Water supply pipeline burst detection method based on continuous flow characteristics

Abstract

The invention relates to a water supply pipeline burst detection method based on continuous flow characteristics. The method comprises the following steps: acquiring three continuous flow residual data of a water supply pipeline to be detected; according to region threshold values of a plurality of preset residual regions, obtaining a corresponding relationship between the three pieces of flow residual data and the plurality of preset residual regions, and according to the corresponding relationship, obtaining three continuous flow characteristics corresponding to the three pieces of flow residual data; and inputting the three continuous flow characteristics into a trained water supply pipeline burst detection model to obtain a burst detection result of the water supply pipeline to be detected. The three continuous flow characteristics are obtained according to the three continuous flow residual data of the water supply pipeline to be detected, so that the characteristics of the continuous flow data of the water supply pipeline to be detected are reflected, the method can be used for accurately performing burst detection on the water supply pipeline, the required data volume is small, and the burst detection efficiency of the water supply pipeline can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of detecting water supply pipelines, and in particular to a water supply pipeline burst detection method based on continuous flow characteristics. BACKGROUND

[0002] As an important part of urban infrastructure, the operation state of the water pipe network is directly related to the safety and stability of urban water supply. However, with the increase of the service life of the pipe network and the uncertainty of the external environment, water supply pipeline burst events occur from time to time, which may cause large-scale water stop and road collapse. Therefore, how to efficiently and accurately detect water supply pipeline burst in real time has become one of the key problems in the field of current municipal engineering and smart water.

[0003] At present, the detection technology of water supply pipelines mainly relies on manual inspection, and the degree of automation is low. The detection personnel usually uses a leak detector, ground penetrating radar and other equipment to patrol and compare suspected leakage points one by one. The leak detector captures the high-frequency sound generated by pipeline leakage to make a manual sound judgment, and the ground penetrating radar can detect underground medium changes to assist in judging the pipeline damage position. Although this method is simple in equipment and low in cost, it relies on manual experience, has low work efficiency, limited coverage, and low accuracy in noisy traffic and complex underground structures, and is not suitable for large-scale and real-time monitoring requirements. SUMMARY

[0004] Therefore, the purpose of the present application is to provide a water supply pipeline burst detection method based on continuous flow characteristics, which can overcome the shortcomings of the prior art.

[0005] In order to achieve the above-mentioned purpose, the technical scheme adopted by the present application is as follows: The first aspect of the embodiment of the present application provides a water supply pipeline burst detection method based on continuous flow characteristics, comprising: obtaining three continuous flow residual data of a water supply pipeline to be detected; obtaining the correspondence between the three flow residual data and a plurality of preset residual regions according to the region threshold of the plurality of preset residual regions; obtaining three continuous flow characteristics corresponding to the three flow residual data according to the correspondence; inputting the three continuous flow characteristics into a trained water supply pipeline burst detection model to obtain a burst detection result of the water supply pipeline to be detected.

[0006] As an implementation manner, the step of obtaining three continuous flow residual data of the water supply pipeline to be detected comprises: obtaining actual flow data and predicted flow data of the water supply pipeline to be detected corresponding to different time nodes; According to a data difference between the predicted flow data and the actual flow data, the flow residual data is obtained; According to a time node corresponding to the flow residual data, three continuous flow residual data are obtained.

[0007] As an implementation, the step of obtaining the actual flow data and the predicted flow data corresponding to different time nodes of the water supply pipeline to be detected comprises: If the actual flow data has data loss, and the amount of continuous loss data is less than 3, the actual flow data is forward filled, and if the amount of continuous loss data is greater than or equal to 3, the actual flow data is interpolated filled according to the average value of historical flow data of the same time node.

[0008] As an implementation, the step of obtaining the actual flow data and the predicted flow data corresponding to different time nodes of the water supply pipeline to be detected comprises: If the time node of the actual flow data is repeated, and the data values corresponding to the repeated time nodes are different, the data values corresponding to the repeated time nodes are updated according to the data values corresponding to a plurality of time nodes before the repeated time nodes.

[0009] As an implementation, the step of obtaining the actual flow data and the predicted flow data corresponding to different time nodes of the water supply pipeline to be detected comprises: If the actual flow data has isolated extreme values, the data values of the isolated extreme values are updated according to the data values corresponding to a plurality of time nodes before and after the isolated extreme values.

[0010] As an implementation, the step of obtaining the actual flow data and the predicted flow data corresponding to different time nodes of the water supply pipeline to be detected comprises: If the waveform graph corresponding to the actual flow data has a sharp peak signal, the data values corresponding to the sharp peak signal are filtered.

[0011] As an implementation, the step of obtaining three continuous flow features corresponding to the three flow residual data according to the corresponding relationship comprises: Based on the corresponding relationship between the first flow residual data and the plurality of preset residual regions and a preset first mapping relationship, a first continuous flow feature and a feature level are obtained; Based on the corresponding relationship between the first flow residual data and the second flow residual data and the plurality of preset residual regions and a preset second mapping relationship, a second continuous flow feature is obtained according to the first continuous flow feature and the feature level; According to the first continuous traffic feature, the second continuous traffic feature and the feature level, a third continuous traffic feature is obtained based on the correspondence between the first traffic residual data, the second traffic residual data and the third traffic residual data and the plurality of preset residual regions, and a preset third mapping relationship.

[0012] As an implementation form, the step of obtaining the first continuous traffic feature and the feature level based on the correspondence between the first traffic residual data and the plurality of preset residual regions and the preset first mapping relationship comprises: The first continuous traffic feature is obtained by the following formula: wherein, is the first continuous traffic feature, is the first traffic residual data, , , , , , and is the plurality of preset residual regions. The feature level is obtained by the following formula: wherein, is the feature level.

[0013] As an implementation form, the step of obtaining the second continuous traffic feature based on the correspondence between the first traffic residual data and the second traffic residual data and the plurality of preset residual regions and the preset second mapping relationship comprises: The second continuous traffic feature is obtained by the following formula: wherein, is the second continuous traffic feature, is the first continuous traffic feature, is the first traffic residual data, is the feature level, , wherein, , , , , and is the plurality of preset residual regions.

[0014] As an implementation, the step of obtaining a third continuous flow feature according to the first continuous flow feature, the second continuous flow feature and the feature level, based on the correspondence relationship between the first flow residual data, the second flow residual data and the third flow residual data and the plurality of preset residual regions, and the preset third mapping relationship, comprises: The third continuous flow feature is obtained by the following formula: wherein, is the third continuous flow feature, is the second continuous flow feature, is the first continuous flow feature, is the first flow residual data, is the feature level, , wherein, , , , , and is the plurality of preset residual regions.

[0015] Compared with the prior art, the application has the following beneficial effects: The water supply pipeline burst detection method based on continuous flow features of the application can obtain three continuous flow features corresponding to three flow residual data of a to-be-detected water supply pipeline according to the correspondence relationship between the three flow residual data and the plurality of preset residual regions, and then input the three continuous flow features into a trained water supply pipeline burst detection model to obtain a burst detection result of the to-be-detected water supply pipeline. Since the three continuous flow features are obtained according to the three flow residual data of the to-be-detected water supply pipeline, the features of the continuous flow data of the to-be-detected water supply pipeline are embodied, which can be used for accurately detecting the burst of the water supply pipeline, and the amount of data required is less, which can improve the burst detection efficiency of the water supply pipeline.

[0016] In order to better understand and implement, the application will be described in detail below with reference to the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 The step schematic diagram of the water supply pipeline burst detection method based on continuous flow features of an embodiment of the application; Figure 2 The waveform diagram of actual flow data of the water supply pipeline burst detection method based on continuous flow features of an embodiment of the application; Figure 3The waveforms of actual flow data and predicted flow data of a water supply pipeline burst detection method based on continuous flow characteristics according to an embodiment of this application are shown. Figure 4 This is a schematic diagram of multiple preset residual regions in a water supply pipeline burst detection method based on continuous flow characteristics according to an embodiment of this application; Figure 5 This is a schematic diagram of the continuous flow characteristics corresponding to the first feature level of a water supply pipeline burst detection method based on continuous flow characteristics according to an embodiment of this application. Figure 6 This is a schematic diagram of the continuous flow characteristics corresponding to the second feature level of a water supply pipeline burst detection method based on continuous flow characteristics according to an embodiment of this application. Figure 7 This is a schematic diagram of the continuous flow characteristics corresponding to the third feature level of a water supply pipeline burst detection method based on continuous flow characteristics according to an embodiment of this application. Figure 8 This is a schematic flowchart of a water supply pipeline burst detection method based on continuous flow characteristics according to an embodiment of this application; Detailed Implementation To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0018] It should be understood that the described embodiments are merely some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of the embodiments of this application.

[0019] In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. In the description of this application, it should be understood that the terms "first," "second," "third," etc., are used only to distinguish similar objects and are not necessarily used to describe a specific order or sequence, nor should they be construed as indicating or implying relative importance. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances. The singular forms "a," "the," and "the" used in this application and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise. The word "if" as used herein can be interpreted as "when," "when," or "in response to determination."

[0020] Furthermore, in the description of this application, unless otherwise stated, "multiple" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0021] Please see Figure 1 This is a flowchart of a water supply pipeline burst detection method based on continuous flow characteristics according to the first embodiment of this application. The method includes: S1: Obtain three consecutive flow residual data of the water supply pipeline to be tested; S2: Based on the region thresholds of multiple preset residual regions, obtain the correspondence between the three traffic residual data and the multiple preset residual regions; S3: Based on the correspondence, obtain the three continuous flow characteristics corresponding to the three flow residual data.

[0022] The three continuous flow characteristics include the first continuous flow characteristic, the second continuous flow characteristic, and the third continuous flow characteristic.

[0023] S4: Input the three continuous flow characteristics into the trained water supply pipeline burst detection model to obtain the burst detection result of the water supply pipeline to be detected.

[0024] The trained water supply pipeline burst detection model was obtained by training an SVM model using training data samples. The burst detection results include multiple categories such as normal bursts, minor bursts, moderate bursts, and severe bursts. The training data samples include continuous flow characteristic samples and corresponding result samples.

[0025] In a feasible embodiment, step S1: obtaining three consecutive flow residual data of the water supply pipeline to be tested, includes: S11: Obtain the actual flow rate data and predicted flow rate data of the water supply pipeline to be tested at different time points.

[0026] The actual flow rate data can be obtained by sensors installed in the water supply pipeline to be tested, and the predicted flow rate data is the predicted data output by the trained flow prediction model based on the actual flow rate data.

[0027] Please see Figure 2If sensor malfunctions, data transmission conflicts, or other issues lead to missing, duplicated, isolated extreme points, or spikes in the actual traffic data, it will severely affect the accuracy of the predicted traffic data obtained from the actual traffic data. Therefore, when missing, duplicated, isolated extreme points, or spikes occur in the actual traffic data, preprocessing is necessary to correct the actual traffic data. For example: S111: If the actual traffic data has missing data and the number of consecutive missing data is less than 3, the actual traffic data is filled in positively; if the number of consecutive missing data is greater than or equal to 3, the data is filled by interpolation based on the average value of historical traffic data at the same time point.

[0028] S112: If the time nodes of the actual traffic data are repeated and the data values ​​corresponding to the repeated time nodes are different, update the data value corresponding to the repeated time node according to the data values ​​corresponding to the several time nodes before the repeated time node.

[0029] Step S112 can update the data value corresponding to the repeated time node using the following formula: in, For repeating time nodes The corresponding data values, For repeating time nodes The data value corresponding to the previous time point. Time node The data value corresponding to the previous time point. Time node The data value corresponding to the previous time point. , and Here, are the data weighting coefficients, .

[0030] S113: If the actual traffic data has isolated extreme values, update the data value of the isolated extreme value according to the data values ​​corresponding to the previous and subsequent time nodes of the isolated extreme value.

[0031] S114: If the waveform corresponding to the actual flow data contains spike signals, the data values ​​corresponding to the spike signals are filtered. For example, Loess filtering technology can be used for filtering.

[0032] The traffic prediction model in this embodiment can use an LSTM model. The trained LSTM model is used to predict data at future time points. For example, it can use seven consecutive data points corresponding to the same time point in three adjacent days as the main input to predict the output at the next time point.

[0033] Please see Figure 3 The deviation value of the flow forecast indicates the degree of anomaly in the current event. Under normal circumstances, the residual between the model's predicted value and the actual value is relatively small. When an anomaly occurs, the residual will change abruptly. Since the predicted value is determined by historical patterns, it will not change drastically and irregularly, while the actual value is affected by real factors and may fluctuate significantly. During a pipe burst, the actual value changes drastically and irregularly, while the predicted value remains stable, resulting in a large abrupt change in the residual.

[0034] S12: Obtain the traffic residual data based on the data difference between the predicted traffic data and the actual traffic data.

[0035] For example, the flow residual data can be obtained using the following formula: in, The traffic residual data, For the predicted traffic data, This refers to the actual traffic data.

[0036] S13: Based on the time nodes corresponding to the traffic residual data, obtain three consecutive traffic residual data.

[0037] Among them, the three traffic residual data are three consecutive traffic residual data at three different time points.

[0038] In a feasible embodiment, step S3: obtaining the three continuous flow characteristics corresponding to the three flow residual data according to the correspondence, includes: S31: Based on the correspondence between the first traffic residual data and the multiple preset residual regions and the preset first mapping relationship, obtain the first continuous traffic feature and the feature level; S32: Based on the correspondence between the first and second traffic residual data and the plurality of preset residual regions, and the preset second mapping relationship, obtain the second continuous traffic feature according to the first continuous traffic feature and the feature level; S33: Based on the correspondence between the first traffic residual data, the second traffic residual data, and the third traffic residual data and the multiple preset residual regions, and the preset third mapping relationship, obtain the third continuous traffic feature according to the first continuous traffic feature, the second continuous traffic feature, and the feature level.

[0039] Please see Figure 4 The plurality of preset residual regions include , , , , , and Multiple preset residual regions can be defined based on residual thresholds to determine their corresponding region ranges, for example: , , , , , , ;in, This is the modification coefficient for the residual threshold. More specifically, by multiplying the standard deviation by... This allows for fine-tuning of the total threshold to adapt to water usage habits in different regions and seasons.

[0040] In a feasible embodiment, step S31, which involves obtaining the first continuous traffic feature and its level based on the correspondence between the first traffic residual data and the plurality of preset residual regions and the preset first mapping relationship, includes: The first continuous flow characteristic is obtained using the following formula: in, This is the first continuous flow characteristic. For the first flow residual data, , , , , , and These are the multiple preset residual regions; The feature level is obtained using the following formula: in, The feature level is described above.

[0041] In a feasible embodiment, step S32: obtaining the second continuous traffic feature based on the correspondence between the first and second traffic residual data and the plurality of preset residual regions, respectively, and the preset second mapping relationship, according to the first continuous traffic feature and the feature level, includes: The second continuous flow characteristic is obtained using the following formula: in, This is the second continuous flow characteristic. This is the first continuous flow characteristic. For the first flow residual data, For the feature level, , ,in, , , , , and These are the multiple preset residual regions.

[0042] In a feasible embodiment, step S33: obtaining the third continuous flow feature based on the correspondence between the first flow residual data, the second flow residual data, and the third flow residual data and the plurality of preset residual regions, respectively, and the preset third mapping relationship, according to the first continuous flow feature, the second continuous flow feature, and the feature level, includes: The third continuous flow characteristic is obtained using the following formula: in, The third continuous flow characteristic, This is the second continuous flow characteristic. This is the first continuous flow characteristic. For the first flow residual data, For the feature level, , ,in, , , , , and These are the multiple preset residual regions.

[0043] Water pipe bursts are sudden and last for a period of time. Fluctuations in pipeline operation data make it difficult to identify individual anomalies, leading to a high false alarm rate. Therefore, this method utilizes continuous anomaly data after a pipe burst to detect it. The obtained continuous flow characteristics are as follows: Figures 5-7 As shown.

[0044] In summary, please refer to Figure 8The water supply pipeline burst detection method based on continuous flow characteristics of this application can obtain three continuous flow characteristics corresponding to the three continuous flow residual data of the water supply pipeline to be detected, according to the correspondence between the three continuous flow residual data and multiple preset residual regions. These three continuous flow characteristics are then input into a trained water supply pipeline burst detection model to obtain the burst detection result of the water supply pipeline to be detected. Since the three continuous flow characteristics are obtained from the three continuous flow residual data of the water supply pipeline to be detected, they reflect the characteristics of the continuous flow data of the water supply pipeline to be detected, and can be used to accurately detect bursts in water supply pipelines. Moreover, the required amount of data is relatively small, which can improve the burst detection efficiency of water supply pipelines.

[0045] Moreover, this application also has the following advantages: Improve the robustness and effectiveness of data processing: In response to the problems of strong fluctuations and frequent anomalies in water supply network operation data, it can effectively improve the stability and reliability of data during transmission and processing.

[0046] Enhanced adaptability and intelligence of rule models: This application improves traditional WEC rules, increases the flexibility of threshold settings, and can automatically adjust detection parameters according to water use characteristics, seasonal changes and historical flow data in different regions, thereby improving adaptability to diverse pipe network environments and reducing false alarms and missed alarms.

[0047] Achieving a more timely and accurate pipe burst early warning mechanism: This application can dynamically acquire the characteristic level of continuous flow data for trend analysis, thereby more sensitively identifying potential pipe burst events. Compared with traditional detection mechanisms based on single-point anomalies, this method has significant improvements in accuracy and real-time performance, which helps to achieve early warning and rapid response in water supply networks.

[0048] The device embodiments described above are merely illustrative. The components described as separate parts may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this application according to actual needs. Those skilled in the art can understand and implement this without any inventive effort.

[0049] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0050] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 The computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function selected in one or more boxes.

[0051] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function selected in one or more boxes.

[0052] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0053] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, like read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0054] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0055] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0056] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for detecting burst water supply pipes based on continuous flow characteristics, characterized in that, include: Obtain three consecutive flow residual data points from the water supply pipeline to be tested; Based on the regional thresholds of multiple preset residual regions, the correspondence between the three traffic residual data and the multiple preset residual regions is obtained; Based on the correspondence, obtain the three continuous flow features corresponding to the three flow residual data; The three continuous flow characteristics are input into the trained water supply pipeline burst detection model to obtain the burst detection result of the water supply pipeline to be detected.

2. The method for detecting burst water supply pipelines based on continuous flow characteristics according to claim 1, characterized in that, The step of obtaining three consecutive flow residual data of the water supply pipeline to be tested includes: Obtain the actual flow rate data and predicted flow rate data of the water supply pipeline to be tested at different time points; The traffic residual data is obtained based on the data difference between the predicted traffic data and the actual traffic data; Based on the time nodes corresponding to the traffic residual data, three consecutive traffic residual data are obtained.

3. The method for detecting burst water supply pipelines based on continuous flow characteristics according to claim 2, characterized in that, The steps of obtaining the actual flow data and predicted flow data of the water supply pipeline to be tested at different time points include: If the actual traffic data has missing data, and the number of consecutive missing data is less than 3, the actual traffic data is filled in positively. If the number of consecutive missing data is greater than or equal to 3, the data is filled by interpolation based on the average value of historical traffic data at the same time point.

4. The method for detecting burst water supply pipelines based on continuous flow characteristics according to claim 2, characterized in that, The steps of obtaining the actual flow data and predicted flow data of the water supply pipeline to be tested at different time points include: If the time points of the actual traffic data are repeated, and the data values ​​corresponding to the repeated time points are different, the data value corresponding to the repeated time point is updated according to the data values ​​corresponding to the several time points before the repeated time point.

5. The method for detecting burst water supply pipelines based on continuous flow characteristics according to claim 2, characterized in that, The steps of obtaining the actual flow data and predicted flow data of the water supply pipeline to be tested at different time points include: If the actual traffic data contains isolated extreme values, the data value of the isolated extreme value is updated based on the data values ​​corresponding to the preceding and following time nodes of the isolated extreme value.

6. The method for detecting burst water supply pipelines based on continuous flow characteristics according to claim 2, characterized in that, The steps of obtaining the actual flow data and predicted flow data of the water supply pipeline to be tested at different time points include: If the waveform corresponding to the actual traffic data contains spike signals, the data values ​​corresponding to the spike signals are filtered.

7. The method for detecting burst water supply pipelines based on continuous flow characteristics according to claim 1, characterized in that, The step of obtaining the three continuous flow features corresponding to the three flow residual data according to the correspondence includes: Based on the correspondence between the first traffic residual data and the multiple preset residual regions and the preset first mapping relationship, the first continuous traffic feature and feature level are obtained; Based on the correspondence between the first and second traffic residual data and the multiple preset residual regions, and the preset second mapping relationship, the second continuous traffic feature is obtained according to the first continuous traffic feature and the feature level. Based on the correspondence between the first, second, and third traffic residual data and the multiple preset residual regions, and the preset third mapping relationship, the third continuous traffic feature is obtained according to the first continuous traffic feature, the second continuous traffic feature, and the feature level.

8. The method for detecting burst water supply pipelines based on continuous flow characteristics according to claim 7, characterized in that, The step of obtaining the first continuous traffic feature and feature level based on the correspondence between the first traffic residual data and the multiple preset residual regions and the preset first mapping relationship includes: The first continuous flow characteristic is obtained using the following formula: in, This is the first continuous flow characteristic. For the first flow residual data, , , , , , and These are the multiple preset residual regions; The feature level is obtained using the following formula: in, The feature level is described above.

9. The method for detecting burst water supply pipelines based on continuous flow characteristics according to claim 7, characterized in that, The step of obtaining the second continuous traffic feature based on the correspondence between the first and second traffic residual data and the plurality of preset residual regions, and the preset second mapping relationship, according to the first continuous traffic feature and the feature level, includes: The second continuous flow characteristic is obtained using the following formula: in, This is the second continuous flow characteristic. This is the first continuous flow characteristic. For the first flow residual data, For the feature level, , ,in, , , , , and These are the multiple preset residual regions.

10. The method for detecting burst water supply pipelines based on continuous flow characteristics according to claim 7, characterized in that, The step of obtaining the third continuous flow feature based on the correspondence between the first, second, and third flow residual data and the plurality of preset residual regions, and the preset third mapping relationship, according to the first continuous flow feature, the second continuous flow feature, and the feature level, includes: The third continuous flow characteristic is obtained using the following formula: in, The third continuous flow characteristic, This is the second continuous flow characteristic. This is the first continuous flow characteristic. For the first flow residual data, For the feature level, , ,in, , , , , and These are the multiple preset residual regions.

Images