Overflow detection and intelligent repair method for municipal pipe network

Abstract

The invention discloses a municipal pipe network overflow detection and intelligent repair method, and relates to the technical field of municipal pipe network management, and the method comprises the following specific steps: data fusion and basic analysis: employing a plurality of sensors to collect various data in real time, and carrying out the fusion and preprocessing in a data processing center, comparing and analyzing historical and real-time data to set a threshold value, and finding out an external environment change factor influencing the operation of the pipe network to provide basic data; through deep integration of meteorological, hydrological and municipal pipe network related data and by means of an intelligent hydrodynamic simulation technology, high-precision simulation of water flow in a pipe network can be realized, the occurrence position, time and influence range of overflow can be accurately predicted in advance, and the risk of overflow can be accurately evaluated based on accurate overflow risk evaluation. The system can automatically formulate and adjust a pipe network operation parameter regulation and control strategy in real time, parameters of the drainage pumping station and the opening degree of a pipe network valve are intelligently adjusted according to different overflow risk grades, and therefore the pipe network operation parameters can be effectively optimized.

Description

Technical Field

[0001] The present invention relates to the technical field of municipal pipe network management, and in particular to a municipal pipe network overflow detection and intelligent repair method. Background Art

[0002] With the rapid advancement of urbanization, the municipal pipeline network, as a core component of the urban water system, undertakes important tasks such as rainwater discharge, sewage treatment, and flood control and drainage. The operating status of the municipal pipeline network is directly related to the city's drainage efficiency, residents' quality of life, and the health of the urban ecological environment.

[0003] When the pipe network overflows, sewage will directly enter the natural environment, such as rivers and lakes. The sewage contains a large amount of pollutants. After the pollutants enter the water body, they will quickly consume the dissolved oxygen in the water, causing hypoxia in the water body. At the same time, nutrients such as nitrogen and phosphorus in the sewage will cause eutrophication of the water body, which not only affects the beauty of the water body, but also further destroys the balance of the water ecosystem, causing a sharp decline in the quality of the surrounding water environment. On the other hand, due to the mixing of rainwater into the inlet water of the sewage treatment plant, the concentration of pollutants in the sewage is diluted. When the concentration of inlet pollutants decreases, the original treatment balance will be broken. The treatment efficiency of some treatment units that rely on high concentrations of pollutants to react will be greatly reduced, making it difficult for the sewage treatment plant to stably meet the emission standards. The quality of the treated tail water will also be affected, further aggravating the pollution problem of the water environment.

[0004] Traditional municipal pipeline management relies mainly on manual inspections and simple monitoring methods, which have many shortcomings. First, manual inspections are inefficient and difficult to detect and address potential problems in the pipeline network in a timely manner. Especially in extreme weather conditions, the difficulty and danger of inspections are greatly increased. Second, existing monitoring systems can only provide limited real-time data and lack comprehensive consideration of different meteorological and hydrological conditions, resulting in insufficient prediction and early warning capabilities for pipeline overflows. In addition, when pipelines overflow or are damaged, traditional repair methods are often delayed and lack intelligence. Not only is the repair time long, but the effectiveness is difficult to guarantee, which has a significant impact on urban operations, residents' lives and the water environment. Summary of the Invention

[0005] The purpose of the present invention is to make up for the shortcomings of the existing technology and provide a municipal pipe network overflow detection and intelligent repair method. It can realize real-time detection, accurate prediction and intelligent repair of municipal pipe network overflow risks by deeply integrating meteorological and hydrological data and combining intelligent hydrodynamic simulation technology. Specifically, meteorological, hydrological and municipal pipe network related data are collected through widely distributed meteorological sensors, water level sensors and other equipment, and fused and analyzed to establish a correlation model between external environmental change factors and pipe network operation status. Then, a hydrodynamic simulation model is constructed based on the structure and characteristic data of the pipe network, and the water flow in the pipe network under different combinations of meteorological and hydrological conditions is simulated and calculated, so as to predict overflow. The possible location, time and scope of impact of overflow can be determined, and the overflow risk level can be determined. According to the risk level, the system can automatically formulate corresponding pipeline operation parameter control strategies to achieve intelligent control and preventive treatment. At the same time, monitoring equipment is installed at key locations of the pipeline network to monitor the pipeline operation status in real time. Once overflow or pipeline damage is detected, the intelligent repair program is immediately started, and the appropriate repair plan is selected from the pre-established repair database and the repair is implemented. In addition, the system also has early warning, emergency and self-optimization functions, which can promptly issue early warning information to relevant departments, assist in emergency treatment, and continuously optimize the model and improve system performance as data accumulates, providing all-round protection for the safe and stable operation of the municipal pipeline network.

[0006] To solve the above technical problems, the present invention provides the following technical solution: a municipal pipe network overflow detection and intelligent repair method, which includes the following specific steps:

[0007] Data fusion and basic analysis: Utilize multiple sensors to collect various data in real time, fuse and pre-process them in the data processing center, and set thresholds by comparing and analyzing historical and real-time data to identify external environmental factors that affect pipeline network operation and provide basic data.

[0008] Hydrodynamic simulation and risk prediction: A hydrodynamic simulation model is constructed based on various pipeline network data and integrated meteorological and hydrological data. The water flow in the pipeline network under different combinations of meteorological and hydrological conditions is simulated and calculated. The dynamic changes in water flow are analyzed, and the overflow risk level is determined by comprehensively considering the actual flow rate at each location in the pipeline network, drainage capacity, and the influence of external factors;

[0009] Intelligent control and preventive treatment: Develop control strategies based on the risk level of overflow risk assessment, and automatically calculate the pipe network control operating parameters by comprehensively considering the basic control parameter values ​​and control coefficients under different risk levels;

[0010] Overflow detection and intelligent repair: Multiple sensors are installed at key locations in the pipeline network to collect data in real time. The deviation between the actual operating status of the pipeline network and the normal state is calculated to detect overflow or pipeline damage. The situation is confirmed by combining the results of hydrodynamic simulation, and the appropriate repair plan is selected from the database. The intelligent equipment is controlled to repair the problem, and the repair is retested to ensure normal operation.

[0011] Early warning, emergency response, and self-optimization: Based on overflow risk assessments and real-time monitoring results, early warnings with detailed information are issued to relevant departments, and advance planning and assistance are provided for the evacuation of residents in affected areas. At the same time, the system utilizes continuously accumulated new data to optimize parameters and update and repair databases to improve system performance.

[0012] Furthermore, in the data fusion and basic analysis steps, various sensors are used to collect various data in real time, including meteorological, hydrological, municipal pipe network topology, material properties, drainage capacity model and geographic information data, and fused in the data processing center. The fusion formula is: Among them, I is the comprehensive impact index, which is used to measure the comprehensive impact of external environmental factors on the operation of the municipal pipe network. The larger the value, the greater the impact. j is the jth type of external environment data, w j is the weight coefficient corresponding to the jth type of external environmental data, which is determined based on the statistical analysis of the impact of this factor on pipe network overflow in historical data, and m is the number of types of external environment data.

[0013] Furthermore, in the hydrodynamic simulation and risk prediction step, a hydrodynamic simulation model is constructed based on various data of the pipeline network and the integrated meteorological and hydrological data. Specifically, based on the topological structure, material properties, drainage capacity model and geographic information data of the pipeline network, combined with the integrated meteorological and hydrological data, a hydrodynamic simulation model of the municipal pipeline network is established, various meteorological and hydrological data parameters are input, the flow direction of water in the pipeline network is simulated, and the flow velocity distribution and pressure changes at different locations are calculated. By simulating different parameter combinations multiple times, the dynamic change results of water flow in the pipeline network under various conditions are obtained. According to the dynamic change results of water flow obtained by simulation calculation, the location, time and impact range of overflow are analyzed, and an overflow risk assessment index system is established. Taking into account the water flow velocity, pressure and flow factors, different risk level standards are set. By comparing the simulation results with the risk level standards, the overflow risk level of different areas is determined.

[0014] Furthermore, in the hydrodynamic simulation and risk prediction step, the integrated meteorological and hydrological data are combined to establish a hydrodynamic simulation model of the municipal pipe network, and the model formula is: Among them, Q is the flow rate in the pipe network, T is the topological structure factor, which reflects the impact of the layout and connection method of the pipe network on the water flow, M is the material characteristic factor, which reflects the friction resistance of the pipe material to the water flow, C is the drainage capacity factor, which represents the designed drainage capacity of the pipe network and is related to the pipe diameter and slope factors, and I is the meteorological and hydrological factor, which is a comprehensive reflection of the integrated meteorological and hydrological data. max is the maximum possible value of meteorological and hydrological factors, and α is the comprehensive correction coefficient, which is used to adjust the proportional relationship of the entire formula.

[0015] Furthermore, in the hydrodynamic simulation and risk prediction steps, an overflow risk assessment index system is established, and its assessment formula is: Among them, R risk Is the overflow risk coefficient, which is used to indicate the relative size of the overflow risk. The larger the value, the higher the overflow risk. k is the flow rate at the kth location in the pipe network, indicating the volume flow rate of water passing through this location, S k is the drainage capacity of the kth position in the pipe network, reflecting the amount of water that the pipe network at that position can discharge per unit time, δ k is the flow impact weight of the kth location, which is determined based on the importance of the location in the network and its performance in historical overflow events. ω is the comprehensive correction coefficient, which takes into account the combined impact of meteorological and hydrological external factors on the water flow in the network. s is the number of locations in the network used for calculation.

[0016] Furthermore, in the hydrodynamic simulation and risk prediction step, the overflow risk level of different areas is determined by comparing the simulation results with the risk level standard. Specifically, let T low is the low risk threshold, T high is a high risk threshold, and T low <T high , when T low <R risk <T high , judged as low risk, when R risk >T high , judged as high risk.

[0017] Furthermore, in the intelligent control and prevention treatment step, a control strategy is formulated according to the risk level of the overflow risk assessment. When the overflow risk assessment is a low risk level, the system automatically fine-tunes the operating parameters of the drainage pump station and adjusts the pumping frequency or pumping power of the pump station. When the assessment is a high risk level, not only the parameters of the drainage pump station are adjusted, but also the valves in the pipe network are intelligently adjusted. By controlling the opening of the valve, the flow rate of water in different pipe sections is reasonably distributed, the water pressure in the pipe network is balanced, and overflow caused by excessive local pressure is avoided. By comprehensively considering the basic control parameter values ​​and control coefficients under different risk levels, the pipe network control operation parameters are automatically calculated. The calculation formula is: Among them, A ction is the pipe network control operation parameter, representing the specific control operation, A mid is the basic control parameter value under low risk conditions, A high is the basic control parameter value under high risk conditions, η mid is the control coefficient under low risk conditions, which is used to balance the procedures of different control operations under low risk conditions, η high is the control coefficient under high-risk conditions, which is used to fine-tune the control operation under high-risk conditions. risk is the overflow risk coefficient, T low is the low risk threshold, T high is the high risk threshold, which is set based on historical data and experience and is used to determine whether it is a high risk situation, and T low <T high .

[0018] Furthermore, in the overflow detection and intelligent repair step, the deviation between the actual operating state of the pipeline network and the normal state is calculated to detect overflow or pipeline damage, and the calculation formula is: Among them, D eviation It is the deviation of the pipeline network operation state, which is used to measure the deviation between the actual operation state of the pipeline network and the normal operation state. The larger the value, the more serious the deviation, and the more likely it is that overflow or pipeline damage will occur. l.real is the actual value of the lth monitoring indicator in the pipe network, Y l.normal is the value of the lth monitoring indicator in the pipe network when it is operating normally, ρ l is the weight coefficient of the lth monitoring indicator, which is determined according to the importance of the indicator in judging the operation status of the pipeline network, and t is the number of monitoring indicators.

[0019] Compared with existing technologies, this municipal pipe network overflow detection and intelligent repair method has the following beneficial effects:

[0020] 1. The present invention deeply integrates meteorological, hydrological and municipal pipeline network related data, and with the help of intelligent hydrodynamic simulation technology, it can achieve high-precision simulation of water flow in the pipeline network, accurately predict the location, time and impact range of overflow in advance, and based on accurate overflow risk assessment, the system can automatically formulate and adjust the pipeline network operation parameter control strategy in real time. According to the different overflow risk levels, the drainage pump station parameters and pipeline network valve opening are intelligently adjusted, thereby effectively optimizing the pipeline network operation parameters, balancing the water pressure in the pipeline network, avoiding overflow caused by excessive local pressure, significantly reducing the probability of overflow events, reducing urban waterlogging, environmental pollution and other losses caused by overflow, and improving the safety and reliability of municipal pipeline network operation.

[0021] 2. The present invention collects data in real time through monitoring equipment installed at key locations of the pipeline network, uses data analysis algorithms to promptly judge abnormal situations, and accurately determines the location and extent of damage in combination with hydrodynamic simulation results. It can screen out suitable repair plans from pre-established pipeline repair models and databases, control intelligent repair equipment or robots to carry the required materials for repair, and re-test after repair to ensure the effect. At the same time, the system has self-learning and optimization capabilities, and can optimize the overflow risk assessment model, hydrodynamic simulation model and pipeline repair model over time and with the continuous accumulation of data, update the repair database, and add new repair plans and technologies, so that the system can continuously improve the accuracy of predictions and the effectiveness of response measures, and can quickly and efficiently complete repair work in the face of various complex situations to ensure the normal operation of the municipal pipeline network.

[0022] Other advantages, objects and features of the present invention will be described in part in the following description and, in part, will be apparent to those skilled in the art based on an examination of the following or may be learned from the practice of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort.

[0024] Figure 1 This is a process diagram for municipal pipe network overflow detection and intelligent repair methods;

[0025] Figure 2 Flowchart of the municipal pipe network overflow detection and intelligent repair method. DETAILED DESCRIPTION

[0026] In order to further illustrate the technical means and effects adopted by the present invention to achieve the predetermined purpose of the invention, the specific implementation methods, structures, features and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0027] Example 1

[0028] The municipal pipeline network in a certain city's old urban area was built a long time ago. The pipeline network is aging, has a complex layout, and has limited drainage capacity. In recent years, with the development of the city and the increase in extreme weather, the area has frequently experienced pipeline overflow problems, which has had a significant impact on the surrounding environment and residents' lives. The old pipeline network is mostly made of cast iron. After years of use, some sections of the pipes have rusted and damaged, resulting in poor drainage. At the same time, the old urban area is low-lying, and the water level of surrounding rivers is prone to rise during the rainy season, further increasing the risk of pipeline overflow.

[0029] A large number of meteorological sensors, including rain gauges, anemometers, and wind vanes, have been deployed in the old city and its surrounding areas to collect meteorological data such as rainfall, rainfall intensity, wind speed, and wind direction in real time. At the same time, high-precision water level sensors and flow rate sensors have been installed at river and groundwater level monitoring points to obtain hydrological data such as river water level, groundwater level, and water flow rate. These sensors are evenly distributed to ensure the comprehensiveness and accuracy of data collection. The topological structure, material properties, drainage capacity model, and geographic information data of the regional pipeline network are obtained from the municipal pipeline network management department. The collected and acquired data are transmitted to the data processing center for deep integration. Data cleaning algorithms are used to remove duplicate and erroneous data. Data analysis tools are used to analyze the comprehensive data, and the formula is introduced. To calculate the comprehensive impact index I, where X j is the jth type of external environment data, collected by the corresponding sensor, w j is the weight coefficient corresponding to the jth type of external environmental data. The initial value is determined based on the statistical analysis of the impact of this factor on pipe network overflow in historical data and expert experience, and m is the number of types of external environmental data. As time goes by and new data accumulates, historical data is regularly analyzed in depth. Machine learning algorithms are used to train a large amount of historical data to automatically evaluate the changes in the correlation between various factors and overflow events, thereby adjusting the weight w. j At the same time, experts in the field of municipal pipeline networks were organized to conduct discussions. Based on new research results and actual engineering experience, the weights were artificially adjusted to make them more in line with actual conditions. Through the study of historical rainfall and overflow events, it was set that when the I value reached a certain threshold (the analysis determined that the rainfall exceeded 50 mm / hour and the river water level exceeded 80% of the warning water level), it was a high-risk external environmental change factor.

[0030] Based on the fused data, a hydrodynamic simulation model of the municipal pipe network in the old city was established. The model introduced the formula Where Q is the flow rate of a certain node or pipe segment in the pipe network, T reflects the impact of the topological structure of the pipe network on the water flow, which is obtained by analyzing the topological structure of the pipe network, for example, using graph theory algorithms to quantify the connection relationship between the nodes and pipe segments of the pipe network, M reflects the impact of the friction resistance of the pipe material on the water flow, and is calculated based on parameters such as the roughness coefficient of the pipe material, C represents the design drainage capacity of the pipe network, and is calculated based on the design parameters of the pipe network, such as pipe diameter and slope, and I is a comprehensive reflection of the fused meteorological and hydrological data, which can be represented by the comprehensive impact index I obtained by the data fusion and basic analysis steps. max It is the maximum possible value of meteorological and hydrological factors, obtained by statistical analysis of historical meteorological and hydrological data, and the maximum value in historical data is taken as I max , α is the comprehensive correction coefficient, which is used to adjust the proportional relationship of the entire formula. It is determined by regression analysis of historical data. Through numerical calculation methods, the formula is used to simulate the dynamic changes of water flow in the pipe network under different combinations of rainfall intensities and river water levels. After multiple simulations, it was found that in a heavy rainfall event with an expected rainfall of 80 mm / hour, the W value is relatively large. According to the formula, the flow Q of multiple nodes and pipe sections in the pipe network in the low-lying area in the southwest of the old city increased significantly.

[0031] Combined formula Calculate the overflow risk coefficient R isk , where Q k is the flow rate at the kth location in the pipeline network, which is collected in real time by the flow sensor installed at the key location of the pipeline network. k is the drainage capacity of the kth position in the pipe network, which is calculated based on the pipe network topology, material properties, pipe diameter and other data provided by the municipal pipe network management department and combined with relevant hydraulic calculation formulas. k is the flow impact weight of the kth location. The initial value is determined by expert evaluation and data analysis based on factors such as the importance of the location in the pipe network and the performance of the location in historical overflow events. ω is the comprehensive correction coefficient, which is calculated by integrating meteorological data and hydrological data through a specific analysis model. s is the number of locations used for calculation in the pipe network, which is determined according to the number of calculation locations actually divided in the pipe network. After each simulation, the simulation results are compared and analyzed with the actual overflow events. If it is found that the predicted risk of some locations deviates greatly from the actual situation, the weight δ of the corresponding location is adjusted by analyzing the water flow characteristics, surrounding environment and other factors at that location. kFor the comprehensive correction coefficient ω, the analysis model is updated and optimized based on the new meteorological and hydrological data, as well as the research results on the impact of pipe network water flow, so as to adjust the value of ω. The actual monitoring data and simulation results are continuously used for comparative analysis to optimize the weights and coefficients and improve the accuracy of the model. The calculation results show that the R risk The value exceeds the set high-risk threshold. The model predicts that the water flow velocity in the pipeline network in this area will increase significantly, the pressure will exceed the normal range, and there will be a high overflow risk. The risk level is judged to be high risk. At the same time, the simulation results also show that several key nodes around the area may experience water blockage, further exacerbating the overflow risk.

[0032] According to the risk prediction results, the system automatically executes high-risk control strategies and introduces the formula To determine the pipe network control operating parameter A ction , where A ction is the pipe network control operation parameter, representing the specific control operation, A mid is the basic control parameter value under low risk conditions, A high is the basic control parameter value under high risk conditions, η mid is the control coefficient under low risk conditions, which is used to balance the procedures of different control operations under low risk conditions, η high is the control coefficient under high-risk conditions, which is used to fine-tune the control operation under high-risk conditions. risk is the overflow risk coefficient, T low is the low risk threshold, T high is the high risk threshold, which is set based on historical data and experience and is used to determine whether it is a high risk situation, and T low <T high , due to R isk >T high , the system determines A ction The value is A high ×η high On the one hand, the pumping power of the drainage pump station near the area is increased to 90% of the maximum rated power (i.e. according to A high ×η high The calculated parameter adjustment value) increases the pumping speed. At the same time, the operating status of the pump station is monitored in real time to ensure the stability of the equipment under high load operation. On the other hand, the opening of the relevant valves is intelligently adjusted to reduce the valve opening near the overflow risk area by 30% (also based on A high ×η highThe calculated parameter adjustment value is used to guide water flow to areas with stronger drainage capacity. During the valve adjustment process, the valve status and water flow changes are fed back in real time through sensors installed at the valve to ensure the accuracy of the regulation. During the actual regulation process, the water level, pressure, flow and other parameter changes in the pipe network are continuously monitored to evaluate the regulation effect. If it is found that the regulation measures at low risk are not effective, such as failing to effectively reduce the water level in the pipe network, or excessive regulation leading to energy waste, etc., the relationship between the regulation parameters and the actual effect is analyzed to adjust η. low The low-risk control strategy is optimized according to the value of η. For medium and high-risk situations, the η is adjusted according to the changes in parameters such as pipe network water level and pressure, as well as the prevention effect of overflow events. mid and η high The feedback control method is used to automatically adjust the control coefficient according to the difference between the actual control effect and the expected effect, so as to achieve precise control of the pipeline network.

[0033] High-precision pressure sensors and flow sensors are installed at key locations of the pipe network to monitor the operation status of the pipe network in real time. These sensors have the characteristics of high sensitivity and fast response, and can capture small changes in the pipe network in time. Calculate the pipe network operation status deviation D eviation , where Y l,real is the actual value of the lth monitoring indicator in the pipe network, such as actual flow, actual pressure, etc., which is collected in real time by the corresponding sensor, Y l.normal is the value of the lth monitoring indicator in the pipeline network when it is operating normally. It is obtained through statistical analysis and model calculation based on the monitoring indicator data of the pipeline network in normal operation in historical data. l is the weight coefficient of the lth monitoring indicator. The initial value is determined by expert evaluation and data analysis based on the importance of the indicator in judging the operation status of the pipeline network, and t is the number of monitoring indicators. When a new overflow or pipe network damage event occurs, the performance of each monitoring indicator in the event is analyzed in detail, and the actual situation is compared with the results calculated based on the current weights. If it is found that some indicators play a more critical role in the event, but the current weight is low, then their weights are appropriately increased. Otherwise, the weights are reduced. At the same time, with the development of monitoring technology and the in-depth understanding of the pipe network operation mechanism, the understanding of the importance of each indicator may change, and the weight ρ should be adjusted accordingly. l , using machine learning methods to analyze a large amount of monitoring data and event records, automatically adjusting weights to improve the accuracy of overflow detection. During heavy rainfall, when the calculated D eviationWhen the value exceeds the set threshold, it is found that the pressure of a certain section of the pipeline increases abnormally and the flow suddenly decreases. The system determines that the pipeline may be blocked and immediately starts the intelligent repair program. It dispatches a dredging robot to the location to clean the pipeline. The dredging robot is equipped with advanced detection equipment and cleaning tools, which can accurately find the blockage location and efficiently remove debris. After the dredging is completed, the pressure and flow in the pipeline are tested again to confirm that they have returned to normal. At the same time, the pipeline is comprehensively inspected to assess whether there are other potential problems. The relevant data is recorded to provide a reference for subsequent maintenance and management.

[0034] The system promptly issues early warning information to municipal management departments, environmental protection departments and surrounding residents, informing them of the areas where overflow may occur and the risk level. The early warning information details the expected overflow time, the scope of impact and the preventive measures to be taken. At the same time, it assists relevant departments in planning residents' evacuation routes and emergency shelters in advance, sets up obvious evacuation signs in areas that may be affected, and organizes residents to conduct emergency drills to improve their emergency awareness and response capabilities. Over time, the system continuously accumulates new rainfall, pipeline operation and repair data, optimizes the overflow risk assessment model, hydrodynamic simulation model and pipeline repair model, and improves the accuracy of the prediction and the effectiveness of the repair plan. In subsequent rainfall events, the control strategy is adjusted according to the optimized model, which effectively reduces the probability of overflow events. For example, through analysis of historical data, it is found that the drainage capacity of some areas has improved after repair and renovation. The system adjusts the overflow risk assessment indicators and control parameters of these areas accordingly.

[0035] It can be seen from the above embodiments that the municipal pipeline overflow detection and intelligent repair method of the present invention, when applied in the old urban area of ​​the city, can effectively cope with complex pipeline conditions and external environmental changes, timely discover and deal with overflow risks, and ensure the normal operation of the city and the safety of residents' lives.

[0036] Example 2

[0037] A newly developed commercial district in a certain city covers a vast area and includes a variety of commercial formats such as shopping malls, office buildings, and hotels. The municipal pipeline network is built according to modern standards. However, due to the intensive commercial activities and large traffic volume in the area, high drainage capacity and stability requirements are required for the pipeline network. In addition, other construction projects are underway in the vicinity of the new commercial district, which may have a certain impact on the pipeline network. To prevent possible pipeline overflow problems, the method of the present invention is applied for management.

[0038] Multiple meteorological monitoring stations and hydrological monitoring points have been set up in and around the commercial area. The meteorological monitoring stations are equipped with advanced meteorological sensors, including high-precision rain gauges, wind speed and direction meters, etc., which collect meteorological data such as rainfall, rainfall intensity, wind speed, and wind direction in real time. The hydrological monitoring points are equipped with water level sensors and flow rate sensors, which can accurately obtain hydrological data such as river water level, groundwater level, and water flow rate. These monitoring equipment transmit data to the data processing center in real time through wireless communication technology.

[0039] At the same time, the detailed pipeline network topology, material properties (using new corrosion-resistant materials with good anti-aging and anti-wear properties), drainage capacity model and geographic information data of the area are obtained. After integrating these data, professional data processing software is used to conduct in-depth analysis of the comprehensive data. Through the study of historical meteorological and hydrological data, it is found that when the wind speed exceeds 10 meters per second and the wind direction is not conducive to the diffusion of rainwater, combined with factors such as rainfall, it may have an impact on the operation of the pipeline network. Relevant thresholds are set. For example, when the rainfall reaches 20 mm / hour and the wind speed exceeds 10 meters per second, it is used as an external environmental change factor that may affect the operation of the pipeline network, providing basic data for overflow risk assessment.

[0040] A hydrodynamic simulation model of the commercial district's municipal pipeline network was established. This model fully considered factors such as the district's building layout, the material properties of the pipeline network, drainage capacity, and geographic information. Using numerical calculation methods, the model simulated water flow within the pipeline network under different meteorological and hydrological conditions. During the simulation, each node and segment of the pipeline network was analyzed in detail to calculate the flow direction, velocity, and pressure distribution. In one simulation, considering the district's building layout and pipeline network characteristics, it was predicted that under a sustained rainfall event with rainfall reaching 30 mm / hour, the pipeline network near the central square of the commercial district might experience localized flow congestion, posing a certain overflow risk. The risk level was determined to be low. The simulation results also revealed that the drainage connection method for some shops around the square might be unreasonable, exacerbating the water flow problem in this area. The system implemented a control strategy for this low-risk scenario. First, the operating parameters of the drainage pump station were adjusted, increasing the pumping frequency by 20% to reduce the water level in the pipeline network. The drainage pump station is equipped with an intelligent control system that automatically adjusts the pumping frequency based on water level changes within the pipeline network, ensuring efficient operation under various operating conditions.

[0041] At the same time, the valve opening is adjusted intelligently, and the valve opening around the square is adjusted appropriately to balance the water pressure of each pipe section and ensure the reasonable distribution of water flow. The valve adopts an electric valve and is operated by a remote control system. It can accurately control the valve opening. In the process of adjusting the valve, the water pressure and flow changes before and after the valve are monitored in real time, and fine-tuning is performed according to actual conditions. In the process of regulation, the operation status of the pipeline network is continuously monitored, and sensors installed at key positions of the pipeline network are used to collect pressure, flow and other data in real time. The data is transmitted to the data analysis system for analysis. According to the analysis results, the regulation parameters are dynamically adjusted to achieve the best regulation effect.

[0042] High-precision sensors are installed to monitor pipe network pressure and flow in real time. These sensors have an automatic calibration function, which can ensure the accuracy and reliability of the data. During a rainfall event, a newly laid pipe was found to have abnormal pressure fluctuations. After inspection, it was found that the pipe was partially blocked due to debris left over from construction. The system quickly launched an intelligent repair program and used a small silt removal device to clean the pipe. The silt removal device was equipped with a high-definition camera and a robotic arm, which can accurately locate the blockage and remove the debris. During the cleaning process, the silt removal was monitored in real time by the camera to ensure that the cleaning work was completed thoroughly. After the cleaning was completed, the pressure and flow of the pipe were tested again to confirm that it had returned to normal. At the same time, the material and connection parts of the pipe were inspected to ensure that they were not damaged. The relevant data of this blockage incident was recorded to provide a reference for subsequent pipe network maintenance.

[0043] When it is detected that the risk level reaches the warning standard, the system will send a warning message to the commercial district management department and relevant merchants, reminding them to make preventive preparations. The warning information includes possible overflow situations, the scope of impact, and recommended measures, such as closing doors and windows of shops in low-lying areas and preparing drainage equipment. At the same time, it assists in formulating emergency plans, such as preparing sandbags, drainage pumps and other emergency supplies at important locations in the commercial district, and organizing relevant personnel to conduct emergency training to improve the ability to respond to sudden overflow incidents.

[0044] With the development of commercial areas and the increase in pipeline operation data, the system continuously optimizes the model. Through analysis of new data, it is found that the drainage demand in certain areas varies with changes in commercial activities. The system adjusts the overflow risk assessment indicators and control strategies of these areas accordingly. For example, in response to the large flow of people in shopping malls during holidays and the increased demand for drainage, the operating parameters and valve openings of the drainage pump station are adjusted in advance to ensure the normal operation of the pipeline network.

[0045] The above embodiments demonstrate the effective application of the municipal pipe network overflow detection and intelligent repair method of the present invention in newly developed commercial areas, which can timely discover and solve problems arising from pipe network operation, and ensure the normal operation and environmental safety of the commercial area.

[0046] The above description is merely a preferred embodiment of the present invention and does not constitute any form of limitation to the present invention. Although the present invention has been disclosed as above in terms of a preferred embodiment, it is not intended to limit the present invention. Any person skilled in the art can, without departing from the scope of the technical solution of the present invention, make some changes or modifications to equivalent embodiments using the technical contents disclosed above. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. A municipal pipe network overflow detection and intelligent repair method, characterized in that: The method comprises the following specific steps: Data fusion and basic analysis: Utilize multiple sensors to collect various data in real time, fuse and pre-process them in the data processing center, and set thresholds by comparing and analyzing historical and real-time data to identify external environmental factors that affect pipeline network operation and provide basic data. Hydrodynamic simulation and risk prediction: A hydrodynamic simulation model is constructed based on various pipeline network data and integrated meteorological and hydrological data. The water flow in the pipeline network under different combinations of meteorological and hydrological conditions is simulated and calculated. The dynamic changes in water flow are analyzed, and the overflow risk level is determined by comprehensively considering the actual flow rate at each location in the pipeline network, drainage capacity, and the influence of external factors; Intelligent control and preventive treatment: Develop control strategies based on the risk level of overflow risk assessment, and automatically calculate the pipe network control operating parameters by comprehensively considering the basic control parameter values ​​and control coefficients under different risk levels; Overflow detection and intelligent repair: Multiple sensors are installed at key locations in the pipeline network to collect data in real time. The deviation between the actual operating status of the pipeline network and the normal state is calculated to detect overflow or pipeline damage. The situation is confirmed by combining the results of hydrodynamic simulation, and the appropriate repair plan is selected from the database. The intelligent equipment is controlled to repair the problem, and the repair is retested to ensure normal operation. Early warning, emergency response, and self-optimization: Based on overflow risk assessments and real-time monitoring results, early warnings with detailed information are issued to relevant departments, and advance planning and assistance are provided for the evacuation of residents in affected areas. At the same time, the system utilizes continuously accumulated new data to optimize parameters and update and repair databases to improve system performance.

2. The municipal pipe network overflow detection and intelligent repair method according to claim 1, characterized in that: In the data fusion and basic analysis steps, various sensors are used to collect various data in real time, including meteorological, hydrological, municipal pipe network topology, material properties, drainage capacity model and geographic information data, and fused in the data processing center. The fusion formula is: Among them, I is the comprehensive impact index, which is used to measure the comprehensive impact of external environmental factors on the operation of the municipal pipe network. The larger the value, the greater the impact. j is the jth type of external environment data, w j is the weight coefficient corresponding to the jth type of external environmental data, which is determined based on the statistical analysis of the impact of this factor on pipe network overflow in historical data, and m is the number of types of external environment data.

3. The municipal pipe network overflow detection and intelligent repair method according to claim 1, characterized in that: In the hydrodynamic simulation and risk prediction step, a hydrodynamic simulation model is constructed based on various data of the pipeline network and the integrated meteorological and hydrological data. Specifically, based on the topological structure, material properties, drainage capacity model and geographic information data of the pipeline network, combined with the integrated meteorological and hydrological data, a hydrodynamic simulation model of the municipal pipeline network is established, various meteorological and hydrological data parameters are input, the flow direction of water in the pipeline network is simulated, and the flow velocity distribution and pressure changes at different locations are calculated. By simulating different parameter combinations multiple times, the dynamic change results of water flow in the pipeline network under various conditions are obtained. According to the dynamic change results of water flow obtained by simulation calculation, the location, time and impact range of overflow are analyzed, and an overflow risk assessment index system is established. Taking into account the water velocity, pressure and flow factors, different risk level standards are set. By comparing the simulation results with the risk level standards, the overflow risk level of different areas is determined.

4. The municipal pipe network overflow detection and intelligent repair method according to claim 2, characterized in that: In the hydrodynamic simulation and risk prediction step, the integrated meteorological and hydrological data are combined to establish a hydrodynamic simulation model for the municipal pipe network. The model formula is: Among them, Q is the flow rate in the pipe network, T is the topological structure factor, which reflects the impact of the layout and connection method of the pipe network on the water flow, M is the material characteristic factor, which reflects the friction resistance of the pipe material to the water flow, C is the drainage capacity factor, which represents the designed drainage capacity of the pipe network and is related to the pipe diameter and slope factors, and I is the meteorological and hydrological factor, which is a comprehensive reflection of the integrated meteorological and hydrological data. max is the maximum possible value of meteorological and hydrological factors, and α is the comprehensive correction coefficient, which is used to adjust the proportional relationship of the entire formula.

5. The municipal pipe network overflow detection and intelligent repair method according to claim 3, characterized in that: In the hydrodynamic simulation and risk prediction steps, an overflow risk assessment index system is established, and its assessment formula is: Among them, R risk Is the overflow risk coefficient, which is used to indicate the relative size of the overflow risk. The larger the value, the higher the overflow risk. k is the flow rate at the kth location in the pipe network, indicating the volume flow rate of water passing through this location, S k is the drainage capacity of the kth position in the pipe network, reflecting the amount of water that the pipe network at that position can discharge per unit time, δ k is the flow impact weight of the kth location, which is determined based on the importance of the location in the network and its performance in historical overflow events. ω is the comprehensive correction coefficient, which takes into account the combined impact of meteorological and hydrological external factors on the water flow in the network. s is the number of locations in the network used for calculation.

6. The municipal pipe network overflow detection and intelligent repair method according to claim 5, characterized in that: In the hydrodynamic simulation and risk prediction step, the overflow risk level of different areas is determined by comparing the simulation results with the risk level standard. Specifically, let T low is the low risk threshold, T high is a high risk threshold, and T low <T high , when T low <R risk <T high , judged as low risk, when R risk >T high , judged as high risk.

7. The municipal pipe network overflow detection and intelligent repair method according to claim 6, characterized in that: In the intelligent control and prevention treatment step, a control strategy is formulated based on the risk level of the overflow risk assessment. When the overflow risk assessment is a low risk level, the system automatically fine-tunes the operating parameters of the drainage pump station and adjusts the pumping frequency or pumping power of the pump station. When the assessment is a high risk level, not only the parameters of the drainage pump station are adjusted, but also the valves in the pipe network are intelligently adjusted. By controlling the opening of the valves, the flow rate of water in different pipe sections is reasonably distributed, the water pressure in the pipe network is balanced, and overflow caused by excessive local pressure is avoided. By comprehensively considering the basic control parameter values ​​and control coefficients under different risk levels, the pipe network control operation parameters are automatically calculated. The calculation formula is: Among them, Action is the pipe network control operation parameter, representing the specific control operation, Amid is the basic control parameter value under low risk conditions, A high is the basic control parameter value under high risk conditions, ηmid is the control coefficient under low risk conditions, which is used to balance the procedures of different control operations under low risk conditions, and η high is the control coefficient under high-risk conditions, which is used to fine-tune the control operation under high-risk conditions. risk is the overflow risk coefficient, T low is the low risk threshold, T high is the high risk threshold, which is set based on historical data and experience and is used to determine whether it is a high risk situation, and T low <T high .

8. The municipal pipe network overflow detection and intelligent repair method according to claim 1, characterized in that: In the overflow detection and intelligent repair step, the deviation between the actual operating state of the pipe network and the normal state is calculated to detect overflow or pipe network damage. The calculation formula is: Among them, D eviation It is the deviation of the pipeline network operation state, which is used to measure the deviation between the actual operation state of the pipeline network and the normal operation state. The larger the value, the more serious the deviation, and the more likely it is that overflow or pipeline damage will occur. l.real is the actual value of the lth monitoring indicator in the pipe network, T l.normal is the value of the lth monitoring indicator in the pipe network when it is operating normally, ρ l is the weight coefficient of the lth monitoring indicator, which is determined according to the importance of the indicator in judging the operation status of the pipeline network, and t is the number of monitoring indicators.

Images