Water supply pipe network partition leakage early warning algorithm and system based on large user water volume
By collecting and analyzing large user usage data in the water supply pipeline network, predicting and supplementing missing data, and combining real-time usage detection, an efficient early warning of DMA partition leakage is achieved, and the lack of sensitivity of data loss and early warning models in traditional methods is solved. The problem improves the accuracy and reliability of leakage analysis.
Patent Information
- Application Number
- CN202411569844.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-06
- Publication Date
- 2024-12-06
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The traditional water supply pipeline leakage detection method has problems such as missing data and insufficient sensitivity of early warning model, especially in the changes in water consumption of large users, which has led to the improvement of the accuracy and effectiveness of leakage analysis.
By collecting and analyzing the usage historical data of large users of DMA partitions, using weighted average and Euclidean distance algorithms to predict missing data, and combining real-time usage data for abnormal detection, judging suspected leaks, and recursively analyzing sub-DMA partitions to locate leaks Loss area.
It improves the completeness of data and the accuracy of early warning analysis, can effectively process missing data, improves the sensitivity and accuracy of early leakage warning, makes full use of large user water volume data, and enhances the reliability of leakage analysis.
Smart Images

Figure CN119084847A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of water supply network leakage detection, and more specifically, to a water supply network zoning leakage early warning algorithm and system based on large user water volume. Background Art
[0002] With the continuous advancement of urbanization, the scale and complexity of urban water supply networks are increasing. The leakage problem of water supply networks has become one of the major challenges facing the water industry. Leakage not only wastes precious water resources, but also may lead to a series of problems such as water pollution and road collapse, posing hidden dangers to urban water supply safety and residents' lives.
[0003] In order to effectively control the leakage of water supply network, domestic and foreign researchers and water workers have carried out a lot of research and practice. At present, common leakage detection methods mainly include zone metering, minimum night flow analysis, acoustic leak detection, etc. Among them, DMA (District Metering Area) zone management is a widely used technical means. By dividing the water supply network into several independent districts and installing flow meters on the inlet and outlet pipes of each district, zone metering and monitoring can be achieved, providing data support for leakage analysis.
[0004] However, the traditional DMA zoning leakage analysis method still has some limitations. First, the water consumption data within the zone is usually missing or incomplete, especially for some newly built or renovated pipe network areas, where historical data accumulation is insufficient, which brings difficulties to leakage analysis. Secondly, most of the existing leakage warning models are based on fixed thresholds or empirical formulas, lack of consideration of the changing trend of users' water use behavior, and the sensitivity and accuracy of the warning need to be improved. In addition, for large users within the zone, such as industrial enterprises, large public buildings, etc., their water consumption changes have a significant impact on the total water consumption of the zone, but the existing methods do not make sufficient use of the water volume data of large users and fail to fully explore their role in leakage analysis.
[0005] In view of the above problems, there is an urgent need for a leakage warning method that can comprehensively utilize various types of water consumption data in DMA partitions, especially large-user water consumption data. This method should be able to effectively handle missing data and accurately predict and supplement complete water consumption information. Summary of the invention
[0006] In order to overcome the above-mentioned defects of the prior art, the present invention provides a water supply network zoning leakage warning algorithm based on large user water volume.
[0007] To achieve the above object, the present invention provides the following technical solutions: The water supply network zoning leakage warning algorithm based on large user water volume includes: S10 collects historical usage data of large users in the DMA partition, and predicts missing usage data of large users in the DMA partition based on the historical usage data of large users in the DMA partition; S20 obtains the real-time DMA partition daily usage, real-time DMA partition night usage, and real-time DMA partition large user usage corresponding to the real-time water supply network DMA partition; S30 The real-time DMA partition night usage has an abnormal year-on-year increase. The DMA partition large user usage is calculated. If the overall growth value of large user usage is less than 60% of the real-time DMA partition daily usage growth value, suspected leakage occurs; if the real-time DMA partition night usage has an abnormal year-on-year increase, the DMA partition large user usage is calculated. If the overall growth value of large user usage is less than 60% of the real-time DMA partition daily usage growth value, suspected leakage occurs.
[0008] S40 repeats steps S10-S30. If a DMA partition is determined to be suspected of leakage, continue to analyze its next-level sub-DMA partition and traverse to obtain the final leakage area.
[0009] Preferably, the method for predicting missing data of large user usage in a DMA partition based on historical data of large user usage in the DMA partition includes: If the historical data of the usage of large users in the DMA partition is greater than or equal to T years, the weighted average of the historical data of the usage of large users in the DMA partition in the same period of T years is used as the simulated usage, and adjustments are made to obtain the missing data of the usage of large users in the DMA partition; If the historical data of large-user usage in a DMA partition is less than T years, the Euclidean distance multiplication is used to find the large-user usage of similar DMA partitions, and the missing values of large-user usage in the DMA partition are simulated based on the large-user usage data of similar DMA partitions, where T is a natural number greater than zero.
[0010] Preferably, the method for predicting missing data of large user usage in a DMA partition based on historical data of large user usage in the DMA partition includes: S11 determines the predicted usage date of the DMA partition's largest user, and takes the historical usage data of the same period N years before the usage date of the DMA partition's largest user as reference data; S12 performs a weighted average of the historical consumption data for these N years, with the weight using an exponential decay function. The more recent the data, the greater the weight. The weight of the i-th year is The calculation formula is: ; is the decay coefficient, which controls the decay speed of the weight, i represents the year index of the historical data, ranging from 1 to N, j is the year index of the historical data, ranging from 1 to N; S13 calculates the weighted average usage Q of the historical data: ; is the historical usage data for the same period of year i; Preferably, the method for predicting missing data of large user usage in a DMA partition based on historical data of large user usage in the DMA partition includes: S14 introduces a trend adjustment coefficient R to reflect the long-term trend of user water consumption. The calculation method of R is as follows: ;in, The average value of historical data years, Indicates the average value of historical usage data; S15 calculates the time distance of the forecast date relative to the historical data center : ; in, Indicates the central date of historical data;
[0011] S16 uses trend adjustment coefficient R and time distance , adjust the weighted average usage Q to get the final predicted usage P: ;in, is the trend adjustment intensity coefficient, and P represents the usage prediction result of large users in the DMA partition.
[0012] Preferably, the method for predicting missing data of large user usage in a DMA partition based on historical data of large user usage in the DMA partition includes: For the DMA partition large user usage to be predicted, extract the usage data of the last three months and record it as a vector ; For each candidate point (k=1, 2, ..., M), extract the usage data for the same three months, recorded as: ; For each candidate measurement point , calculate the Euclidean distance between the candidate measurement point and the large user usage of the DMA partition to be predicted : , ; where n is the number of data points for 3 months, and Respectively represent the DMA partition large user usage and candidate measurement points The usage value at the i-th data point; Among all candidate measurement points, the measurement point with the smallest Euclidean distance is selected as the most similar measurement point, which is recorded as measurement point B: , for the most similar measurement point B, extract its historical usage data for the same period of the past three years, recorded as ; Take the weighted average of the historical data of measuring point B to get the simulated usage : ;in, is the weight of the i-th year, = 1. Preferably, the water supply network partition leakage warning algorithm based on large user water volume also includes: Extract the actual usage data of measurement point A in the last 30 days, recorded as ; Calculate the average actual usage of measuring point A in the last 30 days ; Calculate recent data adjustment factors : ; The simulated amount Adjustment factor with recent data Multiply them to get the final predicted usage of measuring point A The present invention also provides the following technical solution: a water supply network partition leakage warning system based on large user water volume, comprising: A prediction module is used to collect the historical data of usage of large users in the DMA partition, and predict the missing data of usage of large users in the DMA partition based on the historical data of usage of large users in the DMA partition; A real-time data collection module is used to obtain the real-time DMA partition daily usage, real-time DMA partition night usage, and real-time DMA partition large user usage corresponding to the real-time water supply network DMA partition; The judgment module is used to calculate the usage of large users in the real-time DMA partition if there is an abnormal year-on-year increase in the nighttime usage. If the overall growth value of the usage of large users is less than 60% of the daily growth value of the real-time DMA partition, a suspected leakage occurs; if the nighttime usage of the real-time DMA partition increases abnormally year-on-year, the usage of large users in the DMA partition is calculated. If the overall growth value of the usage of large users is less than 60% of the daily growth value of the real-time DMA partition, a suspected leakage occurs.
[0013] The positioning module is used to repeat steps S10-S30. If a DMA partition is determined to be suspected of leakage, the next-level sub-DMA partition is continuously analyzed to traverse and obtain the final leakage area.
[0014] On the one hand, the present invention also provides the following technical solution: an electronic device, comprising a memory, a central processing unit, and a computer program stored in the memory and executable on the central processing unit, characterized in that when the central processing unit executes the computer program, the water supply network zoning leakage warning algorithm based on large user water volume is implemented.
[0015] On the one hand, the present invention also provides the following technical solution: a computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, and when the computer program is executed, the water supply network zoning leakage warning algorithm based on large user water volume is implemented.
[0016] The present invention can predict and fill in the missing usage data by analyzing and modeling the historical usage data of large users in the DMA partition when the data is missing. This data preprocessing method can improve the integrity and reliability of the data and provide more accurate input for subsequent leakage warning analysis.
[0017] In addition, when calculating the weighted average usage, the exponential decay weight function is used to reasonably allocate the weights of different historical data. This method can highlight the impact of recent data while taking into account the trend information of historical data, making the prediction results more accurate and timely. By introducing the trend adjustment coefficient, the long-term trend of user water consumption can be captured. Using the linear regression method, the trend adjustment coefficient is estimated based on historical data and used to adjust the weighted average usage, so that the prediction results can reflect the overall trend of water consumption and improve the rationality of the prediction. When the target user lacks sufficient historical data, the Euclidean distance algorithm is used to find users with similar characteristics among other users, and the historical data of similar users are used to fill the missing data of the target user. This method can make full use of the information of existing data and improve the reliability of missing data estimation.
[0018] In the final stage of the forecasting process, by comparing the target user’s recent actual water usage with the simulated usage, an adjustment factor is calculated and used to correct the final forecast results. This step can effectively incorporate the target user’s recent actual water usage, making the forecast results closer to the actual situation. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0020] Figure 1 It is a flow chart of the water supply network zoning leakage warning algorithm based on large user water volume in the present invention; Figure 2 It is a schematic diagram of the water supply network zoning leakage warning system based on large user water volume of the present invention; Figure 3 A schematic diagram of an electronic device provided by the present invention; Figure 4 A computer-readable storage medium is provided for the present invention. DETAILED DESCRIPTION
[0021] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. Example 1 See also Figure 1 As shown, this embodiment provides a water supply network partition leakage warning algorithm based on large user water volume, including:
[0022] S10, collecting historical usage data of large users in the DMA partition, and predicting missing usage data of large users in the DMA partition based on the historical usage data of large users in the DMA partition; In the case of missing data, by analyzing and modeling the historical usage data of large users in the DMA partition, the missing usage data can be predicted and filled in. This data preprocessing method can improve the integrity and reliability of the data and provide more accurate input for subsequent leakage warning analysis.
[0023] The process of obtaining missing data of large user usage in DMA partition is as follows: If there is T years of historical data on the usage of large users in the DMA partition, where T is a positive integer, the specific value can be selected by those skilled in the art based on experience, for example, T=3. Take the weighted average of the N years of historical data on the usage of large users in the DMA partition as the simulated usage, and then adjust it based on the latest data to obtain the missing data of the usage of large users in the DMA partition. The specific method is as follows: S11 determines the predicted usage date of the DMA partition's largest user, and takes the historical usage data of the same period N years before the usage date of the DMA partition's largest user as reference data; S12 performs weighted average of the historical usage data of these N years. The weight adopts an exponential decay function. The closer the data is to the prediction date, the greater the weight. The weight of the i-th year is The calculation formula is: , is the decay coefficient, which controls the decay speed of the weight. It can be adjusted according to the actual situation. The larger the value, the higher the weight of the recent data. i represents the year index of the historical data, and the value range is 1 to N, where i=1 represents the year closest to the forecast date, and i=N represents the year farthest. j is also the year index of the historical data, which is used in the summation operation of the denominator, and the value range is also 1 to N. Here j is a dummy variable used to calculate the normalization factor of the weight. When calculating the weighted average usage, the exponential decay weight function is used to reasonably allocate the weights of different historical data. This method can highlight the impact of recent data while taking into account the trend information of historical data, making the forecast results more accurate and timely.
[0024] S13 calculates the weighted average usage Q of historical data: , is the historical usage data for the same period of year i; S14 introduces a trend adjustment coefficient R to reflect the long-term trend of user water consumption. The trend adjustment coefficient R is obtained by linear regression of historical data to reflect the long-term trend of user water consumption: ;in, The average value of the historical data year is used to calculate the trend adjustment factor. It represents the average value of historical consumption data and is used to calculate the trend adjustment coefficient. By introducing the trend adjustment coefficient, the long-term trend of user water consumption can be captured. The trend adjustment coefficient is estimated based on historical data using the linear regression method and used to adjust the weighted average consumption, so that the forecast results can reflect the overall trend of water consumption and improve the rationality of the forecast.
[0025] S15 calculates the time distance of the predicted date D relative to the historical data center : ;in, Indicates the central date of historical data, that is, the date corresponding to the middle position of historical data; S16 uses trend adjustment coefficient R and time distance , adjust the weighted average usage Q to get the final predicted usage P: ;in, is the trend adjustment intensity coefficient, which controls the impact of trend adjustment, and P represents the final large-user water consumption forecast result. An exponential decay weight function is used to reasonably allocate the weight of historical data and highlight the impact of recent data. The trend adjustment coefficient is introduced to capture the long-term change trend of user water consumption through linear regression. The intensity of trend impact is dynamically adjusted by using the time distance between the prediction date and the historical data center. The attenuation coefficient and adjustment intensity coefficient in the model can be optimized according to actual conditions to improve the accuracy of the forecast. This forecasting model based on weighted average and trend adjustment of historical consumption data not only takes into account the periodicity of historical data, but also takes into account the long-term change trend of user water consumption. It can more accurately predict the water consumption of large users and provide a reference for the reasonable scheduling of water supply companies.
[0026] If a large user does not have historical data for more than T years, the system uses the Euclidean distance layer method to find similar large users and simulate missing values based on the data of similar users. The formula for calculating similarity is as follows: ;in, and The historical data points of user A and user B are selected, and the measurement point B that is most similar to measurement point A is selected, and its data from the same period is used for supplementary calculation. When the target user lacks sufficient historical data, the Euclidean distance algorithm is used to find users with similar characteristics among other users, and the historical data of similar users are used to fill the missing data of the target user. This method can make full use of the information of existing data and improve the reliability of missing data estimation.
[0027] The Euclidean distance algorithm is used to find the most similar measurement point. For the target measurement point A, the usage data for the last three months is extracted and recorded as vector . ; For each candidate measurement point (k=1, 2, ..., M), extract the usage data for the same three months, recorded as: ; For each candidate measurement point , calculate the Euclidean distance between it and the target point A : ; where n is the number of data points for 3 months, and Represent the target measuring point A and the candidate measuring point respectively The usage value of the i-th data point. Among all candidate measurement points, the measurement point with the smallest Euclidean distance is selected as the most similar measurement point, denoted as measurement point B: , extract the historical data of measuring point B: for the selected most similar measuring point B, extract its historical usage data for the same period of the past three years, recorded as ; Calculate the weighted average simulated usage: Take the weighted average of the historical data of measuring point B to get the simulated usage : ;in, is the weight of the i-th year, satisfying = 1. The weight can be set according to the reliability and time distance of the data, for example =0.5, =0.3, =0.2. Extract the actual usage data of measuring point A in the last 30 days and record it as . Calculate the recent data adjustment factor: Calculate the average actual usage of measurement point A in the last 30 days ; Calculate recent data adjustment factors : ; The simulated amount Adjustment factor with recent data Multiply them to get the final predicted usage of measuring point A .
[0028] S20, obtaining the daily consumption of the DMA partition corresponding to the DMA partition of the water supply network, the minimum consumption of the DMA partition at night, and the consumption of large users of the DMA partition; Among them, it should be noted that DMA zoning management (District Metering Area, that is, independent metering area) refers to dividing the pipe network into several relatively independent areas by cutting off the pipe section or closing the valve on the pipe section, and installing flow meters on the inlet and outlet pipes of each area, so as to realize the monitoring of the inflow and outflow of each area. In simple terms, the overall pipe network is divided into several DMA partitions according to needs, and the daily consumption of each DMA partition and the minimum nighttime consumption of each DMA partition are monitored separately. At the same time, there are several large users under each DMA partition, and the consumption of large users in the DMA partition is monitored manually or by smart water meters.
[0029] S30 The real-time DMA partition night usage has an abnormal year-on-year increase. The DMA partition large user usage is calculated. If the overall growth value of large user usage is less than 60% of the real-time DMA partition daily usage growth value, suspected leakage occurs; if the real-time DMA partition night usage has an abnormal year-on-year increase, the DMA partition large user usage is calculated. If the overall growth value of large user usage is less than 60% of the real-time DMA partition daily usage growth value, suspected leakage occurs.
[0030] S40 repeats steps S10-S30: if a DMA partition is determined to be suspected of leakage, continue to analyze its next-level sub-DMA partition, repeat steps S10-S30, and traverse to obtain the suspected leakage area; S50 locates the area where the leakage point is located: through the recursive analysis of step S40, the smallest DMA partition where the suspected leakage occurs is finally determined, that is, the area where the leakage point is located.
[0031] S60 Report suspected leaks: Generate a report with the location of suspected leaks, estimated leakage and other information and submit it to relevant departments and personnel.
[0032] System notification and SMS notification of leakage information to relevant personnel: Through automated system notification and SMS notification, suspected leakage information will be promptly sent to network maintenance, customer service and other relevant personnel to remind them to handle it in a timely manner.
[0033] Relevant personnel handling: After receiving the leakage notification, maintenance personnel will go to the suspected leakage area for on-site inspection, confirm the leakage location, and carry out repairs and treatment. At the same time, customer service personnel will communicate with the affected users, explain the cause of the leakage and inform them of the progress of the repair.
[0034] Example 2
[0035] This embodiment provides a leakage warning system based on the night water volume after denoising on the basis of embodiment 1, such as Figure 2 As shown, including:
[0036] A prediction module is used to collect the historical data of usage of large users in the DMA partition, and predict the missing data of usage of large users in the DMA partition based on the historical data of usage of large users in the DMA partition; A real-time data collection module is used to obtain the real-time DMA partition daily usage, real-time DMA partition night usage, and real-time DMA partition large user usage corresponding to the real-time water supply network DMA partition; The judgment module is used to calculate the usage of large users in the real-time DMA partition if there is an abnormal year-on-year increase in the nighttime usage. If the overall growth value of the usage of large users is less than 60% of the daily growth value of the real-time DMA partition, a suspected leakage occurs; if the nighttime usage of the real-time DMA partition increases abnormally year-on-year, the usage of large users in the DMA partition is calculated. If the overall growth value of the usage of large users is less than 60% of the daily growth value of the real-time DMA partition, a suspected leakage occurs.
[0037] The positioning module is used to repeat steps S10-S30. If a DMA partition is determined to be suspected of leakage, the next-level sub-DMA partition is continuously analyzed to traverse and obtain the final leakage area.
[0038] Example 3
[0039] like Figure 3 As shown, according to another aspect of the present application, an electronic device 500 is also provided. The electronic device 500 may include one or more processors and one or more memories. The memories store computer readable codes, and when the computer readable codes are executed by one or more processors, the water supply network partition leakage warning algorithm based on large user water volume as described above can be executed.
[0040] The method or system according to the embodiment of the present application can also be used by Figure 3 The electronic device architecture shown in FIG. Figure 3 As shown, the electronic device 500 may include a bus 501, one or more CPUs 502, a read-only memory (ROM) 503, a random access memory (RAM) 504, a communication port 505 connected to a network, an input / output component 506, a hard disk 507, and the like. The storage device in the electronic device 500, such as ROM503 or hard disk 507, can store the S10 provided by the present application to collect the historical data of the usage of large users in the DMA partition, and predict the missing data of the usage of large users in the DMA partition based on the historical data of the usage of large users in the DMA partition; S20 obtains the corresponding real-time DMA partition daily usage and real-time DMA partition night usage in the real-time water supply network DMA partition, S30 real-time DMA partition large user usage; the real-time DMA partition night usage has an abnormal year-on-year sudden increase, and the DMA partition large user usage is calculated. If the overall growth value of the large user usage is less than 60% of the real-time DMA partition daily usage growth value, a suspected leakage is generated; if the real-time DMA partition night usage has an abnormal year-on-year sudden increase, the DMA partition large user usage is calculated. If the overall growth value of the large user usage is less than 60% of the real-time DMA partition daily usage growth value, a suspected leakage is generated; S40 repeats steps S10-S30. If a DMA partition is determined to be suspected of leakage, continue to analyze its next-level sub-DMA partition, and traverse to obtain the final leakage area. Further, the electronic device 500 may also include a user interface 508. certainly, Figure 3 The architecture shown is only exemplary and can be omitted according to actual needs when implementing different devices. Figure 3 One or more components of an electronic device are shown.
[0041] Example 4
[0042] Figure 4 Schematic diagram of a computer-readable storage medium structure provided by an embodiment of the present application. Figure 4As shown, a computer-readable storage medium 600 according to an embodiment of the present application is shown. Computer-readable instructions are stored on the computer-readable storage medium 600. When the computer-readable instructions are executed by the processor, the water supply network partition leakage warning algorithm based on large user water volume according to the embodiment of the present application described with reference to the above figures can be executed. The storage medium 600 includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory (cache). Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.
[0043] In addition, according to the implementation mode of the present application, the process described in the above reference flowchart can be implemented as a computer software program. For example, the present application provides a non-transitory machine-readable storage medium, the non-transitory machine-readable storage medium stores machine-readable instructions, the machine-readable instructions can be executed by a processor to execute instructions corresponding to the method steps provided in the present application, for example: S10 collects the historical data of the usage of large users in the DMA partition, and predicts the missing data of the usage of large users in the DMA partition based on the historical data of the usage of large users in the DMA partition; S20 obtains the corresponding real-time DMA partition daily usage and real-time DMA partition nighttime usage in the real-time water supply network DMA partition, S30 real-time DMA partition large user usage; real-time DMA partition large user usage; The nighttime usage of the partition increases abnormally compared with the same period last year, and the usage of large users in the DMA partition is calculated. If the overall growth value of the usage of large users is less than 60% of the daily usage growth value of the real-time DMA partition, a suspected leakage occurs; if the nighttime usage of the real-time DMA partition increases abnormally compared with the same period last year, the usage of large users in the DMA partition is calculated. If the overall growth value of the usage of large users is less than 60% of the daily usage growth value of the real-time DMA partition, a suspected leakage occurs; S40 repeats steps S10-S30. If a DMA partition is determined to be suspected of leakage, continue to analyze its next-level sub-DMA partition and traverse to obtain the final leakage area. When the computer program is executed by the central processing unit (CPU), the above functions defined in the method of the present application are executed.
[0044] The methods, apparatuses, and devices of the present application may be implemented in many ways. For example, the methods, apparatuses, and devices of the present application may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of steps for the method is for illustration only, and the steps of the method of the present application are not limited to the order specifically described above unless otherwise specified. In addition, in some embodiments, the present application may also be implemented as programs recorded in a recording medium, which include machine-readable instructions for implementing the method according to the present application. Therefore, the present application also covers recording media storing programs for executing the method according to the present application.
[0045] In addition, the parts of the above-mentioned technical solutions provided in the embodiments of the present application that are consistent with the implementation principles of the corresponding technical solutions in the prior art are not described in detail to avoid excessive redundancy.
[0046] The specific implementation modes as described above further describe the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation mode of the present invention and is not intended to limit the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.
Claims
1. A water supply network zoning leakage warning algorithm based on large user water volume, characterized in that: include: S10, collecting historical usage data of large users in the DMA partition, and predicting missing usage data of large users in the DMA partition based on the historical usage data of large users in the DMA partition; S20, obtaining the real-time DMA partition daily usage, real-time DMA partition night usage, and real-time DMA partition large user usage corresponding to the real-time water supply network DMA partition; S30: If the nighttime usage of the real-time DMA partition increases abnormally compared with the same period last year, the usage of large users in the DMA partition is calculated. If the overall growth value of the usage of large users is less than 60% of the daily growth value of the real-time DMA partition, a suspected leakage occurs; If the nighttime usage of the real-time DMA partition increases abnormally year-on-year, calculate the usage of large users in the DMA partition. If the overall growth value of the usage of large users is less than 60% of the daily growth value of the real-time DMA partition, suspected leakage occurs; S40, repeating steps S10-S30, if a DMA partition is determined to be suspected of leakage, continue to analyze its next-level sub-DMA partition, traverse to obtain the final leakage area, and issue an early warning.
2. The water supply network partition leakage warning algorithm based on large user water volume according to claim 1 is characterized in that: The method for predicting missing data of large user usage in a DMA partition based on historical data of large user usage in the DMA partition includes: If the historical data of the usage of large users in the DMA partition is greater than or equal to T years, the weighted average of the historical data of the usage of large users in the DMA partition in the same period of T years is used as the simulated usage, and adjustments are made to obtain the missing data of the usage of large users in the DMA partition; If the historical data of large-user usage in a DMA partition is less than T years, the Euclidean distance multiplication is used to find the large-user usage of similar DMA partitions, and the missing values of large-user usage in the DMA partition are simulated based on the large-user usage data of similar DMA partitions, where T is a natural number greater than zero.
3. The water supply network partition leakage warning algorithm based on large user water volume according to claim 2 is characterized in that: The method for predicting missing data of large user usage in a DMA partition based on historical data of large user usage in the DMA partition includes: S11 determines the predicted usage date of the DMA partition's largest user, and takes the historical usage data of the same period N years before the usage date of the DMA partition's largest user as reference data; S12 performs a weighted average of the historical usage data for these N years, with the weight using an exponential decay function. The more recent the data, the greater the weight. The calculation formula is: ; is the decay coefficient, which controls the decay speed of the weight, i represents the year index of the historical data, ranging from 1 to N, j is the year index of the historical data, ranging from 1 to N; S13 calculates the weighted average usage Q of historical data: ; is the historical usage data for the same period of the i-th year.
4. The water supply network partition leakage warning algorithm based on large user water volume according to claim 3 is characterized in that: The method for predicting missing data of large user usage in a DMA partition based on historical data of large user usage in the DMA partition also includes: S14 introduces a trend adjustment coefficient R to reflect the long-term trend of user water consumption. The calculation method of R is as follows: ;in, The average value of historical data years, Indicates the average value of historical usage data; S15 calculates the time distance of the forecast date relative to the historical data center : ;in, Indicates the central date of historical data; S16 uses trend adjustment coefficient R and time distance , adjust the weighted average usage Q to get the final predicted usage P: ;in, is the trend adjustment intensity coefficient, and P represents the usage prediction result of large users in the DMA partition.
5. The water supply network zoning leakage warning algorithm based on large user water volume according to claim 2 is characterized in that: The method for predicting missing data of large user usage in a DMA partition based on historical data of large user usage in the DMA partition includes: For the DMA partition large user usage to be predicted, extract the usage data of the last three months and record it as a vector ; For each candidate point (k=1, 2, ..., M), extract the usage data for the same three months, recorded as: ; For each candidate measurement point , calculate the Euclidean distance between the candidate measurement point and the large user usage of the DMA partition to be predicted : , ; where n is the number of data points for 3 months, and Respectively represent the DMA partition large user usage and candidate measurement points The usage value at the i-th data point; Among all candidate measurement points, the measurement point with the smallest Euclidean distance is selected as the most similar measurement point, which is recorded as measurement point B: ; For the most similar point B, extract its historical data for the same period in the past three years Quantity data, denoted as ; Take the weighted average of the historical data of measuring point B to get the simulated usage : ;in, is the weight of the i-th year, =1.
6. The water supply network partition leakage warning algorithm based on large user water volume according to claim 5 is characterized in that: Also includes: Extract the actual usage data of measurement point A in the last 30 days, recorded as ; Calculate the average actual usage of measuring point A in the last 30 days ; Calculate recent data adjustment factors : , the simulated dosage Adjustment factor with recent data Multiply them to get the final predicted usage of measuring point A .
7. A water supply network zoning leakage warning system based on large user water volume, characterized in that: include: A prediction module is used to collect the historical data of usage of large users in the DMA partition, and predict the missing data of usage of large users in the DMA partition based on the historical data of usage of large users in the DMA partition; A real-time data collection module is used to obtain the real-time DMA partition daily usage, real-time DMA partition night usage, and real-time DMA partition large user usage corresponding to the real-time water supply network DMA partition; The judgment module is used to calculate the usage of large users in the real-time DMA partition if the nighttime usage of the real-time DMA partition increases abnormally year-on-year. If the overall growth value of the usage of large users is less than 60% of the daily usage growth value of the real-time DMA partition, a suspected leakage occurs; If the nighttime usage of the real-time DMA partition increases abnormally year-on-year, calculate the usage of large users in the DMA partition. If the overall growth value of the usage of large users is less than 60% of the daily growth value of the real-time DMA partition, suspected leakage occurs; The positioning module is used to repeat steps S10-S30. If a DMA partition is determined to be suspected of leakage, the next-level sub-DMA partition is continuously analyzed to traverse and obtain the final leakage area.
8. An electronic device comprising a memory, a central processing unit, and a computer program stored in the memory and executable on the central processing unit, characterized in that: When the central processor executes the computer program, it implements the water supply network zoning leakage warning algorithm based on large user water volume as described in any one of claims 1-6.
9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed, implements the water supply network zoning leakage warning algorithm based on large user water volume according to any one of claims 1 to 6.
Citation Information
Patent Citations
LeakView leakage control and management system for urban water supply pipe network
CN107355688A
Water supply region measurement and leakage control system and design method thereof
CN107422679A
Water flow leakage alarming method, system and device and storage medium
CN109827077A
Urban water supply system leakage monitoring method based on dynamic district metering area (DMA) partitioning
CN110185092A
Community DMA leakage detection management and control method based on noise monitoring technology
CN111720753A
Cited By
Method for judging DMA (Direct Memory Access) leakage through total meter hour data and minute meter hour data of intelligent water meter
CN121452502A
Pipe network leakage intelligent detection and positioning system based on intelligent algorithm
CN121676887A
