Water transfer project leakage traceability identification method and system

Abstract

The invention relates to the technical field of leakage traceability, in particular to a water transfer project leakage traceability identification method and system, and the method comprises the following steps: setting monitoring points in a water transfer project, collecting the temperature, pressure and flow velocity data of the key monitoring points, carrying out the time sequence analysis of parameters, analyzing the water flow dynamic state and environment change in real time, and generating state monitoring data. According to the method, the environment change near the leakage is analyzed by using the state monitoring data, the abnormal change is identified through simulation comparison analysis, the leakage point is predicted and positioned more accurately, the energy state before and after the leakage is evaluated through entropy increase calculation, and the leakage position and time are further predicted accurately; by simulating energy flow under differentiated environment conditions, the accuracy of seepage path identification is improved, and more efficient seepage source positioning is realized, so that the whole seepage traceability identification process is more systematic and scientific, and the safety supervision and maintenance efficiency of water conservancy facilities is greatly enhanced.

Description

Technical Field

[0001] This invention relates to the field of leakage tracing technology, and in particular to a method and system for tracing and identifying leakage sources in water diversion projects. Background Art

[0002] The field of leak source tracing technology focuses on detecting and identifying seepage problems in hydraulic engineering projects to ensure structural safety and functionality. It utilizes various methods such as physical detection, chemical tracing, and computer simulation to determine the source and path of water flow. This helps engineers and maintenance personnel locate leak points and implement effective remediation measures. The application of leak source tracing technology is crucial, especially in large dams, reservoirs, pipelines, and hydraulic facilities, where leaks, if not addressed promptly, can lead to serious structural damage and environmental problems.

[0003] Among them, the water diversion project leakage source identification method refers to a technical means specifically used for the detection and source tracing of seepage points in water diversion projects. By integrating advanced sensor data, geographic information systems, and machine learning techniques, it effectively tracks and locates abnormal leakage paths of water flow. Its main purpose is to prevent and repair leakage problems, ensure the effective management and allocation of water resources, reduce water waste, and protect the long-term stability of hydraulic structures.

[0004] Existing leak tracing technologies rely on physical detection or chemical tracing. While effective in some cases, these methods require considerable time to identify and locate leaks, and their accuracy and efficiency are limited in large-scale or complex hydraulic systems. For example, physical detection techniques such as acoustic monitoring are significantly affected by topography and materials, while chemical tracing is influenced by environmental factors, impacting the accuracy and reliability of the results. Traditional technologies struggle to achieve real-time monitoring and analysis of water flow dynamics, resulting in insufficient response time to rapidly changing seepage events and a failure to intervene effectively before the problem reaches a critical stage. This delay leads to unnecessary resource waste and potential safety risks, especially in emergencies where the lack of rapid and accurate data makes it difficult to implement effective emergency measures. Summary of the Invention

[0005] The purpose of this invention is to address the shortcomings of existing technologies by proposing a method and system for tracing and identifying leakage sources in water diversion projects.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: a method for tracing and identifying the source of leakage in a water diversion project, comprising the following steps: S1: Set up monitoring points in the water diversion project, collect temperature, pressure and flow velocity data of key monitoring points, perform time series analysis on parameters, analyze water flow dynamics and environmental changes in real time, and generate status monitoring data; S2: Based on the status monitoring data, analyze the temperature and pressure data near the water diversion project leakage, identify abnormal changes in temperature and pressure by comparing the deviation between real-time and expected data, and obtain simulation comparison analysis results; S3: Apply the simulation comparison analysis results to evaluate the changes in energy state before and after leakage, compare the theoretical and measured values ​​of entropy, predict the location and time of leakage, and generate dynamic prediction results of entropy increase. S4: Using the entropy increase dynamic prediction results, simulate energy flow under differentiated environmental conditions, estimate the energy distribution of water flow in geological structures, trace the source of leakage, and obtain the energy distribution simulation results; S5: Based on the energy distribution simulation results, and referring to the local temperature and pressure monitoring in the water diversion project, track the changes in parameters, identify potential leakage points, and generate leakage point identification results; S6: Using the leak point identification results and combined with field test data, verify the consistency of the thermodynamic model, predict leakage events and leakage probabilities in real-time water diversion projects, and obtain model verification results.

[0007] As a further aspect of the present invention, the state monitoring data includes time-series temperature, pressure, and flow rate data, historical records of parameters, and real-time update information; the simulation comparison analysis results include deviation analysis between real-time and expected data, identification data of abnormal changes, and abnormal temperature and pressure indicators; the entropy increase dynamic prediction results include comparative analysis between theoretical and measured entropy values, predicted leakage location and time information, and energy state change data; the energy distribution simulation results include simulated energy flow data, energy distribution estimation in geological structures, and source identification information of leakage paths; the leakage source location information includes thermodynamic parameters of potential leakage points, temperature and pressure change tracking data, and local monitoring point information; and the simulation verification results include consistency assessment between simulation and real-time observation data, effectiveness analysis, and data comparison results from on-site verification.

[0008] As a further aspect of the present invention, the steps of setting up monitoring points in the water diversion project, collecting temperature, pressure, and flow velocity data from key monitoring points, performing time series analysis on the parameters, analyzing water flow dynamics and environmental changes in real time, and generating status monitoring data are as follows: S101: Select key locations in the water diversion project to set up monitoring points, deploy temperature, pressure and flow velocity sensors, check the coverage of key water flow dynamics and environmental change areas by the monitoring points, conduct functional tests and calibrations of the sensors, and obtain real-time monitoring parameter data. S102: Based on the real-time monitoring parameter data, perform time series analysis on the collected temperature, pressure and flow rate data, eliminate outliers using data normalization, perform data trend analysis, synchronize the data, and generate parameter time series analysis results. S103: Using the time series analysis results of the parameters, monitor the changes in water flow and environment in the water diversion project in real time, use data trend analysis to identify fluctuation patterns, adjust the threshold through sensitivity analysis, optimize the data capture frequency, and generate status monitoring data.

[0009] As a further aspect of the present invention, the steps of analyzing temperature and pressure data near the leakage of the water diversion project based on the aforementioned status monitoring data, identifying abnormal changes in temperature and pressure by comparing the real-time and expected data deviations, and obtaining the simulation comparison analysis results are as follows: S201: Based on the status monitoring data, select monitoring points near the water diversion project leakage, collect temperature and pressure data for the target time period, process the data, eliminate errors and interference, and generate initial monitoring data for the leakage area. S202: Initialize monitoring data through the leakage area, compare the data with a preset threshold, analyze the mutation points in the data, identify data segments that do not conform to the normal pattern, and generate abnormal data detection results; S203: Based on the abnormal data detection results, analyze the abnormal changes in temperature and pressure, identify the trends and intensity of changes, assess the location and scale of potential leaks, and generate simulation comparison analysis results.

[0010] As a further aspect of the present invention, the steps of applying the simulation comparison analysis results to evaluate the changes in energy state before and after leakage, comparing the theoretical and measured values ​​of entropy, predicting the location and time of leakage, and generating dynamic entropy increase prediction results are as follows: S301: Based on the simulation comparison analysis results, calculate the energy state before and after leakage, assess the energy loss, compare and analyze the theoretical model of entropy with the measured data, capture the key points of energy state change, and generate energy state assessment data; S302: Using the energy state assessment data, compare the theoretical and measured values ​​of entropy using the entropy change model, analyze the deviation between the two, record the patterns and rules of the deviation, and generate entropy value comparison analysis results. S303: Based on the entropy value comparison analysis results, the location and time of leakage are predicted using the deviation mode, the time and location of leakage are analyzed, and dynamic prediction results of entropy increase are generated.

[0011] As a further aspect of the present invention, the steps of using the entropy increase dynamic prediction results to simulate energy flow under differentiated environmental conditions, estimate the energy distribution of water flow in geological structures, trace the source of seepage, and obtain the energy distribution simulation results are as follows: S401: Based on the entropy increase dynamic prediction results, the finite element method is used to simulate the energy transfer model, optimize the energy distribution estimation under different geological structure conditions, and generate energy flow simulation data by adjusting the model parameters to match the measured energy state. S402: Using the energy flow simulation data, perform energy distribution analysis, identify key energy flow paths in the water diversion project, evaluate the matching degree between the paths and known geological structures, and generate energy path analysis results; S403: Based on the energy path analysis results, the leakage path is traced and identified, the correlation between energy loss points and geological structure data is identified, the starting point and path of leakage are analyzed, the location and diffusion pattern of leakage are mapped, and energy distribution simulation results are generated.

[0012] As a further aspect of the present invention, the formula for the finite element method is as follows:

[0013] in, The energy flow through the geological medium, Thermal conductivity, The area traversed. For temperature difference, For the thickness of the material, This is a modulating coefficient for the temperature gradient and the complexity of the geological structure. It is a resisting factor for geological structures.

[0014] As a further aspect of the present invention, based on the energy distribution simulation results, and referring to local temperature and pressure monitoring in water diversion projects, the steps of tracking parameter changes, identifying potential leakage points, and generating leakage point identification results are as follows: S501: Based on the energy distribution simulation results, collect the microscopic thermodynamic parameters in the water diversion project, refer to the local temperature and pressure data of the leakage area, track the sensitivity of data changes, and generate microscopic parameter monitoring data. S502: Using the micro-parameter monitoring data, analyze the fluctuations in temperature and pressure, identify key data points that deviate from the normal range, analyze potential leakage activities, and generate parameter anomaly identification results; S503: Based on the anomaly identification results of the parameters, combined with geological and water diversion project data, the location of the identified potential leakage points is determined, the location of the leakage points in the water diversion project structure is mapped, and leakage point identification results are generated.

[0015] As a further aspect of the present invention, the steps for using the leakage point identification results, combined with field test data, to verify the consistency of the thermodynamic model and predict leakage events and probabilities in real-time water diversion projects, and to obtain model verification results are as follows: S601: Based on the leak point identification results, organize the field testing team to deploy monitoring equipment at the designated leak points, collect real-time thermodynamic data of the leak locations, synchronize the data, and generate field test data; S602: Using the field test data, compare it with the predicted data of the thermodynamic model, analyze the consistency between the model prediction and the field observation data, and generate model consistency analysis results by adjusting the model to avoid errors; S603: Based on the model consistency analysis results, the updated thermodynamic model is used to predict leakage events and calculate leakage probabilities in a real-time water diversion project environment. The reliability of the model is verified through real-time data, and model verification results are generated.

[0016] A water diversion project leakage tracing and identification system, the system being used to execute the aforementioned water diversion project leakage tracing and identification method, the system comprising: The status monitoring module collects temperature, pressure and flow velocity data based on key monitoring points of the water diversion project, analyzes water flow dynamics and environmental changes in real time, and generates monitoring datasets. The data comparison and analysis module analyzes the temperature and pressure data near the leak using the monitoring dataset, identifies abnormal changes by comparing the real-time data with the expected data, and generates anomaly identification results. The entropy calculation module assesses changes in energy state based on the anomaly identification results, compares the theoretical and measured values ​​of entropy, predicts the location and time of leakage, and generates entropy increase prediction results. The flow simulation module simulates energy flow under differentiated geological conditions based on the entropy increase prediction results, adjusts model parameters to match measured data, estimates energy distribution, and generates energy distribution simulation data. Based on the energy distribution simulation data, the leak point location module analyzes the thermodynamic parameters around potential leak points, locates leak points by tracking parameter changes, performs on-site verification and compares the data with the simulation data, and generates simulation verification results.

[0017] Compared with the prior art, the advantages and positive effects of the present invention are as follows: This invention improves the understanding of water flow dynamics and environmental changes by real-time monitoring of temperature, pressure, and flow velocity data at key monitoring points and performing time-series analysis. This enables rapid location and analysis of abnormal leakage paths in water conservancy projects. It utilizes state monitoring data to analyze environmental changes near leaks and identifies abnormal changes through simulation and comparative analysis, allowing for more accurate prediction and location of leak points. Entropy increase calculations assess the energy state before and after leakage, further accurately predicting the location and timing of leaks. Simulating energy flow under differentiated environmental conditions improves the accuracy of seepage path identification. Energy distribution simulation results help better understand changes in thermodynamic parameters around leak points, achieving more efficient leak source location. This makes the entire leak tracing and identification process more systematic and scientific, significantly enhancing the safety supervision and maintenance efficiency of water conservancy facilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a schematic diagram of the workflow of the present invention; Figure 2 This is a detailed flowchart of S1 of the present invention; Figure 3 This is a detailed flowchart of the S2 process of the present invention; Figure 4 This is a detailed flowchart of the S3 process of the present invention; Figure 5 This is a detailed flowchart of the S4 process of the present invention; Figure 6 This is a detailed flowchart of S5 of the present invention; Figure 7 This is a detailed flowchart of S6 of the present invention; Figure 8 This is a system flowchart of the present invention. DETAILED DESCRIPTION

[0019] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0020] In the description of this invention, it should be understood that the terms "length," "width," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientation or positional relationships, are based on the orientation or positional relationships shown in the accompanying drawings and are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Furthermore, in the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0021] See also Figure 1 This invention provides a technical solution, a method for tracing and identifying the source of leakage in a water diversion project, comprising the following steps: S1: Set up monitoring points in the water diversion project, collect temperature, pressure and flow velocity data of key monitoring points, process parameters, analyze water flow dynamics and environmental changes in real time, and generate status monitoring data; S2: Based on the status monitoring data, trace the source of leakage in the water diversion project, analyze the temperature and pressure data near the leakage, identify abnormal changes in temperature and pressure by comparing the deviation between real-time and expected data, and obtain the simulation comparison analysis results. S3: Apply the simulation comparison analysis results to calculate entropy increase, evaluate the change in energy state before and after leakage, compare the theoretical and measured values ​​of entropy, predict the location and time of leakage, and generate dynamic prediction results of entropy increase. S4: Using the dynamic prediction results of entropy increase, perform energy conservation simulation. By simulating energy flow under different environmental conditions, estimate the energy distribution of water flow in various geological structures, trace the source of leakage, and obtain the energy distribution simulation results. S5: Based on the energy distribution simulation results, and according to the microscopic thermodynamic parameters in the water transfer project, the changes in parameters are tracked through local temperature and pressure monitoring to identify potential leakage points and generate leakage point identification results; S6: Using the leakage point identification results and combined with field test data, verify the consistency of the thermodynamic model, predict leakage events and leakage probabilities in real-time water diversion projects, and obtain model verification results.

[0022] The condition monitoring data includes time-series temperature, pressure, and flow rate data, historical parameter records, and real-time updates. The simulation comparison analysis results include deviation analysis between real-time and expected data, identification data of abnormal changes, and abnormal temperature and pressure indicators. The entropy increase dynamic prediction results include comparative analysis between theoretical and measured entropy values, predicted leakage location and time information, and energy state change data. The energy distribution simulation results include simulated energy flow data, energy distribution estimation in geological structures, and source identification information for leakage paths. The leakage source location information includes thermodynamic parameters of potential leakage points, temperature and pressure change tracking data, and local monitoring point information. The simulation verification results include consistency assessment between simulation and real-time observation data, effectiveness analysis, and data comparison results from field verification.

[0023] See also Figure 2 The specific steps for setting up monitoring points in water diversion projects, collecting temperature, pressure, and flow velocity data from key monitoring points, performing time-series analysis on the parameters, analyzing water flow dynamics and environmental changes in real time, and generating status monitoring data are as follows: S101: The execution process for setting up monitoring points at key locations in the water diversion project, deploying temperature, pressure and flow velocity sensors, verifying that the monitoring points cover key water flow dynamics and environmental change areas, conducting sensor function tests and calibrations, and obtaining real-time monitoring parameter data is as follows; Monitoring points are set up at key locations in the water diversion project, deploying temperature, pressure, and flow velocity sensors to ensure coverage of dynamic water flow and critical environmental changes. Sensor functionality is tested and calibrated to guarantee data accuracy and sensor reliability. The location of monitoring points considers key inflection points in the water flow, such as reservoir inlets and outlets, and main water transfer pipelines. Data collection from these monitoring points is crucial for predicting reservoir water level changes, regulating water flow, and providing early warnings of floods and other environmental changes. By collecting temperature, pressure, and flow velocity data in real time, the information is transmitted to central monitoring equipment to generate real-time monitoring parameter data, using the formula:

[0024] in, The comprehensive parameter values ​​representing the monitoring points, 、 and These are the weighting coefficients for each parameter. It's a temperature value. It is the flow rate value. It's time.

[0025] S102: Based on real-time monitoring parameter data, the collected temperature, pressure, and flow rate data are analyzed over time. Outliers are eliminated using data normalization, data trend analysis is performed, and data synchronization is conducted to generate the parameter time series analysis results. The execution flow is as follows: Based on real-time monitoring parameter data, time series analysis of temperature, pressure, and flow velocity data is performed to identify long-term trends and short-term fluctuations in water flow. Data normalization eliminates outliers caused by sensor errors or changes in the external environment. Advanced statistical methods are used for data trend analysis, including moving averages and exponential smoothing techniques to smooth the time series data. Data synchronization ensures that data collected from various monitoring points are aligned in time, enhancing the accuracy of the analysis. This is crucial for ensuring the effectiveness of water resource management and the safety of water transfer projects. The parameter time series analysis results are generated using the following formula:

[0026] in, It is time Smoothed data, It is time Smoothed data, It is the smoothing coefficient. It is time The actual data points.

[0027] S103: The execution flow for generating status monitoring data is as follows: using the results of parametric time series analysis, the changes in water flow and environment in the water diversion project are monitored in real time, fluctuation patterns are identified by using data trend analysis, thresholds are adjusted by sensitivity analysis, data capture frequency is optimized, and status monitoring data is generated. Using parametric time series analysis, real-time monitoring of water flow and environmental changes in water transfer projects is conducted. Through data trend analysis, not only can natural water flow fluctuation patterns be identified, but also abnormal fluctuations caused by sudden events such as floods or equipment failures can be detected. Sensitivity analysis is used to adjust sensor thresholds to more accurately capture key data and avoid data noise and false alarms. Optimizing data capture frequency to adapt to different monitoring needs and save resources is an indispensable part of water transfer projects. Status monitoring data is generated using the following formula:

[0028] in, It is a sensitivity score for fluctuation patterns. It is a single data point. It is the average of the data points. It represents the number of data points.

[0029] See also Figure 3 Based on the status monitoring data, the temperature and pressure data near the water diversion project leakage are analyzed. By comparing the deviation between real-time and expected data, abnormal changes in temperature and pressure are identified, and the simulation comparison analysis results are obtained. The specific steps are as follows: S201: Based on the status monitoring data, select monitoring points near the water diversion project leakage, collect temperature and pressure data for the target time period, process the data, eliminate errors and interference, and generate the initial monitoring data for the leakage area. The execution flow is as follows: Based on condition monitoring data, temperature and pressure data are collected for selected time periods to ensure that the monitoring data accurately reflects the leakage situation. Data processing is performed, including removing errors introduced by sensor malfunctions or environmental interference. Data normalization and filtering are applied to improve the accuracy of data analysis. The establishment of monitoring points and data processing are fundamental to detecting and locating leaks, effectively helping to determine the specific location and cause of the leak, and generating initial monitoring data for the leak area using the following formula:

[0030] in, Indicates the Standardized difference of each data point It's a pressure reading. It is the average pressure value. It is the standard deviation of the pressure reading.

[0031] S202: The execution flow of initializing monitoring data through the leakage area, comparing the data with the preset threshold, analyzing the abrupt change points in the data, identifying data segments that do not conform to the normal mode, and generating abnormal data detection results is as follows; By initializing monitoring data from the processed and standardized leakage area, anomaly detection is performed. The data is compared against preset pressure and temperature thresholds, and statistical methods are used to analyze abrupt changes in the data, indicating potential leaks. Identifying anomalous data segments is crucial for determining the precise location and severity of leaks, enabling timely detection and appropriate maintenance measures to prevent potential environmental damage and economic losses. Anomaly detection results are generated using the following formula:

[0032] in, It is the magnitude of data mutation. and They represent In the The maximum and minimum values ​​of sudden changes in data from each monitoring point.

[0033] S203: Based on the abnormal data detection results, the execution flow for analyzing abnormal changes in temperature and pressure, identifying the trend and intensity of changes, assessing the location and scale of potential leaks, and generating simulation comparison analysis results is as follows; Based on the anomaly data detection results, further analysis is conducted on anomalous temperature and pressure changes. By analyzing the trends and intensity of these changes, the location and scale of the leak are comprehensively assessed. The identified anomalous temperature and pressure changes will be used to simulate the leak. By comparing the simulation with data models under normal conditions, the leak can be located more accurately and its potential impact assessed. This helps engineers and managers understand the specific circumstances of the leak and take appropriate remedial measures to reduce environmental and operational risks. The simulation comparison analysis results are generated using the following formula:

[0034] in, It is a leakage intensity rating. It is a sample The values ​​at points of abnormal change This is the average value under normal conditions. It refers to the number of samples.

[0035] See also Figure 4 The specific steps for applying simulation and comparative analysis results to assess changes in energy state before and after leakage, comparing theoretical and measured entropy values, predicting the location and timing of leakage, and generating dynamic entropy increase prediction results are as follows: S301: Based on the simulation comparison analysis results, calculate the energy state before and after leakage, assess energy loss, compare and analyze the theoretical model of entropy with the measured data, capture the key points of energy state change, and generate energy state assessment data. The execution process is as follows: By conducting in-depth research on the simulation comparison analysis results, the energy state before and after leakage is assessed, and the relevant energy loss is calculated. A detailed comparison between the theoretical model of entropy and field measurement data identifies the key changes in energy loss. This not only helps determine the quantitative value of energy loss but also reveals the crucial links in the energy state change, which is essential for understanding the overall impact on system performance and generating energy state assessment data.

[0036] S302: The execution flow for using energy state assessment data, comparing the theoretical and measured values ​​of entropy using an entropy change model, analyzing the deviation between the two, recording the patterns and rules of the deviation, and generating entropy value comparison analysis results is as follows; Using information from energy state assessment data, an entropy change model is applied to compare theoretical entropy values ​​with those obtained through actual measurements. This comparative analysis reveals key deviations in system performance, providing a deeper understanding of system stability and efficiency. Recording patterns and regularities of these deviations helps identify non-optimal regions in system operation, providing data support for improvement measures and preventative maintenance. The entropy value comparison analysis results are generated using the following formula:

[0037] in, It is the deviation value of entropy. It is the theoretical entropy value. It is the measured entropy value.

[0038] S303: Based on the entropy value comparison analysis results, the location and time of leakage are predicted using the deviation mode. The execution flow for analyzing the time and location of leakage and generating dynamic entropy increase prediction results is as follows; Based on entropy comparison analysis, deviation patterns are used to predict the potential location and timing of leaks. The prediction method, based on statistical analysis and historical data patterns, can accurately pinpoint the specific area and time window of leakage. This is crucial for timely response and reducing potential system losses. The prediction is based not only on static data but also on the influence of dynamic behavior, improving the accuracy and reliability of the prediction. The dynamic entropy increase prediction results are generated using the following formula:

[0039] in, This is the predicted leakage time. It is entropy bias. It is the current time, the function This represents a prediction model based on entropy bias and the current time.

[0040] See also Figure 5 The specific steps for simulating energy flow under differentiated environmental conditions using entropy increase dynamic prediction results, estimating the energy distribution of water flow in geological structures, tracing the source of seepage, and obtaining energy distribution simulation results are as follows: S401: Based on the dynamic prediction results of entropy increase, the finite element method is used to simulate the energy transfer model, optimize the energy distribution estimation under different geological structure conditions, and generate energy flow simulation data by adjusting the model parameters to match the measured energy state. The execution process is as follows: By utilizing entropy increase dynamic prediction results, the finite element method is applied to conduct detailed simulations of energy transfer in water diversion projects. This allows for accurate energy distribution estimation under different geological conditions, and further model optimization to match measured energy states. Fine-tuning model parameters ensures a high degree of consistency between simulation results and field data, providing profound insights into energy flow. This not only improves prediction accuracy but also enhances model adaptability, effectively addressing the complexity of geological structures and generating simulated energy flow data.

[0041] The formula for the finite element method is as follows:

[0042] in, The energy flow through the geological medium, Thermal conductivity, The area traversed. For temperature difference, For the thickness of the material, This is a modulating coefficient for the temperature gradient and the complexity of the geological structure. It is a resisting factor for geological structures.

[0043] The execution process is as follows: Calculate basic energy flow pass This represents energy transfer under a simple one-dimensional heat flow model, introducing... and To adjust the model to adapt to complex geological conditions, It is an adjustment coefficient based on the temperature gradient, obtained from experimental data, and It is a factor that reflects the resistance of geological structure. It is determined based on geological exploration data and material properties. The two parameters work together to adjust the traditional heat flow model to better match the measured energy state and improve the prediction accuracy of the model.

[0044] S402: The execution flow for generating energy path analysis results by using energy flow simulation data, identifying key energy flow paths in water diversion projects, evaluating the matching degree between the paths and known geological structures, is as follows; By utilizing energy flow simulation data and conducting detailed energy distribution analysis, key energy flow paths in water transfer projects can be identified, and the compatibility of these paths with known geological structures can be assessed. This helps determine the optimal path for energy transfer efficiency and areas of energy loss. It also reveals how geological mismatches lead to increased energy losses, providing a basis for structural improvements and risk management, and generating energy path analysis results.

[0045] S403: Based on the energy path analysis results, the seepage path is traced and identified, the correlation between energy loss points and geological structure data is identified, the starting point and path of seepage are analyzed, the location and diffusion pattern of seepage are mapped, and the energy distribution simulation results are generated. The execution flow is as follows: Based on energy path analysis results, the key to identifying the source of leakage lies in recognizing the correlation between energy loss points and geological structure data, and analyzing the initiation point and path of leakage. By mapping energy distribution and flow patterns, the location of leakage can be accurately pinpointed, and diffusion patterns can be predicted. This is crucial for timely response to leakage events, reducing losses, and developing effective countermeasures. The energy distribution simulation results are generated using the following formula:

[0046] in, This indicates the distance from the leak source to the detection point. It is the difference in coordinates between the location of the leakage source and the detection point in three-dimensional space.

[0047] See also Figure 6 Based on the energy distribution simulation results, and referring to the local temperature and pressure monitoring in the water diversion project, the steps for tracking parameter changes, identifying potential leakage points, and generating leakage point identification results are as follows: S501: Based on the energy distribution simulation results, collect the microscopic thermodynamic parameters in the water diversion project, refer to the local temperature and pressure data of the leakage area, track the sensitivity of data changes, and generate microscopic parameter monitoring data. The execution process is as follows: By analyzing energy distribution simulations, microscopic thermodynamic parameters in water diversion projects are collected, with particular attention paid to local temperature and pressure data in leakage areas. This data is crucial for identifying microscopic changes. Monitoring and recording the sensitivity of these parameters allows for effective tracking and assessment of changes in the microscopic state of the project. This not only helps in understanding environmental changes before and after leakage but also provides early warning information for timely response to potential leaks or remaining issues. Microscopic parameter monitoring data is generated using the following formula:

[0048] in, Represents sensitivity to micro parameters. It is the change in pressure. It is the change in temperature. S502: The execution flow for analyzing temperature and pressure fluctuations using micro-parameter monitoring data, identifying key data points that deviate from the normal range, analyzing potential leakage activities, and generating parameter anomaly identification results is as follows; By using microscopic parameter monitoring data, a systematic analysis of temperature and pressure fluctuations is conducted to identify key data points that significantly deviate from normal ranges. These data points indicate potential leakage activity. Detailed analysis reveals abnormal patterns and fluctuation trends in the data, which is crucial for early leakage diagnosis and preventative measures. The parameter anomaly identification results are generated using the following formula:

[0049] in, The total deviation of the representative parameter, and These are deviations in temperature and pressure, respectively.

[0050] S503: Based on the parameter anomaly identification results, combined with geological and water diversion project data, the location of the identified potential leakage points is determined, the location of the leakage points in the water diversion project structure is mapped, and the execution flow for generating leakage point identification results is as follows; Based on the parameter anomaly identification results, combined with detailed geological and water diversion engineering data, the precise location of identified potential leakage points is determined. By analyzing and mapping the specific location of leakage points within the water diversion engineering structure, the extent and potential impact of leakage can be better understood. This ensures accurate identification and rapid response to potential risks, providing crucial information for subsequent maintenance and repair work. The leakage point identification results are generated using the following formula:

[0051] in, This indicates the distance between the leak point and the reference point. It is the difference in lateral and longitudinal position of the leakage point relative to the reference point.

[0052] See also Figure 7 Using the leak point identification results and combined with field test data, the consistency of the thermodynamic model is verified, and the model is used to predict leakage events and leakage probabilities in real-time water transfer projects. The specific steps to obtain the model verification results are as follows: S601: Based on the leak point identification results, organize the field testing team to deploy monitoring equipment at the designated leak points, collect real-time thermodynamic data of the leak locations, synchronize the data, and generate field test data. The execution process is as follows: Based on the leak point identification results, the field testing team was dispatched to the designated leak points to deploy high-precision monitoring equipment. This equipment is specifically designed to collect real-time thermodynamic data at the leak location, such as temperature, pressure, and flow rate, to monitor and analyze the immediate impact of the leak. Ensuring the comprehensiveness and accuracy of data collection supports in-depth leak analysis. The application of synchronization technology allows for real-time uploading of monitoring data, ensuring the timeliness and integrity of the data and generating field test data.

[0053] S602: The execution flow of using field test data to compare with the predicted data of the thermodynamic model, analyzing the consistency between the model prediction and the field observation data, and adjusting the model to avoid errors and generate model consistency analysis results is as follows; By comparing field test data with predictions from a pre-established thermodynamic model, the consistency between model predictions and actual observations is analyzed. The key is to identify biases and limitations of the model in practical applications. Through analyzing these discrepancies, the team can adjust and optimize the model to reduce future prediction errors, improve its accuracy and reliability, and generate model consistency analysis results using the following formula:

[0054] in, This represents the average consistency error between the model and the actual data. Is the model in the first Predicted values ​​in this test These are the corresponding observed values. It represents the total number of data points.

[0055] S603: Based on the model consistency analysis results, the updated thermodynamic model is used to predict leakage events and calculate leakage probabilities in a real-time water transfer project environment. The reliability of the model is verified through real-time data, and the execution flow for generating model verification results is as follows. Based on the model consistency analysis results, the updated thermodynamic model is used to continue predicting leakage events in a real-time water transfer engineering environment. Not only is the leakage probability calculated, but the reliability and accuracy of the model are also verified through continuous validation with real-time data. Feedback on model performance helps the team understand how the model performs in practical applications, ensuring that the model can provide reliable predictions in future engineering applications. Model validation results are generated using the following formula:

[0056] in, This represents the reliability index of the model. and These are the model's predicted values ​​and observed values, respectively. It represents the number of observation points.

[0057] See also Figure 8 A water diversion project leakage tracing and identification system, used to execute the above-mentioned water diversion project leakage tracing and identification method, the system includes: The status monitoring module collects temperature, pressure and flow velocity data based on key monitoring points of the water diversion project, analyzes water flow dynamics and environmental changes in real time, and generates monitoring datasets. The data comparison and analysis module monitors the dataset, analyzes the temperature and pressure data near the leak, and identifies abnormal changes by comparing the real-time data with the expected data, generating anomaly identification results. The entropy calculation module assesses changes in energy state based on anomaly identification results, compares theoretical and measured entropy values, predicts leakage location and time, and generates entropy increase prediction results. The flow simulation module simulates energy flow under different geological conditions based on entropy increase prediction results, adjusts model parameters to match measured data, estimates energy distribution, and generates simulated energy distribution data. The leak point location module analyzes the thermodynamic parameters around potential leak points based on energy distribution simulation data, locates leak points by tracking parameter changes, conducts on-site verification and compares the data with simulation data, and generates simulation verification results.

[0058] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention in any other way. Any person skilled in the art may make changes or modifications to the above-disclosed technical content to create equivalent embodiments that can be applied to other fields. However, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the protection scope of the present invention.

Claims

1. A method for tracing and identifying leakage sources in water diversion projects, characterized in that: The following steps are involved: Set up monitoring points in the water diversion project, collect temperature, pressure and flow rate data at key monitoring points, conduct time series analysis on parameters, analyze water flow dynamics and environmental changes in real time, and generate status monitoring data; According to the state monitoring data, the temperature and pressure data near the leakage of the water diversion project are analyzed, and by comparing the real-time and expected data deviations, abnormal changes in temperature and pressure are identified to obtain simulation comparative analysis results; Apply the simulation comparative analysis results to evaluate the change in energy state before and after leakage, compare the theoretical value and measured value of entropy, predict the location and time of leakage, and generate entropy increase dynamic prediction results; By using the entropy increase dynamic prediction results, the energy flow under differentiated environmental conditions is simulated, the energy distribution of water flow in the geological structure is estimated, the leakage path is traced and identified, and the energy distribution simulation results are obtained; Based on the energy distribution simulation results, referring to the local temperature and pressure monitoring in the water diversion project, tracking the changes in parameters, identifying potential leakage points, and generating leakage point identification results; The leakage point identification results are used in combination with field test data to verify the consistency of the thermodynamic model, predict leakage events and leakage probabilities in real-time water diversion projects, and obtain model verification results.

2. The method for tracing and identifying leakage sources of water diversion projects according to claim 1 is characterized in that: The state monitoring data includes time-serialized temperature, pressure and flow rate data, historical records of parameters and real-time update information; the simulation comparison analysis results include deviation analysis of real-time and expected data, identification data of abnormal changes, and temperature and pressure abnormality indicators; the entropy increase dynamic prediction results include comparative analysis of entropy theoretical values ​​and measured values, predicted leakage location and time information, and energy state change data; the energy distribution simulation results include simulated energy flow data, energy distribution estimation in geological structures, and source tracing identification information of leakage paths; the leakage source positioning information includes thermodynamic parameters of potential leakage points, temperature and pressure change tracking data, and local monitoring point information; the simulation verification results include consistency evaluation of simulation and real-time observation data, effectiveness analysis, and data comparison results of field verification.

3. The method for tracing and identifying leakage sources of water diversion projects according to claim 1 is characterized in that: Monitoring points are set up in the water diversion project to collect temperature, pressure and flow rate data of key monitoring points, conduct time series analysis on parameters, and analyze water flow dynamics and environmental changes in real time. The specific steps for generating status monitoring data are as follows: Set up monitoring points at key locations of the water diversion project, deploy temperature, pressure and flow rate sensors, check that the monitoring points cover key water flow dynamics and environmental change areas, perform functional testing and calibration of sensors, and obtain real-time monitoring parameter data; Based on the real-time monitoring parameter data, time series analysis is performed on the collected temperature, pressure and flow rate data, outliers are eliminated by data normalization, data trend analysis is performed, and data synchronization is performed to generate parameter time series analysis results; The parameter time series analysis results are used to monitor the changes in water flow and environment in the water diversion project in real time, and the fluctuation pattern is identified using data trend analysis. The threshold is adjusted through sensitivity analysis, the data capture frequency is optimized, and the status monitoring data is generated.

4. The method for tracing and identifying leakage sources of water diversion projects according to claim 1 is characterized in that: According to the state monitoring data, the temperature and pressure data near the leakage of the water diversion project are analyzed, and the abnormal changes of temperature and pressure are identified by comparing the real-time and expected data deviations. The specific steps of obtaining the simulation comparison analysis results are as follows: According to the state monitoring data, a monitoring point near the leakage of the water diversion project is selected, the temperature and pressure data of the target time period are collected, and the data is processed to eliminate errors and interferences, and generate initialization monitoring data of the leakage area; Initialize monitoring data from the leakage area, compare the data with a preset threshold, analyze mutation points in the data, identify data segments that do not conform to the normal pattern, and generate abnormal data detection results; Based on the abnormal data detection results, the abnormal change points of temperature and pressure are analyzed, the change trend and intensity are identified, the location and scale of potential leakage are evaluated, and simulation comparative analysis results are generated.

5. The method for tracing and identifying leakage sources of water diversion projects according to claim 1 is characterized in that: The steps of applying the simulation comparative analysis results, evaluating the change of energy state before and after leakage, comparing the theoretical value and measured value of entropy, predicting the location and time of leakage, and generating the entropy increase dynamic prediction results are as follows: According to the simulation comparative analysis results, the energy state before and after the leakage is calculated, the energy loss is evaluated, and the key points of the energy state change are captured by comparing and analyzing the theoretical model of entropy with the measured data to generate energy state evaluation data; Using the energy state assessment data, using an entropy change model to compare the theoretical value of entropy with the measured value, analyzing the deviation between the two, recording the pattern and law of the deviation, and generating entropy value comparison analysis results; Based on the entropy value comparison analysis results, the deviation model is used to predict the location and time of the leakage, the time and location of the leakage are analyzed, and the entropy increase dynamic prediction results are generated.

6. The method for tracing and identifying leakage sources of water diversion projects according to claim 1 is characterized in that: The entropy increase dynamic prediction results are used to simulate the energy flow under differentiated environmental conditions, estimate the energy distribution of water flow in the geological structure, and identify the leakage path. The specific steps for obtaining the energy distribution simulation results are as follows: The energy transfer model is simulated by using the finite element method through the entropy increase dynamic prediction results, the energy distribution estimation under the differentiated geological structure conditions is optimized, and the energy flow simulation data is generated by adjusting the model parameters to match the measured energy state; Using the energy flow simulation data, energy distribution analysis is performed to identify key energy flow paths in the water diversion project, evaluate the matching degree of the paths with known geological structures, and generate energy path analysis results; Based on the energy path analysis results, the leakage path is traced and identified, the correlation between the energy loss point and the geological structure data is identified, the starting point and path of the leakage are analyzed, the location and diffusion pattern of the leakage are mapped, and the energy distribution simulation results are generated.

7. The method for tracing and identifying leakage sources of water diversion projects according to claim 6 is characterized in that: The formula of the finite element method is as follows: in, is the energy flow through the geological medium, is the thermal conductivity, is the area passed through, is the temperature difference, is the thickness of the material, is the adjustment coefficient of temperature gradient and geological structure complexity, It is the resistance factor of geological structure.

8. The method for tracing and identifying leakage sources of water diversion projects according to claim 1, characterized in that: Based on the energy distribution simulation results, referring to the local temperature and pressure monitoring in the water diversion project, tracking the changes in parameters, identifying potential leakage points, and generating leakage point identification results are specifically as follows: Through the energy distribution simulation results, the microscopic thermodynamic parameters in the water diversion project are collected, the local temperature and pressure data of the leakage area are referred to, the sensitivity of the data changes is tracked, and the microscopic parameter monitoring data is generated; Using the microscopic parameter monitoring data, analyze the fluctuations of temperature and pressure, identify key data points that deviate from the normal range, analyze potential leakage activities, and generate parameter anomaly identification results; Based on the parameter anomaly identification results, combined with geological and water diversion project data, the identified potential leakage points are located, the positions of the leakage points in the water diversion project structure are mapped, and the leakage point identification results are generated.

9. The method for tracing and identifying leakage sources of water diversion projects according to claim 1, characterized in that: The leakage point identification results are used in combination with field test data to verify the consistency of the thermodynamic model, and leakage events and leakage probabilities are predicted in real-time water diversion projects. The specific steps for obtaining the model verification results are as follows: According to the leakage point identification results, organize a field test team to deploy monitoring equipment at the designated leakage point, collect real-time thermodynamic data of the leakage location, synchronize the data, and generate field test data; The field test data is compared with the predicted data of the thermodynamic model to analyze the consistency between the model prediction and the field observation data, and the model is adjusted to avoid errors to generate a model consistency analysis result; Through the model consistency analysis results, the updated thermodynamic model is used in a real-time water diversion project environment to predict leakage events and calculate leakage probabilities, and the reliability of the model is verified through real-time data to generate model verification results.

10. A water diversion project leakage tracing and identification system, characterized in that: According to the method for tracing and identifying the source of leakage in a water diversion project according to any one of claims 1 to 9, the system comprises: The status monitoring module collects temperature, pressure and flow rate data based on key monitoring points of the water diversion project, analyzes water flow dynamics and environmental changes in real time, and generates monitoring data sets; The data comparison and analysis module analyzes the temperature and pressure data near the leak through the monitoring data set, identifies abnormal changes through real-time difference comparison with expected data, and generates abnormal identification results; The entropy value calculation module evaluates the change of energy state according to the abnormality identification result, compares the theoretical value and measured value of entropy, predicts the leakage location and time, and generates an entropy increase prediction result; The flow simulation module simulates the energy flow under the conditions of differentiated geological structures according to the entropy increase prediction results, adjusts the model parameters to match the measured data, estimates the energy distribution, and generates energy distribution simulation data; The leakage point locating module analyzes the thermodynamic parameters around the potential leakage point based on the energy distribution simulation data, locates the leakage point by tracking the parameter changes, performs on-site verification and compares the simulation data, and generates a simulation verification result.

Images