy of water supply pipe leakage detection and meets the complex and changeable water supply environment and the growing leakage detection needs.

[0115] To solve the above technical problems, the present application embodiment also provides an Internet of Things platform. Figure 8 , Figure 8 This is a basic structural block diagram of the Internet of Things platform in this embodiment.

[0116] The Internet of Things platform 7 includes a memory 71, a processor 72, and a network interface 73 that are interconnected through a system bus. It should be noted that: Figure 8 Only an IoT platform 7 having three components, memory 71, processor 72, and network interface 73, is shown, but it should be understood that it is not required to implement all the components shown, and more or fewer components may be implemented instead. Among them, those skilled in the art can understand that the IoT platform here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (ASIC), programmable gate arrays (FPGA), digital signal processors (DSP), embedded devices, etc.

[0117] The memory 71 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 71 can be an internal storage unit of the Internet of Things platform 7, such as a hard disk or memory of the Internet of Things platform 7. In other embodiments, the memory 71 can also be an external storage device of the Internet of Things platform 7, such as a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the Internet of Things platform 7. Of course, the memory 71 can also include both the internal storage unit of the Internet of Things platform 7 and its external storage device. In this embodiment, the memory 71 is generally used to store the operating system and various application software installed on the Internet of Things platform 7, such as the program code of the water supply pipeline leakage detection method, etc. In addition, the memory 71 can also be used to temporarily store various types of data that have been output or are to be output.

[0118] The processor 72 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 72 is generally used to control the overall operation of the Internet of Things platform 7. In this embodiment, the processor 72 is used to run the program code stored in the memory 71 or process data, such as running the program code of the water supply pipeline leakage detection method to implement various embodiments of the water supply pipeline leakage detection method.

[0119] The network interface 73 may include a wireless network interface or a wired network interface, and the network interface 73 is generally used to establish a communication connection between the Internet of Things platform 7 and other electronic devices.

[0120] The present application also provides another implementation, namely, providing a computer-readable storage medium, which stores a computer program. The computer program can be executed by at least one processor to enable the at least one processor to perform the steps of a water supply pipeline leakage detection method as described above.

[0121] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods of each embodiment of the present application.

[0122] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to replace some of the technical features therein with equivalents. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A water supply pipeline leakage detection method, characterized in that: include: Record the water pipe information of each pipe in the water supply network into a water pipe information table, and record the water pipe information of the upstream pipe and the downstream pipe connected to each pipe into a water pipe association information table; Collecting status data of each pipeline in the water supply network, and storing the status data in a water pipe status table of a time series database; Determine the prediction parameters of the current pipeline based on the water pipe information table, the water pipe associated information table and the water pipe status table, wherein the prediction parameters are the status data of the current pipeline and the status data of the upstream pipeline and the downstream pipeline connected to the current pipeline; Perform leakage prediction processing based on the prediction parameters through the pipeline leakage model to obtain a leakage degree prediction value; Based on the leakage degree prediction value and the prediction parameters, the prediction information table is recorded, and based on the pipeline leakage model, the next pipeline in the water supply network is subjected to leakage prediction processing until all pipelines in the water supply network are predicted, thereby obtaining a target prediction information table; Constructing new training data based on the target prediction information table; The pipeline leakage model is trained by using the new training data to obtain a new pipeline leakage model; The pipeline leakage model is replaced by the new pipeline leakage model.

2. The water supply pipeline leakage detection method according to claim 1, characterized in that: The collecting of the status data of each pipeline in the water supply network and storing the status data in a water pipe status table of a time series database includes: The state data is collected based on a preset period by an Internet of Things detection device of each of the pipes in the water supply network, wherein the state data includes the water pipe number, pressure, flow rate, water temperature and water quality; The state data is stored in the water pipe state table of the time series database.

3. The water supply pipeline leakage detection method according to claim 1, characterized in that: The determining the prediction parameters of the current pipeline based on the water pipe information table, the water pipe associated information table and the water pipe status table includes: Determine whether the current time is within a preset water peak time period, and if so, traverse the water pipe information table to obtain the water pipe information of the current pipe, wherein the water pipe information includes pipe number, pipe diameter, length and altitude information; Acquire the status data of the current pipeline within a preset time from the water pipe status table according to the pipeline number; Based on the pipeline number, water pipe information of the upstream pipeline and the downstream pipeline connected to the current pipeline is obtained from the water pipe association information table to obtain the upstream pipeline information and the downstream pipeline information; Based on the upstream pipeline information and the downstream pipeline information, the status data of the upstream pipeline and the downstream pipeline connected to the current pipeline within the preset time are acquired from the water pipe status table.

4. The water supply pipeline leakage detection method according to claim 1, characterized in that: Before performing leakage prediction processing based on the prediction parameters by using the pipeline leakage model to obtain a leakage degree prediction value, the method further includes: Acquire historical data of pipeline status within a preset water peak time period, wherein each piece of training data in the historical data of pipeline status includes the leakage degree of the current training pipeline, the status data of the current training pipeline, and the status data of the upstream pipeline and the downstream pipeline corresponding to the current training pipeline; The training data is loaded into the neural network model, the leakage degree of the current training pipeline is used as the prediction value of the model training, and the neural network model is trained by using a cross-validation algorithm to obtain the model training prediction result; If the accuracy of the model training prediction result is lower than the preset value, the parameters of the neural network model are adjusted and the iterative training is performed again until the accuracy of the new model training prediction result is higher than the preset value, so as to obtain a trained neural network model, and use the trained neural network model as the pipeline leakage model.

5. The water supply pipeline leakage detection method according to claim 4, characterized in that: If the accuracy of the model training prediction result is lower than the preset value, the parameters of the neural network model are adjusted, and iterative training is performed again until the accuracy of the new model training prediction result is higher than the preset value, and a trained neural network model is obtained. After the trained neural network model is used as the pipeline leakage model, the method further includes: Loading the pipeline leakage model through an application programming interface based on a machine learning development framework; Encapsulates the model prediction interface corresponding to the pipeline leakage model.

6. The water supply pipeline leakage detection method according to any one of claims 1 to 5, characterized in that: After the leakage prediction process is performed based on the prediction parameters by the pipeline leakage model to obtain the leakage degree prediction value, the method further includes: Determine whether the predicted value of the leakage degree exceeds a preset threshold value, and obtain a determination result; If the judgment result is that the predicted value of the leakage degree exceeds the preset threshold, an alarm message is generated, and a pipeline leakage alarm is issued based on the alarm message.

7. A water supply pipeline leakage detection device, characterized in that: include: A water pipe information recording unit, used to record the water pipe information of each pipe in the water supply network into a water pipe information table, and record the water pipe information of the upstream pipe and the downstream pipe connected to each of the pipes into a water pipe association information table; A state data collection unit, used for collecting state data of each of the pipes in the water supply network, and storing the state data in a water pipe state table of a time series database; A prediction parameter determination unit, configured to determine a prediction parameter of a current pipeline based on the water pipe information table, the water pipe associated information table, and the water pipe status table, wherein the prediction parameter is status data of the current pipeline and status data of an upstream pipeline and a downstream pipeline connected to the current pipeline; A leakage prediction unit, used to perform leakage prediction processing based on the prediction parameters through a pipeline leakage model to obtain a leakage degree prediction value; a target prediction information table generating unit, configured to record the leakage degree prediction value and the prediction parameters into a prediction information table, and perform leakage prediction processing on the next pipeline in the water supply network based on the pipeline leakage model, until the prediction of all pipelines in the water supply network is completed, thereby obtaining a target prediction information table; A new training data generating unit, used for constructing new training data based on the target prediction information table; A new model generation unit, used to train the pipeline leakage model using the new training data to obtain a new pipeline leakage model; The model replacement unit is used to replace the pipeline leakage model with the new pipeline leakage model.

8. An Internet of Things platform, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the water supply pipeline leakage detection method according to any one of claims 1 to 6 when executing the computer program.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the water supply pipeline leakage detection method according to any one of claims 1 to 6 is implemented.

Citation Information

Patent Citations

  • Water supply network leakage monitoring method, computer device and storage medium

    CN115218129A