Water supply network leakage detection method and system

Abstract

The present invention provides a water supply network leakage detection method and system, which relates to the field of data processing technology. The method includes: performing exception processing on an original flow data set and an original pressure data set to obtain a standby flow data set and a standby pressure data set; obtaining predicted flow data through a flow prediction model, and judging whether there is a large amount of leakage at a pipeline node based on the real-time flow data and the predicted flow data; combining a plurality of pipeline nodes into a plurality of node pairs, obtaining the fluctuation correlation of the node pairs, and judging whether the node pairs are abnormal pairs based on the fluctuation correlation; selecting a plurality of nodes to be identified from all pipeline nodes based on the pipeline nodes in the abnormal pairs, obtaining residual values corresponding to the nodes to be identified, and selecting leakage nodes from the plurality of nodes to be identified based on the residual values to complete small-scale leakage detection. Compared with traditional manual detection, the method improves detection efficiency while improving detection accuracy, and achieves accurate detection of small amounts of leakage.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a water supply network leakage detection method and system. Background Art

[0002] Water supply networks are essential infrastructure for modern urban development and play a vital role in urban development and people's lives. Essentially, they are the pipeline systems that transport and distribute water to users within water supply projects.

[0003] However, as urban water supply networks continue to expand and their service life increases, leakage in large water supply networks has become a pressing issue that needs to be addressed. Leakage in water supply networks not only wastes water resources but also increases water supply safety risks.

[0004] At present, leakage detection in water supply networks mostly still relies on traditional passive manual inspection methods. Inspectors use tools such as listening sticks to detect and locate leakage in water supply networks. This method is not only inefficient, but also difficult to accurately identify whether there is a leakage when the leakage amount is small. Summary of the Invention

[0005] In view of the shortcomings of the existing technology, the purpose of the present invention is to provide a water supply network leakage detection method and system, which aims to solve the technical problem that the passive manual inspection method in the existing technology is used to detect and locate leakage in the water supply network. It not only has low detection efficiency, but also is difficult to accurately identify whether there is a leakage when the leakage amount is small.

[0006] To achieve the above objectives, in a first aspect, an embodiment of the present application provides a method for detecting leakage in a water supply network, comprising the following steps:

[0007] Acquire an original flow data set and an original pressure data set of a pipeline node in a water supply network, perform exception processing on the original flow data set and the original pressure data set to obtain a standby flow data set and a standby pressure data set, wherein the standby flow data set includes a plurality of standby flow data, and the standby pressure data set includes a plurality of standby pressure data;

[0008] Obtaining predicted flow data through a flow prediction model, and determining whether there is a large amount of leakage at the pipeline node based on the real-time flow data and the predicted flow data;

[0009] performing equalization processing on the standby pressure data set to obtain an updated pressure data set, the updated pressure data set including a plurality of updated pressure data, combining a plurality of pipeline nodes into a plurality of node pairs, obtaining fluctuation correlations of the node pairs, and determining whether the node pairs are abnormal pairs based on the fluctuation correlations;

[0010] Based on the pipeline nodes in the abnormal pairs, several nodes to be identified are selected from all the pipeline nodes, the node pairs corresponding to the nodes to be identified are all selected as reference pairs, and the fluctuation correlation corresponding to the reference pairs is selected as the reference correlation. The predicted correlation of the reference pairs is obtained based on the fluctuation prediction model, and the residual value corresponding to the node to be identified is obtained based on the reference correlation and the predicted correlation. The leakage node is selected from the several nodes to be identified through the residual value to complete a small amount of leakage detection.

[0011] Furthermore, the original flow data set includes a plurality of flow data in a continuous time frame, and the original pressure data set includes a plurality of pressure data in a continuous time frame. The step of performing exception processing on the original flow data set and the original pressure data set to obtain a standby flow data set and a standby pressure data set, wherein the standby flow data set includes a plurality of standby flow data and the standby pressure data set includes a plurality of standby pressure data, comprises:

[0012] Obtaining a flow average of a plurality of flow data, and obtaining a pressure average of a plurality of pressure data, respectively obtaining a flow calibration value and a pressure calibration value based on the flow average and the pressure average, obtaining a flow threshold range through the flow average and the flow calibration value, and obtaining a pressure threshold range through the pressure average and the pressure calibration value;

[0013] Comparing a plurality of the flow data with the flow threshold range respectively, selecting the flow data outside the flow threshold range as abnormal flow data, selecting the flow data within the flow threshold range as retained flow data, eliminating the abnormal flow data, and combining the plurality of the retained flow data into a retained flow data set;

[0014] comparing the plurality of pressure data with the pressure threshold range respectively, selecting the pressure data outside the pressure threshold range as abnormal pressure data, selecting the pressure data within the pressure threshold range as retained pressure data, eliminating the abnormal pressure data, and combining the plurality of retained pressure data into a retained pressure data set;

[0015] determining whether there is a flow missing area in the reserved flow data set based on a time frame; if there is a flow missing area in the reserved flow data set, generating flow filling data based on the reserved flow data adjacent to the flow missing area, filling the flow missing area with the flow filling data, and selecting both the reserved flow data and the flow filling data as standby flow data to form a standby flow data set;

[0016] Based on the time frame, it is determined whether there is a pressure missing area in the retained pressure data set. If there is a pressure missing area in the retained pressure data set, pressure filling data is generated based on the retained pressure data adjacent to the pressure missing area, and the pressure missing area is filled with the pressure filling data. The retained pressure data and the pressure filling data are both selected as stand-by pressure data to form a stand-by pressure data set.

[0017] Furthermore, the formula for obtaining the flow calibration value is:

[0018] ,

[0019] in, represents the flow calibration value of the i-th pipeline node, Indicates the total number of timeframes, represents the flow data of the i-th pipeline node in the t-th time frame, represents the mean flow rate of the i-th pipeline node.

[0020] Furthermore, the formula for obtaining the updated pressure data is:

[0021] ,

[0022] in, represents the updated pressure data of the j-th pipeline node in the t-th time frame, represents the standby pressure data of the jth pipeline node in the tth time frame, represents the mean pressure of the jth pipeline node, Indicates the pressure calibration value of the j-th pipeline node.

[0023] Furthermore, the step of obtaining the fluctuation correlation of the node pair and determining whether the node pair is an abnormal pair according to the fluctuation correlation includes:

[0024] Segmenting the updated pressure data into a plurality of window data groups based on a time window, and obtaining a window average pressure of the window data groups;

[0025] Acquire a plurality of fluctuation correlations corresponding to the node pairs through the updated pressure data and the window average pressure;

[0026] Obtain a fluctuation correlation difference between adjacent fluctuation correlations, compare the fluctuation correlation difference with a fluctuation threshold, and if the fluctuation correlation difference is greater than the fluctuation threshold, determine that the node pair is an abnormal pair.

[0027] Furthermore, the formula for obtaining the fluctuation correlation is:

[0028] ,

[0029] in, It represents the fluctuation correlation degree in the mth time window when the jth pipeline node and the kth pipeline node are a node pair. represents the length of the mth time window, represents the qth time frame in the mth time window, represents the updated pressure data of the jth pipeline node in the qth time frame in the mth time window, represents the window average pressure of the jth pipeline node in the mth time window, represents the updated pressure data of the kth pipeline node in the qth time frame in the mth time window, Represents the window average pressure of the kth pipeline node in the mth time window.

[0030] Furthermore, the step of selecting a plurality of nodes to be identified from all the pipeline nodes based on the pipeline nodes in the abnormal pair includes:

[0031] Selecting both pipeline nodes in the abnormal pair as abnormal nodes, and selecting both node pairs with the abnormal nodes as standby pairs;

[0032] The pipeline nodes in the abnormal pair and the standby pair are all selected as nodes to be identified.

[0033] Furthermore, the step of obtaining the residual value corresponding to the node to be identified based on the reference association degree and the predicted association degree includes:

[0034] Obtaining the correlation residual of the reference correlation degree and the predicted correlation degree in the same time window;

[0035] superimposing a plurality of the associated residuals into a sub-residual corresponding to the reference pair;

[0036] A plurality of the sub-residuals are superimposed to form a residual value corresponding to the node to be identified.

[0037] Furthermore, the step of selecting a leaking node from the plurality of nodes to be identified using the residual value includes:

[0038] Obtaining residual calibration values through a plurality of the residual values, and respectively obtaining calibration differences between the residual values and the residual calibration values;

[0039] The calibration difference is compared with a residual threshold, and a node to be identified corresponding to a calibration difference greater than the residual threshold is selected as a leakage node.

[0040] In a second aspect, an embodiment of the present application provides a water supply network leakage detection system, which is applied to the water supply network leakage detection method as described in the first aspect above, and the system includes:

[0041] an acquisition module, configured to obtain an original flow data set and an original pressure data set of a pipeline node in a water supply network, and perform exception processing on the original flow data set and the original pressure data set to obtain a standby flow data set and a standby pressure data set, wherein the standby flow data set includes a plurality of standby flow data, and the standby pressure data set includes a plurality of standby pressure data;

[0042] A first detection module is configured to obtain predicted flow data through a flow prediction model, and determine whether there is a large amount of leakage at the pipeline node based on the real-time flow data and the predicted flow data;

[0043] an identification module, configured to perform equalization processing on the standby pressure data set to obtain an updated pressure data set, the updated pressure data set including a plurality of updated pressure data, grouping a plurality of pipeline nodes into a plurality of node pairs, obtaining a fluctuation correlation degree of the node pairs, and determining whether the node pairs are abnormal pairs based on the fluctuation correlation degree;

[0044] The second detection module is used to select several nodes to be identified from all the pipeline nodes based on the pipeline nodes in the abnormal pairs, select all node pairs corresponding to the nodes to be identified as reference pairs, and select the fluctuation correlation corresponding to the reference pairs as reference correlation, obtain the predicted correlation of the reference pairs based on the fluctuation prediction model, obtain the residual value corresponding to the node to be identified based on the reference correlation and the predicted correlation, and select leakage nodes from several nodes to be identified through the residual value to complete a small amount of leakage detection.

[0045] In a third aspect, an embodiment of the present application provides a computer comprising a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the water supply network leakage detection method as described in the first aspect above is implemented.

[0046] In a fourth aspect, an embodiment of the present application provides a storage medium on which a computer program is stored. When the computer program is executed by a processor, the water supply network leakage detection method as described in the first aspect above is implemented.

[0047] Compared with the prior art, the beneficial effects of the present invention are: after obtaining the original flow data set and the original pressure data set, by performing exception processing on both, the erroneous collection and missed collection caused by errors in the collection sensors during the data collection process can be avoided, the accuracy of the data can be improved, and an accurate data basis can be provided for subsequent leakage detection; the difference between the actual flow data and the predicted flow data can be quickly identified for pipeline nodes with large amounts of leakage; by setting the node pairs and introducing the fluctuation correlation, small amounts of leakage can be identified by the pressure synergy of the two nodes within the time window. When the influence of small amounts of leakage on the changes in pressure or flow is small, the detection of small amounts of leakage can still be accurately completed by the sudden change of the hydraulic relationship between the nodes, while avoiding the influence of water fluctuations or noise on the detection of small amounts of leakage; by performing the equalization processing, the comparability of data between different nodes is ensured; large amounts of leakage are identified by flow, and small amounts of leakage are identified by pressure. Compared with traditional manual detection, the detection efficiency is improved while the detection accuracy is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 Flowchart of the water supply network leakage detection method according to the first embodiment of the present invention;

[0049] Figure 2 This is a structural block diagram of a water supply network leakage detection system in a second embodiment of the present invention;

[0050] The following specific embodiments will further illustrate the present invention in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION

[0051] To facilitate understanding of the present invention, the present invention will be described more fully below with reference to the accompanying drawings. The drawings illustrate several embodiments of the present invention. However, the present invention may be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and comprehensive understanding of the present invention.

[0052] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be an intermediate element. When an element is referred to as being "connected to" another element, it may be directly connected to the other element or there may be an intermediate element. The terms "vertical," "horizontal," "left," "right," and similar expressions used herein are for illustrative purposes only.

[0053] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one skilled in the art to which this invention pertains. The terms used in this specification of the present invention are for the purpose of describing specific embodiments only and are not intended to limit the present invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0054] See also Figure 1 The first embodiment of the present invention provides a method for detecting water pipe network leakage, comprising the following steps:

[0055] S10: obtaining an original flow data set and an original pressure data set of a pipeline node in the water supply network, performing exception processing on the original flow data set and the original pressure data set to obtain a standby flow data set and a standby pressure data set, wherein the standby flow data set includes a plurality of standby flow data, and the standby pressure data set includes a plurality of standby pressure data;

[0056] It is understandable that a flow sensor and a pressure sensor are provided on the pipeline node to obtain the raw flow data set and the raw pressure data set. The raw flow data set includes a plurality of flow data in a continuous time frame, and the raw pressure data set includes a plurality of pressure data in a continuous time frame.

[0057] The step S10 includes:

[0058] S110: Obtaining a flow average value of a plurality of flow data and a pressure average value of a plurality of pressure data, respectively obtaining a flow calibration value and a pressure calibration value based on the flow average value and the pressure average value, obtaining a flow threshold range through the flow average value and the flow calibration value, and obtaining a pressure threshold range through the pressure average value and the pressure calibration value;

[0059] The formula for obtaining the flow calibration value is:

[0060] ,

[0061] in, represents the flow calibration value of the i-th pipeline node, Indicates the total number of timeframes, represents the flow data of the i-th pipeline node in the t-th time frame, The method for obtaining the pressure calibration value is the same as that for obtaining the flow calibration value, and will not be described in detail here.

[0062] S120: Comparing the plurality of flow data with the flow threshold range respectively, selecting the flow data outside the flow threshold range as abnormal flow data, selecting the flow data within the flow threshold range as retained flow data, removing the abnormal flow data, and combining the plurality of retained flow data into a retained flow data set;

[0063] The first endpoint value=the flow average value-3*the flow calibration value, the second endpoint value=the flow average value+3*the flow calibration value, and the first endpoint value and the second endpoint value constitute the flow threshold range.

[0064] S130: Comparing the plurality of pressure data with the pressure threshold range respectively, selecting the pressure data outside the pressure threshold range as abnormal pressure data, selecting the pressure data within the pressure threshold range as retained pressure data, eliminating the abnormal pressure data, and combining the plurality of retained pressure data into a retained pressure data set;

[0065] The pressure threshold range is obtained in the same manner as the flow threshold range, and will not be further described here.

[0066] S140: Determine whether there is a flow missing area in the reserved flow data set based on the time frame; if there is a flow missing area in the reserved flow data set, generate flow filling data based on the reserved flow data adjacent to the flow missing area, fill the flow missing area with the flow filling data, and select both the reserved flow data and the flow filling data as standby flow data to form a standby flow data set;

[0067] In this embodiment, the average of the retained flow data adjacent to the flow missing area is the flow filling data.

[0068] S150: Determine whether there is a pressure missing area in the retained pressure data set based on the time frame; if there is a pressure missing area in the retained pressure data set, generate pressure filling data based on the retained pressure data adjacent to the pressure missing area, fill the pressure missing area with the pressure filling data, and select both the retained pressure data and the pressure filling data as stand-by pressure data to form a stand-by pressure data set.

[0069] S20: Obtaining predicted flow data through a flow prediction model, and determining whether there is a large amount of leakage at the pipeline node based on the real-time flow data and the predicted flow data;

[0070] It should be noted that the traffic prediction model is a trained traffic prediction neural network model, and its training process is: obtain the past normal traffic data set corresponding to the pipeline node, separate the past normal traffic data set into an input data set and an output data set, use the input data set as the input value of the traffic prediction neural network model, obtain the training predicted traffic data through the traffic prediction neural network model, construct a loss function based on the training predicted traffic data and the output data set, and then complete the training of the traffic prediction neural network model to achieve the acquisition of predicted traffic data. When there is a large difference between the real-time traffic data and the predicted traffic data, it can be determined that there is a large amount of leakage in the pipeline node, resulting in a change in traffic. There are many applications of neural network models for data prediction, which will not be repeated here. The standby traffic data set is used as the input value of the traffic prediction model to obtain predicted traffic data.

[0071] S30: performing equalization processing on the standby pressure data set to obtain an updated pressure data set, wherein the updated pressure data set includes a plurality of updated pressure data, combining a plurality of pipeline nodes into a plurality of node pairs, obtaining fluctuation correlations of the node pairs, and determining whether the node pairs are abnormal pairs based on the fluctuation correlations;

[0072] The formula for obtaining the updated pressure data is:

[0073] ,

[0074] in, represents the updated pressure data of the j-th pipeline node in the t-th time frame, represents the standby pressure data of the jth pipeline node in the tth time frame, represents the mean pressure of the jth pipeline node, represents the pressure calibration value of the jth pipeline node. Assuming there are four nodes A, B, C, and D, there are node pairs (A, B), (A, C), (A, D), (B, C), (B, D), and (C, D).

[0075] The step S30 includes:

[0076] S310: Segmenting the updated pressure data into a plurality of window data groups based on a time window, and obtaining the window average pressure of the window data groups;

[0077] Assuming that the updated pressure data set includes the updated pressure data in 24 time frames, that is, the updated pressure data is collected once every hour, and the length of the time window is 3 hours, then 8 window data groups are generated. The three updated pressure data in the window data group are averaged to obtain the window average pressure.

[0078] S320: Acquire a plurality of fluctuation correlations corresponding to the node pair through the updated pressure data and the window average pressure;

[0079] The formula for obtaining the fluctuation correlation is:

[0080] ,

[0081] in, It represents the fluctuation correlation degree in the mth time window when the jth pipeline node and the kth pipeline node are a node pair. represents the length of the mth time window, represents the qth time frame in the mth time window, represents the updated pressure data of the jth pipeline node in the qth time frame in the mth time window, represents the window average pressure of the jth pipeline node in the mth time window, represents the updated pressure data of the kth pipeline node in the qth time frame in the mth time window, represents the window average pressure of the kth pipeline node in the mth time window. If there are 8 time windows, there are 8 corresponding fluctuation correlations.

[0082] S330: Obtaining a fluctuation correlation difference between adjacent fluctuation correlations, comparing the fluctuation correlation difference with a fluctuation threshold, and determining that the node pair is an abnormal pair if the fluctuation correlation difference is greater than the fluctuation threshold;

[0083] The significant change in the fluctuation correlation difference indicates that the synergy between the two nodes in the time window has changed, indicating that there may be a small amount of leakage between the two corresponding pipeline nodes.

[0084] S40: Based on the pipeline nodes in the abnormal pairs, a plurality of nodes to be identified are selected from all the pipeline nodes, node pairs corresponding to the nodes to be identified are selected as reference pairs, and fluctuation correlations corresponding to the reference pairs are selected as reference correlations. Based on a fluctuation prediction model, predicted correlations of the reference pairs are obtained, and residual values corresponding to the nodes to be identified are obtained based on the reference correlations and the predicted correlations. Leakage nodes are selected from the plurality of nodes to be identified using the residual values, thereby completing a small amount of leakage detection.

[0085] The step S40 includes:

[0086] S410: Selecting both pipeline nodes in the abnormal pair as abnormal nodes, and selecting both node pairs containing the abnormal nodes as standby pairs;

[0087] Assuming that the node pair (A, B) is an abnormal pair, then A and B are both selected as abnormal nodes, and the node pairs (A, B), (A, C), (A, D), (B, C), and (B, D) are all standby pairs.

[0088] S420: Selecting the pipeline nodes in the abnormal pair and the standby pair as nodes to be identified;

[0089] Furthermore, nodes A, B, C, and D are all nodes to be identified. It should be noted that several of the nodes to be identified include the abnormal node, and only the names are different.

[0090] Similarly, the reference pairs corresponding to node A are (A, B), (A, C), and (A, D). The fluctuation prediction model and the flow prediction model are predictive neural network models of the same nature and are not further described here. The fluctuation correlation of the preceding time window is used as input to the fluctuation prediction model to obtain the predicted correlation. By selecting the node to be identified, all pipeline nodes related to the abnormal node are included in the detection scope to avoid missed detections.

[0091] S430: Obtaining the correlation residual of the reference correlation and the predicted correlation in the same time window;

[0092] The difference between the reference correlation degree and the predicted correlation degree is the correlation residual.

[0093] S440: superimposing a plurality of the associated residuals into a sub-residual corresponding to the reference pair;

[0094] It can be understood that, since there are several time windows, there are several associated residuals, which are superimposed to form the sub-residuals.

[0095] S450: Superimposing a plurality of the sub-residuals to form a residual value corresponding to the node to be identified;

[0096] Taking node A as an example, there are 3 reference pairs, and thus there are 3 sub-residuals. The 3 sub-residuals are superimposed to form the residual value corresponding to node A.

[0097] S460: Obtain residual calibration values through a plurality of the residual values, and respectively obtain calibration differences between the residual values and the residual calibration values;

[0098] After obtaining the residual value of the node to be identified, the average of several residual values is the residual calibration value.

[0099] S470: Compare the calibration difference with a residual threshold, and select the to-be-identified node corresponding to the calibration difference greater than the residual threshold as a leakage node.

[0100] Understandably, this leakage node is a pipeline node experiencing a small amount of leakage. After obtaining the predicted correlation, it is compared with the reference correlation to generate the residual value, which is then superimposed. Based on the coordinated fluctuations between pipeline nodes, the abnormal signal is amplified, and small coordinated anomalies are captured to accurately locate the leakage node.

[0101] After obtaining the original flow data set and the original pressure data set, by performing exception processing on both, the erroneous collection and missed collection caused by errors in the collection sensors during the data collection process can be avoided, the accuracy of the data can be improved, and an accurate data basis can be provided for subsequent leakage detection; the difference between the actual flow data and the predicted flow data can be quickly identified as pipeline nodes with a large number of leaks; by setting the node pairs and introducing the fluctuation correlation, a small amount of leakage can be identified by the pressure synergy of the two nodes within the time window. When a small amount of leakage has a small impact on the change of pressure or flow, the detection of a small amount of leakage can still be accurately completed by the sudden change of the hydraulic relationship between the nodes, while avoiding the influence of water fluctuations or noise on the detection of a small amount of leakage; by performing the equalization processing, the comparability of data between different nodes is ensured; large amounts of leakage are identified by flow, and small amounts of leakage are identified by pressure. Compared with traditional manual detection, the detection efficiency is improved while the detection accuracy is improved.

[0102] See also Figure 2 The second embodiment of the present invention provides a water supply network leakage detection system, which is applied to the water supply network leakage detection method described in the above embodiment. The details that have been explained will not be repeated here. As used below, the terms "module", "unit", "sub-unit", etc. can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and conceivable.

[0103] The system comprises:

[0104] The acquisition module 10 is used to obtain an original flow data set and an original pressure data set of a pipeline node in the water supply network, and perform exception processing on the original flow data set and the original pressure data set to obtain a standby flow data set and a standby pressure data set, wherein the standby flow data set includes a plurality of standby flow data and the standby pressure data set includes a plurality of standby pressure data;

[0105] The acquisition module 10 includes:

[0106] The first unit is configured to obtain a flow average value of a plurality of flow data and a pressure average value of a plurality of pressure data, obtain a flow calibration value and a pressure calibration value based on the flow average value and the pressure average value, respectively, obtain a flow threshold range through the flow average value and the flow calibration value, and obtain a pressure threshold range through the pressure average value and the pressure calibration value;

[0107] The second unit is configured to compare the plurality of flow data with the flow threshold range, select the flow data outside the flow threshold range as abnormal flow data, select the flow data within the flow threshold range as retained flow data, remove the abnormal flow data, and combine the plurality of retained flow data into a retained flow data set;

[0108] a third unit, configured to compare the plurality of pressure data with the pressure threshold range, select the pressure data outside the pressure threshold range as abnormal pressure data, select the pressure data within the pressure threshold range as retained pressure data, remove the abnormal pressure data, and combine the plurality of retained pressure data into a retained pressure data set;

[0109] a fourth unit configured to determine, based on a time frame, whether a flow missing area exists in the reserved flow data set; if a flow missing area exists in the reserved flow data set, generate flow filling data based on the reserved flow data adjacent to the flow missing area, fill the flow missing area with the flow filling data, and select both the reserved flow data and the flow filling data as standby flow data to form a standby flow data set;

[0110] a fifth unit configured to determine, based on a time frame, whether a pressure-missing region exists in the retained pressure dataset; if a pressure-missing region exists in the retained pressure dataset, generate pressure-filling data based on retained pressure data adjacent to the pressure-missing region, fill the pressure-missing region with the pressure-filling data, and select both the retained pressure data and the pressure-filling data as standby pressure data to form a standby pressure dataset;

[0111] A first detection module 20 is configured to obtain predicted flow data through a flow prediction model, and determine whether there is a large amount of leakage at the pipeline node based on the real-time flow data and the predicted flow data;

[0112] an identification module 30 configured to perform equalization processing on the standby pressure data set to obtain an updated pressure data set, wherein the updated pressure data set includes a plurality of updated pressure data, grouping a plurality of pipeline nodes into a plurality of node pairs, obtaining a fluctuation correlation degree of the node pairs, and determining whether the node pairs are abnormal pairs based on the fluctuation correlation degree;

[0113] The identification module 30 includes:

[0114] a sixth unit, configured to segment the plurality of updated pressure data into a plurality of window data groups based on a time window, and obtain a window average pressure of the window data groups;

[0115] A seventh unit is configured to obtain a plurality of fluctuation correlations corresponding to the node pairs through the updated pressure data and the window average pressure;

[0116] an eighth unit, configured to obtain a fluctuation correlation difference between adjacent fluctuation correlation degrees, compare the fluctuation correlation difference with a fluctuation threshold, and determine that the node pair is an abnormal pair if the fluctuation correlation difference is greater than the fluctuation threshold;

[0117] A second detection module 40 is configured to select a plurality of nodes to be identified from all the pipeline nodes based on the pipeline nodes in the abnormal pairs, select the node pairs corresponding to the nodes to be identified as reference pairs, select the fluctuation correlations corresponding to the reference pairs as reference correlations, obtain predicted correlations of the reference pairs based on a fluctuation prediction model, obtain residual values corresponding to the nodes to be identified based on the reference correlations and the predicted correlations, and select leakage nodes from the plurality of nodes to be identified using the residual values to complete small-scale leakage detection;

[0118] The second detection module 40 includes:

[0119] A ninth unit is configured to select both pipeline nodes in the abnormal pair as abnormal nodes, and select both node pairs containing the abnormal nodes as standby pairs;

[0120] a tenth unit, configured to select the pipeline nodes in the abnormal pair and the standby pair as nodes to be identified;

[0121] The eleventh unit is used to obtain the correlation residual of the reference correlation degree and the predicted correlation degree in the same time window;

[0122] a twelfth unit, configured to superimpose a plurality of the associated residuals into a sub-residual corresponding to the reference pair;

[0123] A thirteenth unit is configured to superimpose a plurality of the sub-residuals into a residual value corresponding to the node to be identified;

[0124] A fourteenth unit is configured to obtain residual calibration values through a plurality of the residual values, and respectively obtain calibration differences between the residual values and the residual calibration values;

[0125] The fifteenth unit is configured to compare the calibration difference with a residual threshold value, and select a node to be identified corresponding to a calibration difference value greater than the residual threshold value as a leakage node.

[0126] The present invention also provides a computer, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the water supply network leakage detection method as described in the above technical solution is implemented.

[0127] The present invention also provides a storage medium on which a computer program is stored. When the computer program is executed by a processor, the water supply network leakage detection method as described in the above technical solution is implemented.

[0128] Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "examples," "specific examples," or "some examples" means that a specific feature, structure, material, or characteristic described in conjunction with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0129] The above-described embodiments merely illustrate several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art would be able to make numerous variations and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

Claims

1. A water supply network leakage detection method, characterized in that: The following steps are involved: Acquire an original flow data set and an original pressure data set of a pipeline node in a water supply network, perform exception processing on the original flow data set and the original pressure data set to obtain a standby flow data set and a standby pressure data set, wherein the standby flow data set includes a plurality of standby flow data, and the standby pressure data set includes a plurality of standby pressure data; Obtaining predicted flow data through a flow prediction model, and determining whether there is a large amount of leakage at the pipeline node based on the real-time flow data and the predicted flow data; performing equalization processing on the standby pressure data set to obtain an updated pressure data set, the updated pressure data set including a plurality of updated pressure data, combining a plurality of pipeline nodes into a plurality of node pairs, obtaining fluctuation correlations of the node pairs, and determining whether the node pairs are abnormal pairs based on the fluctuation correlations; The step of obtaining the fluctuation correlation degree of the node pair and determining whether the node pair is an abnormal pair according to the fluctuation correlation degree includes: Segmenting the updated pressure data into a plurality of window data groups based on a time window, and obtaining a window average pressure of the window data groups; Acquire a plurality of fluctuation correlations corresponding to the node pairs through the updated pressure data and the window average pressure; The formula for obtaining the fluctuation correlation is: ， in, It represents the fluctuation correlation degree in the mth time window when the jth pipeline node and the kth pipeline node are a node pair. represents the length of the mth time window, represents the qth time frame in the mth time window, represents the updated pressure data of the jth pipeline node in the qth time frame in the mth time window, represents the window average pressure of the jth pipeline node in the mth time window, represents the updated pressure data of the kth pipeline node in the qth time frame in the mth time window, represents the window average pressure of the kth pipeline node in the mth time window; Obtaining a fluctuation correlation difference between adjacent fluctuation correlation degrees, comparing the fluctuation correlation difference with a fluctuation threshold, and determining that the node pair is an abnormal pair if the fluctuation correlation difference is greater than the fluctuation threshold; Based on the pipeline nodes in the abnormal pairs, several nodes to be identified are selected from all the pipeline nodes, the node pairs corresponding to the nodes to be identified are all selected as reference pairs, and the fluctuation correlation corresponding to the reference pairs is selected as the reference correlation. The predicted correlation of the reference pairs is obtained based on the fluctuation prediction model, and the residual value corresponding to the node to be identified is obtained based on the reference correlation and the predicted correlation. The leakage node is selected from the several nodes to be identified through the residual value to complete a small amount of leakage detection.

2. The water supply network leakage detection method according to claim 1, characterized in that: The original flow data set includes a plurality of flow data in a continuous time frame, and the original pressure data set includes a plurality of pressure data in a continuous time frame. The step of performing exception processing on the original flow data set and the original pressure data set to obtain a standby flow data set and a standby pressure data set, wherein the standby flow data set includes a plurality of standby flow data and the standby pressure data set includes a plurality of standby pressure data, comprises: Obtaining a flow average of a plurality of flow data, and obtaining a pressure average of a plurality of pressure data, respectively obtaining a flow calibration value and a pressure calibration value based on the flow average and the pressure average, obtaining a flow threshold range through the flow average and the flow calibration value, and obtaining a pressure threshold range through the pressure average and the pressure calibration value; Comparing a plurality of the flow data with the flow threshold range respectively, selecting the flow data outside the flow threshold range as abnormal flow data, selecting the flow data within the flow threshold range as retained flow data, eliminating the abnormal flow data, and combining the plurality of the retained flow data into a retained flow data set; comparing the plurality of pressure data with the pressure threshold range respectively, selecting the pressure data outside the pressure threshold range as abnormal pressure data, selecting the pressure data within the pressure threshold range as retained pressure data, eliminating the abnormal pressure data, and combining the plurality of retained pressure data into a retained pressure data set; determining whether there is a flow missing area in the reserved flow data set based on a time frame; if there is a flow missing area in the reserved flow data set, generating flow filling data based on the reserved flow data adjacent to the flow missing area, filling the flow missing area with the flow filling data, and selecting both the reserved flow data and the flow filling data as standby flow data to form a standby flow data set; Based on the time frame, it is determined whether there is a pressure missing area in the retained pressure data set. If there is a pressure missing area in the retained pressure data set, pressure filling data is generated based on the retained pressure data adjacent to the pressure missing area, and the pressure missing area is filled with the pressure filling data. The retained pressure data and the pressure filling data are both selected as stand-by pressure data to form a stand-by pressure data set.

3. The water supply network leakage detection method according to claim 2, characterized in that: The formula for obtaining the flow calibration value is: ， in, represents the flow calibration value of the i-th pipeline node, Indicates the total number of timeframes, represents the flow data of the i-th pipeline node in the t-th time frame, represents the mean flow rate of the i-th pipeline node.

4. The water supply network leakage detection method according to claim 1, characterized in that: The formula for obtaining the updated pressure data is: ， in, represents the updated pressure data of the j-th pipeline node in the t-th time frame, represents the standby pressure data of the jth pipeline node in the tth time frame, represents the mean pressure of the jth pipeline node, Indicates the pressure calibration value of the j-th pipeline node.

5. The water supply network leakage detection method according to claim 1, characterized in that: The step of selecting a plurality of nodes to be identified from all the pipeline nodes based on the pipeline nodes in the abnormal pair includes: Selecting both pipeline nodes in the abnormal pair as abnormal nodes, and selecting both node pairs with the abnormal nodes as standby pairs; The pipeline nodes in the abnormal pair and the standby pair are all selected as nodes to be identified.

6. The water supply network leakage detection method according to claim 1, characterized in that: The step of obtaining the residual value corresponding to the node to be identified based on the reference association degree and the predicted association degree includes: Obtaining the correlation residual of the reference correlation degree and the predicted correlation degree in the same time window; superimposing a plurality of the associated residuals into a sub-residual corresponding to the reference pair; A plurality of the sub-residuals are superimposed to form a residual value corresponding to the node to be identified.

7. The water supply network leakage detection method according to claim 1, characterized in that: The step of selecting a leakage node from the plurality of nodes to be identified by using the residual value includes: Obtaining residual calibration values through a plurality of the residual values, and respectively obtaining calibration differences between the residual values and the residual calibration values; The calibration difference is compared with a residual threshold, and a node to be identified corresponding to a calibration difference greater than the residual threshold is selected as a leakage node.

8. A water supply network leakage detection system, applied to the water supply network leakage detection method according to any one of claims 1 to 7, characterized in that: The system comprises: an acquisition module, configured to obtain an original flow data set and an original pressure data set of a pipeline node in a water supply network, and perform exception processing on the original flow data set and the original pressure data set to obtain a standby flow data set and a standby pressure data set, wherein the standby flow data set includes a plurality of standby flow data, and the standby pressure data set includes a plurality of standby pressure data; A first detection module is configured to obtain predicted flow data through a flow prediction model, and determine whether there is a large amount of leakage at the pipeline node based on the real-time flow data and the predicted flow data; an identification module, configured to perform equalization processing on the standby pressure data set to obtain an updated pressure data set, the updated pressure data set including a plurality of updated pressure data, grouping a plurality of pipeline nodes into a plurality of node pairs, obtaining a fluctuation correlation degree of the node pairs, and determining whether the node pairs are abnormal pairs based on the fluctuation correlation degree; The identification module includes: a sixth unit, configured to segment the plurality of updated pressure data into a plurality of window data groups based on a time window, and obtain a window average pressure of the window data groups; A seventh unit is configured to obtain a plurality of fluctuation correlations corresponding to the node pairs through the updated pressure data and the window average pressure; The formula for obtaining the fluctuation correlation is: ， in, It represents the fluctuation correlation degree in the mth time window when the jth pipeline node and the kth pipeline node are a node pair. represents the length of the mth time window, represents the qth time frame in the mth time window, represents the updated pressure data of the jth pipeline node in the qth time frame in the mth time window, represents the window average pressure of the jth pipeline node in the mth time window, represents the updated pressure data of the kth pipeline node in the qth time frame in the mth time window, represents the window average pressure of the kth pipeline node in the mth time window; an eighth unit, configured to obtain a fluctuation correlation difference between adjacent fluctuation correlation degrees, compare the fluctuation correlation difference with a fluctuation threshold, and determine that the node pair is an abnormal pair if the fluctuation correlation difference is greater than the fluctuation threshold; The second detection module is used to select several nodes to be identified from all the pipeline nodes based on the pipeline nodes in the abnormal pairs, select all node pairs corresponding to the nodes to be identified as reference pairs, and select the fluctuation correlation corresponding to the reference pairs as reference correlation, obtain the predicted correlation of the reference pairs based on the fluctuation prediction model, obtain the residual value corresponding to the node to be identified based on the reference correlation and the predicted correlation, and select leakage nodes from several nodes to be identified through the residual value to complete a small amount of leakage detection.

Images