Water supply network failure risk prediction method and system based on big data

Abstract

The present invention discloses a method and system for predicting the risk of water supply network failure based on big data, which relates to the technical field of dynamic monitoring of water supply network, including: obtaining historical water supply data of water supply pipelines; predicting future water supply data of water supply pipelines; determining the material of water supply pipelines; analyzing and obtaining a performance degradation database of water supply pipelines; fitting and obtaining the wear rate of water supply pipelines under each water supply data; based on the historical water supply data of water supply pipelines, combined with the performance degradation database of water supply pipelines, evaluating the historical total wear index of water supply pipelines under the historical water supply data of water supply pipelines; based on the future water supply data of water supply pipelines and the historical total wear index of water supply pipelines, evaluating water supply pipelines, and predicting the risk of water supply pipeline failure in the future. The advantages of the present invention are: realizing real-time monitoring, early warning and prediction of water supply network failures, improving the management level and operation efficiency of water supply networks, and ensuring the stability and safety of urban water supply.

Description

Technical Field

[0001] The present invention relates to the technical field of dynamic monitoring of water supply pipe networks, and in particular to a method and system for predicting water supply pipe network failure risks based on big data. Background Art

[0002] The water supply network is a pipeline system that transmits and distributes water to users in water supply projects. It is also called the water supply network. The water supply network consists of water transmission pipelines, water distribution networks, pressure pumping stations, water towers, pools and network ancillary facilities. The main function of the water supply network is to provide clean drinking water and production water to meet people's daily life, production and fire fighting needs. As an important part of urban infrastructure, the safety and stability of the water supply network are directly related to the quality of life of residents and the normal operation of the city.

[0003] Since the pipes of the water supply network are usually buried in a concealed manner, the current operation and maintenance of the water supply network pipeline failures is carried out by regular inspections and fault location. However, this method lacks reasonable planning and the regular inspections lack specificity, making it difficult to timely discover the hidden dangers of pipeline failures in the water supply network and difficult to meet the efficient and stable management needs of the water supply network. Summary of the invention

[0004] In order to solve the above technical problems, a method and system for predicting the risk of water supply network failure based on big data are provided. This technical solution solves the problem that at the current stage, the water supply network pipeline failure is operated and maintained by regular inspection and fault location. However, this method lacks reasonable planning and the regular inspection lacks specificity, making it difficult to timely discover the hidden dangers of pipeline failure in the water supply network and difficult to meet the needs of efficient and stable management of the water supply network.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0006] A water supply network failure risk prediction method based on big data, comprising:

[0007] Obtain historical water supply data of the water supply pipeline, the water supply data including the water supply flow rate and water supply pressure in the pipeline;

[0008] Based on the historical water supply data of water supply pipelines, predict the future water supply data of water supply pipelines;

[0009] Determine the material of the water supply pipe;

[0010] Analyze the materials of the water supply pipeline to obtain a performance degradation database of the water supply pipeline;

[0011] Based on the performance degradation database of water supply pipelines, the wear rate of water supply pipelines under each water supply data is obtained by fitting;

[0012] Based on the historical water supply data of water supply pipelines and the performance degradation database of water supply pipelines, the historical total wear index of water supply pipelines under the historical water supply data of water supply pipelines is evaluated;

[0013] Based on the future water supply data of the water supply pipeline and the historical total wear index of the water supply pipeline, the water supply pipeline is evaluated, the risk of failure of the water supply pipeline in the future is predicted, and the operation and maintenance plan of the water supply network is dynamically adjusted based on the risk.

[0014] Preferably, the predicting of future water supply data of water supply pipelines based on historical water supply pipeline water supply data specifically includes:

[0015] Observe historical water supply pipeline water supply data at different time scales to obtain at least one change cycle scale of the water supply data;

[0016] Based on each change cycle scale, several sample data are selected from the historical water supply pipeline water supply data;

[0017] The linear fitting method is used to fit and analyze the predicted water supply data at each change cycle scale based on the sample data;

[0018] Based on the average water supply data at each change cycle scale, the future water supply data of the water supply pipeline is obtained.

[0019] Preferably, the linear fitting method is adopted, and the water supply data at each change cycle scale is analyzed based on the sample data fitting method, specifically including:

[0020] In order from the earliest to the latest time, add a number to each sample data;

[0021] Based on the linear regression fitting principle, the linear regression equation between sample data and serial number is analyzed;

[0022] The loss value of the linear regression equation is calculated using the mean square error method;

[0023] Based on the linear regression equation, the predicted water supply data at the current change cycle scale is predicted;

[0024] The calculation formula for the predicted water supply data is:

[0025] In the formula, is the linear regression coefficient, To predict water supply data, is the total number of sample data, is the jth sample data, The number of the sample data.

[0026] Preferably, the analysis based on the material of the water supply pipeline to obtain the performance degradation database of the water supply pipeline specifically includes:

[0027] Based on historical water supply data of the water supply pipeline, determine the water supply flow rate range and water supply pressure range of the water supply pipeline;

[0028] Set the water supply flow rate value step size and the water supply pressure value step size respectively;

[0029] Based on the water supply flow rate value taking step length, a number of values ​​are taken from the water supply flow rate interval as the number of samples of the water supply flow rate;

[0030] Based on the water supply pressure value step length, a number of values ​​are taken from the water supply pressure interval as the number of samples of the water supply pressure;

[0031] The number of samples of water supply flow rate and the number of samples of water supply pressure are combined in pairs to obtain a number of water supply flow rate-water supply pressure sample groups;

[0032] Take a sample tube made of the same material as the water supply pipe, and use each water supply flow rate-water supply pressure sample group to conduct a simulation experiment, and obtain the water supply pipe wear rate corresponding to each water supply flow rate-water supply pressure sample group;

[0033] The water supply pipe wear rates corresponding to all water supply flow rate-water supply pressure sample groups are combined into a water supply pipe performance degradation database.

[0034] Preferably, the water supply pipe wear rate obtained by fitting each water supply data based on the performance degradation database of the water supply pipe specifically includes:

[0035] The water supply data set is ,in, is the water supply pressure, is the water supply flow rate;

[0036] Retrieve from the database and calculate the vector distance between each water supply flow rate-water supply pressure sample group and the water supply data group;

[0037] Screen out two water supply flow rate-water supply pressure sample groups with the smallest vector distances from the water supply data group, and record them as the first target water supply flow rate-water supply pressure sample group and the second target water supply flow rate-water supply pressure sample group respectively;

[0038] Obtain the water supply pipe wear rate of the first target water supply flow rate-water supply pressure sample group and the second target water supply flow rate-water supply pressure sample group respectively;

[0039] Based on the water supply pipe wear rate of the first target water supply flow rate-water supply pressure sample group and the second target water supply flow rate-water supply pressure sample group, the water supply pipe wear rate of the water supply data group is calculated by a fitting formula;

[0040] In the formula, for The corresponding water supply pipe wear rate, is the vector distance between the first target water supply flow rate-water supply pressure sample group and the water supply data group, is the vector distance between the second target water supply flow rate-water supply pressure sample group and the water supply data group, is the water supply pipe wear rate of the first target water supply flow rate-water supply pressure sample group, It is the wear rate of the water supply pipe of the second target water supply flow rate-water supply pressure sample group.

[0041] Preferably, the calculation formula of the vector distance is:

[0042] In the formula, is the vector distance between the water supply flow rate-water supply pressure sample group and the water supply data group, is the water supply flow rate in the water supply flow rate-water supply pressure sample group, It is the water supply pressure in the water supply flow rate - water supply pressure sample group.

[0043] Preferably, the water supply pipeline performance under the historical water supply pipeline water supply data is evaluated based on the historical water supply pipeline water supply data in combination with the water supply pipeline performance degradation database, and recorded as the real-time water supply pipeline performance, specifically including:

[0044] Based on the historical water supply data of water supply pipelines, the relationship between the historical water supply flow rate and time and the relationship between the historical water supply pressure and time are obtained respectively;

[0045] Based on the wear analysis formula, calculate the total historical wear index of the water supply pipeline;

[0046] The wear analysis formula is specifically:

[0047] In the formula, is the historical total wear index of the water supply pipeline, is the total historical working hours of the water supply pipeline, is the relationship between historical water supply flow rate and time, is the relationship between historical water supply pressure and time, For time.

[0048] Preferably, the water supply pipeline is evaluated based on the future water supply data and the historical total wear index of the water supply pipeline to predict the risk of failure of the water supply pipeline in the future, specifically including:

[0049] Based on the water supply data of the future water supply pipeline, determine the average wear rate of the future water supply pipeline;

[0050] The average wear rate of the water supply pipeline in the future is multiplied by the analysis time and the total historical wear index of the water supply pipeline to obtain the predicted wear index of the water supply pipeline in the future;

[0051] It is determined whether the predicted wear index of the water supply pipeline is greater than a preset value. If so, it is determined that the risk of failure of the water supply pipeline in the future is high. If not, it is determined that the risk of failure of the water supply pipeline in the future is low.

[0052] Furthermore, a water supply network fault risk prediction system based on big data is proposed, which is used to implement the above-mentioned water supply network fault risk prediction method based on big data, including:

[0053] A storage module, the storage module is used to store a performance degradation database of each water supply pipeline in the water supply network and historical water supply data of the water supply pipelines in the water supply network;

[0054] A water supply analysis module, the water supply analysis module is electrically connected to the storage module, and the water supply analysis module is used to predict future water supply data of the water supply pipeline based on historical water supply data of the water supply pipeline;

[0055] A wear analysis module, the wear analysis module is electrically connected to the storage module, and the wear analysis module is used to fit the wear rate of the water supply pipeline under each water supply data based on the performance degradation database of the water supply pipeline;

[0056] A risk prediction module, which is electrically connected to the water supply analysis module and the wear analysis module. The risk prediction module is used to evaluate the historical total wear index of the water supply pipeline under the historical water supply data of the water supply pipeline based on the historical water supply data of the water supply pipeline, combined with the performance degradation database of the water supply pipeline, and to evaluate the water supply pipeline based on the future water supply data of the water supply pipeline and the historical total wear index of the water supply pipeline, predict the risk of failure of the water supply pipeline in the future, and dynamically adjust the operation and maintenance plan of the water supply network based on the risk.

[0057] Compared with the prior art, the present invention has the following beneficial effects:

[0058] The present invention proposes a water supply network failure risk prediction scheme based on big data. Based on the historical water supply pipeline water supply data of the water supply network, the water supply pipeline water supply data in the future is analyzed and predicted, and a performance degradation database of the water supply pipeline is constructed. The wear rate of the water supply pipeline under each water supply data is analyzed based on the performance degradation database of the water supply pipeline. Combined with the historical water supply pipeline water supply data of the water supply network and the predicted water supply pipeline water supply data in the future, it is analyzed whether the water supply pipeline of the water supply network can meet the next water supply demand. Combined with the analysis results, advance inspection planning of the water supply network can be realized, and high-risk pipeline areas with unmet water supply demand can be pre-maintained, so as to realize real-time monitoring, early warning and prediction of water supply network failures, improve the management level and operation efficiency of the water supply network, and ensure the stability and safety of urban water supply. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 A flow chart of a water supply network failure risk prediction method based on big data proposed in this scheme;

[0060] Figure 2 A flow chart of the method for predicting future water supply data of water supply pipelines in this solution;

[0061] Figure 3 This is a flow chart of the method for fitting and analyzing water supply data at each change cycle scale based on sample data in this scheme;

[0062] Figure 4 A flow chart of a method for obtaining a performance degradation database of a water supply pipeline by analyzing the material of the water supply pipeline in this solution;

[0063] Figure 5 A flow chart of the method for obtaining the water supply pipe wear rate under each water supply data by fitting in this scheme;

[0064] Figure 6 A flow chart of a method for evaluating the performance of a water supply pipeline under historical water supply pipeline water supply data in this solution;

[0065] Figure 7 Flowchart of the method for predicting the risk of future failure of water supply pipelines in this scenario. DETAILED DESCRIPTION

[0066] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0067] Reference Figure 1 As shown, a water supply network failure risk prediction method based on big data includes:

[0068] Obtain historical water supply data of the water supply pipeline, the water supply data including the water supply flow rate and water supply pressure in the pipeline;

[0069] Based on the historical water supply data of water supply pipelines, predict the future water supply data of water supply pipelines;

[0070] Determine the material of the water supply pipe;

[0071] Analyze the materials of the water supply pipeline to obtain a performance degradation database of the water supply pipeline;

[0072] Based on the performance degradation database of water supply pipelines, the wear rate of water supply pipelines under each water supply data is obtained by fitting;

[0073] Based on the historical water supply data of water supply pipelines and the performance degradation database of water supply pipelines, the historical total wear index of water supply pipelines under the historical water supply data of water supply pipelines is evaluated;

[0074] Based on the future water supply data of the water supply pipeline and the historical total wear index of the water supply pipeline, the water supply pipeline is evaluated, the risk of failure of the water supply pipeline in the future is predicted, and the operation and maintenance plan of the water supply network is dynamically adjusted based on the risk.

[0075] This solution is based on the historical water supply data of the water supply pipes of the water supply network, analyzes and predicts the water supply data of the water supply pipes in the future, and constructs a performance degradation database for the water supply pipes. The wear rate of the water supply pipes under each water supply data is analyzed based on the performance degradation database for the water supply pipes. Combined with the historical water supply data of the water supply pipes of the water supply network and the predicted water supply data for the water supply pipes in the future, it is analyzed whether the water supply pipes of the water supply network can meet the subsequent water supply demand. Combined with the analysis results, advance inspection planning of the water supply network can be implemented, and pre-inspection of high-risk pipeline areas where water supply demand cannot be met can be carried out.

[0076] Reference Figure 2 As shown in the figure, based on the historical water supply data of water supply pipelines, the predicted water supply data of water supply pipelines in the future specifically includes:

[0077] Observe historical water supply pipeline water supply data at different time scales to obtain at least one change cycle scale of the water supply data;

[0078] Based on each change cycle scale, several sample data are selected from the historical water supply pipeline water supply data;

[0079] The linear fitting method is used to fit and analyze the predicted water supply data at each change cycle scale based on the sample data;

[0080] Based on the average of the water supply data at each change cycle scale, the future water supply data of the water supply pipeline is obtained;

[0081] The predicted future water supply data of the water supply pipeline is the average value of the water supply data within the future analysis period, and the collected sample data are all the average values ​​of the historical water supply data within the same analysis period.

[0082] Reference Figure 3 As shown, the linear fitting method is used, and the water supply data at each change cycle scale is analyzed based on the sample data fitting, including:

[0083] In order from the earliest to the latest time, add a number to each sample data;

[0084] Based on the linear regression fitting principle, the linear regression equation between sample data and serial number is analyzed;

[0085] The loss value of the linear regression equation is calculated using the mean square error method;

[0086] Based on the linear regression equation, the predicted water supply data at the current change cycle scale is predicted;

[0087] The calculation formula for predicting water supply data is:

[0088] In the formula, is the linear regression coefficient, To predict water supply data, is the total number of sample data, is the jth sample data, The number of the sample data.

[0089] It is understandable that the water supply demand in different water supply areas usually has periodic fluctuations, and the periodic fluctuations are usually related to the degree of people's gathering and people's water use habits. For example, during non-working hours, the gathering of people in residential areas will increase, and the water demand in the area will increase. During meal times, the water demand in residential areas will also increase. This periodic change is based on days, while the changes in working days and non-working days are usually based on weeks. Therefore, when analyzing water demand, it is necessary to conduct targeted predictive analysis based on the periodic changes in water supply in different areas presented in historical water supply data, and conduct a comprehensive analysis based on the linear fitting results at different periodic scales to obtain water supply forecast data that is closer to the water use habits of the water supply area.

[0090] Reference Figure 4 As shown, according to the material of the water supply pipeline, the performance degradation database of the water supply pipeline is analyzed and specifically includes:

[0091] Based on historical water supply data of the water supply pipeline, determine the water supply flow rate range and water supply pressure range of the water supply pipeline;

[0092] Set the water supply flow rate value step size and the water supply pressure value step size respectively;

[0093] Based on the water supply flow rate value taking step length, a number of values ​​are taken from the water supply flow rate interval as the number of samples of the water supply flow rate;

[0094] Based on the water supply pressure value step length, a number of values ​​are taken from the water supply pressure interval as the number of samples of the water supply pressure;

[0095] The number of samples of water supply flow rate and the number of samples of water supply pressure are combined in pairs to obtain a number of water supply flow rate-water supply pressure sample groups;

[0096] Take a sample tube made of the same material as the water supply pipe, and use each water supply flow rate-water supply pressure sample group to conduct a simulation experiment, and obtain the water supply pipe wear rate corresponding to each water supply flow rate-water supply pressure sample group;

[0097] The water supply pipe wear rates corresponding to all water supply flow rate-water supply pressure sample groups are combined into a water supply pipe performance degradation database.

[0098] After the pipeline is laid, its working environment is basically fixed. On this basis, the parameters that affect the life of the pipeline are the water flow rate and pressure in the pipeline. Too fast a water flow rate will have a greater impact on the inner wall of the pipeline and accelerate wear. Long-term exposure to excessive pressure may cause the water pipe to deform and rupture. Therefore, in this scheme, based on the water supply flow rate range and water supply pressure range that the pipeline may withstand during actual operation, several sample values ​​are determined for simulation experiments to construct a performance degradation database for the water supply pipeline, and the performance degradation database for the water supply pipeline is used as the theoretical data basis for pipeline failure prediction.

[0099] Reference Figure 5 As shown in the figure, based on the performance degradation database of the water supply pipeline, the wear rate of the water supply pipeline under each water supply data is fitted and specifically includes:

[0100] The water supply data set is ,in, is the water supply pressure, is the water supply flow rate;

[0101] Retrieve from the database and calculate the vector distance between each water supply flow rate-water supply pressure sample group and the water supply data group;

[0102] Screen out two water supply flow rate-water supply pressure sample groups with the smallest vector distances from the water supply data group, and record them as the first target water supply flow rate-water supply pressure sample group and the second target water supply flow rate-water supply pressure sample group respectively;

[0103] Obtain the water supply pipe wear rate of the first target water supply flow rate-water supply pressure sample group and the second target water supply flow rate-water supply pressure sample group respectively;

[0104] Based on the water supply pipe wear rate of the first target water supply flow rate-water supply pressure sample group and the second target water supply flow rate-water supply pressure sample group, the water supply pipe wear rate of the water supply data group is calculated by a fitting formula;

[0105] In the formula, for The corresponding water supply pipe wear rate, is the vector distance between the first target water supply flow rate-water supply pressure sample group and the water supply data group, is the vector distance between the second target water supply flow rate-water supply pressure sample group and the water supply data group, is the water supply pipe wear rate of the first target water supply flow rate-water supply pressure sample group, It is the wear rate of the water supply pipe of the second target water supply flow rate-water supply pressure sample group.

[0106] The calculation formula for vector distance is:

[0107] In the formula, is the vector distance between the water supply flow rate-water supply pressure sample group and the water supply data group, is the water supply flow rate in the water supply flow rate-water supply pressure sample group, It is the water supply pressure in the water supply flow rate - water supply pressure sample group.

[0108] This scheme uses the pre-constructed performance degradation database of water supply pipelines as the theoretical data basis, and adopts a similar fitting method to calculate the wear rate of water supply pipelines under any water supply flow rate-water supply pressure data, thereby providing an effective evaluation basis for the subsequent water supply network failure risk prediction.

[0109] This solution uses the pre-built water supply pipeline performance degradation database as the theoretical data basis, and forms a comprehensive degradation data set by recording and analyzing the performance changes of various water supply pipelines under different conditions in detail. Using the similarity fitting method, we can calculate the wear rate of the water supply pipeline under any combination of water supply flow rate and water supply pressure data. This method fits the degradation data set to find the best similarity match, thereby estimating the wear under current conditions. In this way, the degree of wear of the water supply pipeline can be more accurately evaluated, providing an effective evaluation basis for the subsequent prediction of the risk of water supply network failure. Provide scientific guidance for maintenance and repair work to ensure the stable operation of the water supply system.

[0110] Reference Figure 6 As shown, based on the historical water supply pipeline water supply data and combined with the performance degradation database of the water supply pipeline, the water supply pipeline performance under the historical water supply pipeline water supply data is evaluated, which is recorded as the real-time water supply pipeline performance, and specifically includes:

[0111] Based on the historical water supply data of water supply pipelines, the relationship between the historical water supply flow rate and time and the relationship between the historical water supply pressure and time are obtained respectively;

[0112] Based on the wear analysis formula, calculate the total historical wear index of the water supply pipeline;

[0113] Among them, the wear analysis formula is as follows:

[0114] In the formula, is the historical total wear index of the water supply pipeline, is the total historical working hours of the water supply pipeline, is the relationship between historical water supply flow rate and time, is the relationship between historical water supply pressure and time, For time.

[0115] Reference Figure 7 As shown in the figure, based on the future water supply data of the water supply pipeline and the historical total wear index of the water supply pipeline, the water supply pipeline is evaluated and the risk of failure of the water supply pipeline in the future is predicted, including:

[0116] Based on the water supply data of the future water supply pipeline, determine the average wear rate of the future water supply pipeline;

[0117] The average wear rate of the water supply pipeline in the future is multiplied by the analysis time and the total historical wear index of the water supply pipeline to obtain the predicted wear index of the water supply pipeline in the future;

[0118] It is determined whether the predicted wear index of the water supply pipeline is greater than a preset value. If so, it is determined that the risk of failure of the water supply pipeline in the future is high. If not, it is determined that the risk of failure of the water supply pipeline in the future is low.

[0119] By analyzing the historical water supply data of the water supply network and combining it with the forecast of the water supply data of the water supply network in the future, we can comprehensively evaluate whether the water supply network's water supply pipelines have the ability to meet the water supply demand in the next period of time, so as to formulate a more scientific and reasonable water supply network inspection plan to ensure the efficient operation and water supply safety of the water supply system. By pre-inspecting high-risk pipeline areas where water supply demand cannot be met, problems in the water supply network can be discovered and solved in a timely manner, and resource allocation can be optimized to reduce the risk of sudden water supply interruptions and improve the reliability and stability of the entire water supply system.

[0120] Furthermore, this solution also proposes a water supply network fault risk prediction system based on big data, which is used to implement the above-mentioned water supply network fault risk prediction method based on big data, including:

[0121] A storage module, the storage module is used to store a performance degradation database of each water supply pipeline in the water supply network and historical water supply data of the water supply pipelines in the water supply network;

[0122] A water supply analysis module, the water supply analysis module is electrically connected to the storage module, and the water supply analysis module is used to predict future water supply data of the water supply pipeline based on historical water supply data of the water supply pipeline;

[0123] A wear analysis module, the wear analysis module is electrically connected to the storage module, and the wear analysis module is used to fit the wear rate of the water supply pipeline under each water supply data based on the performance degradation database of the water supply pipeline;

[0124] A risk prediction module is electrically connected to the water supply analysis module and the wear analysis module. The risk prediction module is used to evaluate the historical total wear index of the water supply pipeline under the historical water supply data of the water supply pipeline based on the historical water supply data of the water supply pipeline and the performance degradation database of the water supply pipeline. Based on the future water supply data of the water supply pipeline and the historical total wear index of the water supply pipeline, the water supply pipeline is evaluated to predict the risk of failure of the water supply pipeline in the future and the operation and maintenance plan of the water supply network is dynamically adjusted based on the risk.

[0125] In summary, the advantages of the present invention are: achieving real-time monitoring, early warning and prediction of water supply network failures, improving the management level and operation efficiency of the water supply network, and ensuring the stability and safety of urban water supply.

[0126] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. A method for predicting water supply network failure risk based on big data, characterized in that: include: Obtain historical water supply data of the water supply pipeline, the water supply data including the water supply flow rate and water supply pressure in the pipeline; Based on the historical water supply data of water supply pipelines, predict the future water supply data of water supply pipelines; Determine the material of the water supply pipe; Analyze the materials of the water supply pipeline to obtain a performance degradation database of the water supply pipeline; Based on the performance degradation database of water supply pipelines, the wear rate of water supply pipelines under each water supply data is obtained by fitting; Based on the historical water supply data of water supply pipelines and the performance degradation database of water supply pipelines, the historical total wear index of water supply pipelines under the historical water supply data of water supply pipelines is evaluated; Based on the future water supply data of the water supply pipeline and the historical total wear index of the water supply pipeline, the water supply pipeline is evaluated, the risk of failure of the water supply pipeline in the future is predicted, and the operation and maintenance plan of the water supply network is adjusted dynamically based on the risk; The water supply pipe wear rate obtained by fitting each water supply data based on the water supply pipe performance degradation database specifically includes: The water supply data set is , where is the water supply pressure, is the water supply flow rate; Retrieve from the database and calculate the vector distance between each water supply flow rate-water supply pressure sample group and the water supply data group; Screen out two water supply flow rate-water supply pressure sample groups with the smallest vector distances from the water supply data group, and record them as the first target water supply flow rate-water supply pressure sample group and the second target water supply flow rate-water supply pressure sample group respectively; Obtain the water supply pipe wear rate of the first target water supply flow rate-water supply pressure sample group and the second target water supply flow rate-water supply pressure sample group respectively; Based on the water supply pipe wear rate of the first target water supply flow rate-water supply pressure sample group and the second target water supply flow rate-water supply pressure sample group, the water supply pipe wear rate of the water supply data group is calculated by a fitting formula; In the formula, for The corresponding water supply pipe wear rate, is the vector distance between the first target water supply flow rate-water supply pressure sample group and the water supply data group, is the vector distance between the second target water supply flow rate-water supply pressure sample group and the water supply data group, is the water supply pipe wear rate of the first target water supply flow rate-water supply pressure sample group, The wear rate of the water supply pipe of the second target water supply flow rate-water supply pressure sample group; The calculation formula of the vector distance is: In the formula, is the vector distance between the water supply flow rate-water supply pressure sample group and the water supply data group, is the water supply flow rate in the water supply flow rate-water supply pressure sample group, is the water supply pressure in the water supply flow rate-water supply pressure sample group; The water supply pipeline performance under the historical water supply pipeline water supply data is evaluated based on the historical water supply pipeline water supply data and combined with the water supply pipeline performance degradation database, which is recorded as the real-time water supply pipeline performance and specifically includes: Based on the historical water supply data of water supply pipelines, the relationship between the historical water supply flow rate and time and the relationship between the historical water supply pressure and time are obtained respectively; Based on the wear analysis formula, calculate the total historical wear index of the water supply pipeline; The wear analysis formula is specifically: In the formula, is the historical total wear index of the water supply pipeline, is the total historical working hours of the water supply pipeline, is the relationship between historical water supply flow rate and time, is the relationship between historical water supply pressure and time, For time.

2. A method for predicting water supply network failure risk based on big data according to claim 1, characterized in that: The prediction of future water supply data based on historical water supply data specifically includes: Observe historical water supply pipeline water supply data at different time scales to obtain at least one change cycle scale of the water supply data; Based on each change cycle scale, several sample data are selected from the historical water supply pipeline water supply data; The linear fitting method is used to fit and analyze the predicted water supply data at each change cycle scale based on the sample data; Based on the average water supply data at each change cycle scale, the future water supply data of the water supply pipeline is obtained.

3. A method for predicting water supply network failure risk based on big data according to claim 2, characterized in that: The linear fitting method is used to fit and analyze the water supply data at each change cycle scale based on sample data, specifically including: In order from the earliest to the latest time, add a number to each sample data; Based on the linear regression fitting principle, the linear regression equation between sample data and serial number is analyzed; The loss value of the linear regression equation is calculated using the mean square error method; Based on the linear regression equation, the predicted water supply data at the current change cycle scale is predicted; The calculation formula for the predicted water supply data is: In the formula, is the linear regression coefficient, To predict water supply data, is the total number of sample data, is the jth sample data, and j is the number of the sample data.

4. A method for predicting water supply network failure risk based on big data according to claim 3, characterized in that: The analysis based on the material of the water supply pipeline to obtain the performance degradation database of the water supply pipeline specifically includes: Based on historical water supply data of the water supply pipeline, determine the water supply flow rate range and water supply pressure range of the water supply pipeline; Set the water supply flow rate value step size and the water supply pressure value step size respectively; Based on the water supply flow rate value taking step length, a number of values ​​are taken from the water supply flow rate interval as the number of samples of the water supply flow rate; Based on the water supply pressure value step length, a number of values ​​are taken from the water supply pressure interval as the number of samples of the water supply pressure; The number of samples of water supply flow rate and the number of samples of water supply pressure are combined in pairs to obtain a number of water supply flow rate-water supply pressure sample groups; Take a sample tube made of the same material as the water supply pipe, and use each water supply flow rate-water supply pressure sample group to conduct a simulation experiment, and obtain the water supply pipe wear rate corresponding to each water supply flow rate-water supply pressure sample group; The water supply pipe wear rates corresponding to all water supply flow rate-water supply pressure sample groups are combined into a water supply pipe performance degradation database.

5. A method for predicting water supply network failure risk based on big data according to claim 4, characterized in that: The risk of failure of the water supply pipeline in the future is predicted by evaluating the water supply pipeline based on the future water supply pipeline water supply data and the historical total wear index of the water supply pipeline, including: Based on the water supply data of the future water supply pipeline, determine the average wear rate of the future water supply pipeline; The average wear rate of the water supply pipeline in the future is multiplied by the analysis time and the total historical wear index of the water supply pipeline to obtain the predicted wear index of the water supply pipeline in the future; It is determined whether the predicted wear index of the water supply pipeline is greater than a preset value. If so, it is determined that the risk of failure of the water supply pipeline in the future is high. If not, it is determined that the risk of failure of the water supply pipeline in the future is low.

6. A water supply network failure risk prediction system based on big data, characterized in that: The method for predicting water supply network failure risk based on big data according to any one of claims 1 to 5 comprises: A storage module, the storage module is used to store a performance degradation database of each water supply pipeline in the water supply network and historical water supply data of the water supply pipelines in the water supply network; A water supply analysis module, the water supply analysis module is electrically connected to the storage module, and the water supply analysis module is used to predict future water supply data of the water supply pipeline based on historical water supply data of the water supply pipeline; A wear analysis module, the wear analysis module is electrically connected to the storage module, and the wear analysis module is used to fit the wear rate of the water supply pipeline under each water supply data based on the performance degradation database of the water supply pipeline; A risk prediction module, which is electrically connected to the water supply analysis module and the wear analysis module. The risk prediction module is used to evaluate the historical total wear index of the water supply pipeline under the historical water supply data of the water supply pipeline based on the historical water supply data of the water supply pipeline, combined with the performance degradation database of the water supply pipeline, and to evaluate the water supply pipeline based on the future water supply data of the water supply pipeline and the historical total wear index of the water supply pipeline, predict the risk of failure of the water supply pipeline in the future, and dynamically adjust the operation and maintenance plan of the water supply network based on the risk.

Images