Urban drainage pipe network operation safety assessment method and system

Abstract

The invention relates to the field of urban drainage, and discloses an urban drainage pipe network operation safety assessment method and system, and the method comprises the steps: obtaining pipe network operation state data and pipe network physical structure data, and constructing a drainage pipe network GIS database; acquiring a pipeline defect detection image based on CCTV television detection and QV video detection technologies, and importing the pipeline defect detection image into a GIS system; performing model calibration dynamic simulation on the constructed drainage hydraulic model based on the data in the GIS and the real-time operation monitoring data of the drainage pipe network to obtain drainage pipe hydraulic data; performing defect evaluation on the sewage pipe network, the rainwater pipe network and the confluence pipe network by adopting different safety level models based on the drainage pipe hydraulic data; based on the corresponding defect probability, the risk is divided into a first-level risk, a second-level risk and a third-level risk; analyzing the pairwise variable relationship to find key indexes influencing the risk; and matching a corresponding coping strategy based on the key index influencing the risk, and displaying the coping strategy.

Description

Technical Field

[0001] The present invention relates to the field of urban drainage, and in particular to a method and system for evaluating the operation safety of an urban drainage network. Background Art

[0002] Urban domestic sewage treatment is a key means of reducing pollutant emissions from urban water systems. Urban sewage treatment plants and their supporting pipeline networks are crucial components of urban environmental infrastructure, playing a crucial role in controlling urban water pollution and improving the water environment. With sewage systems in many central urban areas largely complete, the focus of sewage treatment efforts has shifted from facility construction to facility management and improving system quality and efficiency.

[0003] However, the current sewage network faces numerous challenges. Its wide service area, large pipelines, and complex system lack scientifically sound interconnections. This makes timely detection of sewage system incidents difficult, forcing the system to resort to passive emergency response measures. This leads to extremely low efficiency, severely restricting the safe operation of the sewage system and even negatively impacting the normal functioning of the city. Therefore, regular sewage system risk assessments are necessary, and maintenance strategies should be developed based on the system's risk level.

[0004] How to solve the above technical problems is a technical difficulty that needs to be overcome by those skilled in the art. Summary of the Invention

[0005] The present invention provides a method and system for evaluating the operation safety of an urban drainage network, so as to at least partially solve the above-mentioned technical problems.

[0006] In a first aspect, in order to solve the above technical problems, the present invention provides a method for evaluating the operation safety of an urban drainage network, comprising:

[0007] Obtain the pipe network operation status data and pipe network physical structure data to build the drainage pipe network GIS database;

[0008] Obtain pipeline defect detection images based on CCTV television detection and QV video detection technology and import them into the GIS system to obtain the pipeline structural health index;

[0009] Based on the data in the GIS system and the real-time operation monitoring data of the drainage network, the constructed drainage hydraulic model is calibrated and dynamically simulated to obtain the drainage pipe hydraulic data;

[0010] Based on drainage pipe hydraulic data, different safety hierarchical models are used to conduct defect assessments on sewage pipe networks, stormwater pipe networks, and combined pipe networks. Based on the corresponding defect probabilities, these risks are divided into first-level, second-level, and third-level risks. The first-level risk is more risky than the second-level risk; the second-level risk is more risky than the third-level risk.

[0011] For the first and second level risks, analyze the relationship between paired variables to find the key indicators that affect the risks;

[0012] Match corresponding response strategies based on key indicators that affect risks and display the response strategies.

[0013] 8. In an optional embodiment, the method further comprises: a topological analysis step of the drainage hydraulic model, specifically comprising:

[0014] The various drainage facilities in the drainage system are classified into three types of objects: pipelines, nodes, and regions. Pipelines are used to represent drainage pipes; nodes are used to represent connection points, inspection wells, and pumping stations in drainage pipes; and regions are used to represent catchment areas and receiving bodies.

[0015] Constructing an urban drainage topology logic model based on the classified object categories of drainage facilities; the urban drainage topology logic model is used to sort out the topological relationships between various types of facilities in the drainage system;

[0016] A drainage hydraulic model is constructed, wherein the drainage hydraulic model is used to simulate the movement and changes of water flow in the drainage system.

[0017] 9. In an optional embodiment, the step of generating the security hierarchy model includes:

[0018] Use one or more combinations of convolutional neural networks, recurrent neural networks, and long short-term memory networks to build the initial model;

[0019] The pipe section data of the first-level risk, second-level risk, and third-level risk are divided into a training set, a validation set, and a test set in proportion. The training set is used to train the initial model so that it learns the characteristics corresponding to different defect types; the validation set is used to adjust the initial model parameters to prevent the model from overfitting; and the test set is used to evaluate the performance of the initial model;

[0020] Use the training set to train the initial model, and continuously adjust the initial model parameters during the training process to continuously improve the model's ability to identify pipeline defects. Use the validation set to verify the initial model during training, and optimize the initial model based on the verification results.

[0021] The trained initial model is used as a safety hierarchy model to process pipeline defects, identify different types of defects, and count the number and location information of each type of defects based on the identification results.

[0022] 10. In an optional embodiment, the pipe segment damage rate, pipe segment siltation rate, and rainwater-sewage mixing rate of the pipe network are obtained, including:

[0023] The calculation formula of pipe section damage rate P is: Where P is the pipe breakage rate; L P is the length of the damaged pipe section; L Z is the total pipe length; the pipe damage rate is calculated by adding the length of the identified damaged pipe section to the total pipe length;

[0024] The calculation formula of pipe section siltation rate S is: Where D is the outer diameter of the pipe, d is the inner diameter of the pipe, L is the length of the pipe, ρ is the silt density, V 管 is the pipe volume; the pipe section siltation rate is calculated based on the identified internal siltation of the pipe and the size parameters of the pipe;

[0025] For the stormwater pipe network, the calculation formula for sewage mixing density is: Mixed water ratio C Where n is the number of sewage mixing points or users in the stormwater pipe network, N is the total number of drainage users in the drainage pipe network service area, q is the total amount of sewage mixing water in the stormwater pipe network obtained from the survey, and Q is the total sewage generation in the surveyed area;

[0026] For sewage pipe networks, the formula for calculating rainwater mixing density is: Mixed water ratio Where n is the number of rainwater mixed users in the sewage network, Q 雨 is the amount of water delivered by the sewage network on rainy days, and Q is the total sewage generated in the surveyed area.

[0027] In an optional embodiment, for the first-level risk and the second-level risk, the relationship between paired variables is analyzed to find key indicators that affect the risk, including:

[0028] Extract variables related to first- and second-level risks from the drainage network GIS database, defect detection results, and data from topological analysis and hydraulic modeling. These variables include pipeline physical characteristics, environmental factors, hydraulic conditions, and pipeline defect-related variables.

[0029] The extracted variable data were cleaned to remove outliers and missing values; missing values ​​were processed by filling in the mean;

[0030] Standardize different types of variables;

[0031] According to the type and distribution characteristics of the variables, the corresponding correlation analysis method was selected; for continuous variables, the Pearson correlation coefficient method was used; for non-normally distributed continuous variables or ordered categorical variables, the Spearman rank correlation coefficient method was used; for nominal categorical variables, the chi-square test was used to analyze the association between variables;

[0032] Combine the selected variables in pairs and calculate the correlation coefficient between each pair of variables;

[0033] The calculated correlation coefficient is tested for significance according to the pre-set significance level; pairs of variables that pass the significance test and whose absolute value of the correlation coefficient is greater than the set threshold are determined to be significantly correlated variables;

[0034] Based on significantly correlated paired variables, a variable association network is constructed. In the network, each variable is a node, and the lines between nodes represent the significant correlation between the variables. The thickness of the lines is set according to the size of the correlation coefficient.

[0035] Using network analysis methods, we conducted a structural analysis of the constructed variable association network. We calculated the degree centrality, betweenness centrality, and closeness centrality of the nodes. Degree centrality reflects the number of connections a node has with other nodes. Nodes with high degree centrality have significant connections with multiple other nodes in the network. Betweenness centrality measures a node's ability to act as an intermediary for the shortest path between other nodes in the network. Closeness centrality indicates the degree of proximity of a node to other nodes in the network.

[0036] Based on the physical significance of the variables in the actual operation of the drainage network and the structural characteristics of the variable association network, the importance of each variable is evaluated; a variable importance evaluation model is established to combine the physical significance weight of the variable and the network structure index weight to calculate the importance score of each variable;

[0037] All variables are ranked according to their importance scores; a preset proportion of variables ranked high are selected as key indicators affecting risk.

[0038] In an optional embodiment, matching corresponding response strategies based on key indicators affecting risk and displaying the response strategies include:

[0039] Collect and organize relevant experience, industry standards, expert advice, and historical cases in urban drainage network operation and maintenance to build a knowledge base of response strategies;

[0040] Classify and annotate the response strategies in the knowledge base, and categorize them according to the type of key indicators and risk level;

[0041] Develop corresponding matching rules for each key indicator that affects risk;

[0042] According to the key indicators affecting the risk and their current values, the corresponding response strategies are selected from the response strategy knowledge base according to the matching rules.

[0043] In an optional embodiment, constructing an urban drainage topology logic model based on the classified object categories of drainage facilities includes:

[0044] A graph data structure is used to represent the topological relationship of the drainage system; pipelines are regarded as edges in the graph, nodes as vertices in the graph, and regions as attribute information associated with nodes or pipelines;

[0045] Based on the actual operation logic of the drainage system, the topological relationship between various facilities is sorted out; the flow direction of the pipeline is clarified for the connection relationship between pipelines and nodes; for the relationship between the area, pipelines and nodes, the distribution of pipelines in the catchment area and the connection location between the receiving body and the pipeline are determined;

[0046] Verify the constructed urban drainage topology logic model using known actual operation data of the drainage system or historical cases; check whether the connection relationship between pipelines and nodes in the model conforms to the actual water flow path, and whether the association between the area and drainage facilities is accurate;

[0047] Use hydraulic simulation software to simulate the flow path of water in the drainage system based on the constructed topological logic model; compare the simulation results with the actual monitored water flow data to check whether the water flows according to the topological relationship set by the model, and whether there is any abnormal water flow convergence or diversion; if the simulation results do not match the actual situation, check the errors in the topological relationship in the model and correct them.

[0048] In a second aspect, the present invention provides a device for evaluating the operation safety of an urban drainage network, comprising:

[0049] The first processing module is used to obtain the pipe network operation status data and the pipe network physical structure data to build a drainage pipe network GIS database;

[0050] The second processing module is used to obtain pipeline defect detection images based on CCTV television detection and QV video detection technology and import them into the GIS system to obtain the pipeline structure health index;

[0051] The third processing module is used to: perform model calibration and dynamic simulation on the constructed drainage hydraulic model based on the data in the GIS system and the real-time operation monitoring data of the drainage network to obtain the drainage pipe hydraulic data;

[0052] The fourth processing module is configured to: perform defect assessments on the sewage pipe network, the rainwater pipe network, and the combined pipe network using different safety hierarchy models based on the hydraulic data of the drainage pipes; and classify the defects into first-level risk, second-level risk, and third-level risk based on the corresponding defect probabilities; the first-level risk has a greater risk level than the second-level risk; the second-level risk has a greater risk level than the third-level risk;

[0053] A fifth processing module is configured to: for the first-level risk and the second-level risk, analyze the relationship between paired variables to find key indicators that affect the risk;

[0054] The sixth processing module is used to match corresponding response strategies based on key indicators affecting risks and display the response strategies.

[0055] In a third aspect, the present invention also provides an electronic device comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, it implements any one of the above-mentioned methods for evaluating the operation safety of an urban drainage network.

[0056] In a fourth aspect, the present invention also provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned methods for evaluating the operation safety of an urban drainage network.

[0057] Compared with the existing technology, the present invention has at least the following beneficial effects: discovering potential risks of the pipeline network in advance and ensuring the safe and stable operation of the pipeline network. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 This is a flow chart of a method for evaluating the operation safety of an urban drainage network provided by the first embodiment of the present invention;

[0059] Figure 2 It is a structural diagram of a device for evaluating the operation safety of an urban drainage network provided by the second embodiment of the present invention. DETAILED DESCRIPTION

[0060] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0061] Reference Figure 1 The first embodiment of the present invention provides a method for evaluating the operation safety of an urban drainage network, comprising the following steps:

[0062] S101, obtaining pipe network operation status data and pipe network physical structure data to build a drainage pipe network GIS database.

[0063] Specifically, the operational status of urban drainage networks is influenced by a variety of factors, and obtaining comprehensive and accurate data is fundamental to their evaluation. Network operational status data includes real-time monitoring data such as flow, water level, water quality, and pressure. This data, acquired through monitoring equipment installed at key nodes in the drainage network, reflects the network's operational status at various times. Network physical structure data encompasses pipe material, diameter, length, slope, and connection method, determining the network's fundamental physical properties and drainage capacity.

[0064] To build a GIS (Geographic Information System) database for the drainage network, multi-channel data collection is necessary. First, online monitoring data is collected, utilizing a sensor network to collect real-time information such as flow and water levels at each network node. Second, regular manual inspections are used to obtain manual inspection data, such as flow and water quality during specific time periods. Furthermore, pipeline design drawings, historical maintenance records, and GIS data for the area are collected; these data provide richer context for the assessment. For areas of the network where the status is unknown, professional personnel conduct on-site surveys and inspections to obtain actual data on conditions such as cracks, blockages, and corrosion. The collected data may contain outliers, duplicates, and missing values, necessitating the application of data cleaning algorithms. This removes outliers and fills in missing data to ensure data accuracy and completeness. The cleaned data, using codes generated from the coordinates of pipeline points (or pipeline start and end points) as unique identifiers, is integrated with health data to construct a drainage network GIS database. This database not only effectively stores network data but also leverages the powerful spatial analysis capabilities of GIS to intuitively display the spatial distribution and operational status of the network.

[0065] S102, based on CCTV television detection and QV video detection technology, pipeline defect detection images are obtained and imported into the GIS system to obtain the pipeline structure health index.

[0066] Specifically, the pipeline structural health index includes the pipe segment damage rate, pipe segment siltation rate, and the network's rainwater-sewage mixing rate. CCTV and QV video inspection technologies are important means of obtaining information about the internal condition of drainage networks. CCTV inspection uses a camera moving inside the pipeline to capture images of the interior, clearly demonstrating the condition of the pipeline's inner wall, including the presence of defects such as cracks, deformation, and damage. QV video inspection utilizes rapid inspection equipment to rapidly scan the pipeline, obtaining intuitive video images that can promptly identify obvious defects. After obtaining pipeline defect detection images using these two technologies, the images require preprocessing. First, they are screened and deleted to remove blurry and invalid image information. Then, denoising and enhancement are performed to highlight key pipeline features, such as the pipeline name, diameter, manhole name, and manhole bottom elevation data. The preprocessed images are imported into a GIS system and combined with the network's spatial data to facilitate the subsequent location and analysis of pipeline defects.

[0067] S103, based on the data in the GIS system and the real-time operation monitoring data of the drainage pipe network, a model calibration dynamic simulation is performed on the constructed drainage hydraulic model to obtain the drainage pipe hydraulic data.

[0068] S104, based on the hydraulic data of the drainage pipes, different safety hierarchy models are used to conduct defect assessment on the sewage network, rainwater network, and combined network; based on the corresponding defect probabilities, the risks are divided into first-level risk, second-level risk, and third-level risk; the risk level of the first-level risk is greater than that of the second-level risk; the risk level of the second-level risk is greater than that of the third-level risk.

[0069] Specifically, different safety level models are adopted for sewage pipe networks, rainwater pipe networks, and combined pipe networks.

[0070] The sewage network safety hierarchy model is divided into two levels. The first level selects four evaluation dimensions: pipe segment physical factors, environmental factors, hydraulic conditions, and pipeline defects. The second level selects 12 key evaluation indicators, as follows: ① Four physical factors: pipe material, pipe diameter, burial depth, and pipe age; ② Three environmental factors: road grade, geological hazard risk, and subway impact; ③ Two hydraulic conditions: daily cumulative flow rate and overload status. Excessive flow or overload can lead to overflow pollution. An overload status of less than 1 is equivalent to fullness; an overload status of 1 indicates a hydraulic gradient less than the pipe gradient; an overload status of 2 indicates a hydraulic gradient greater than the pipe gradient; ④ Three pipeline defect factors: pipe segment damage rate, pipe segment siltation rate, and the network's rainwater-sewage mixing rate.

[0071] The safety hierarchy model for stormwater and combined sewer networks is divided into two levels. The first level selects five evaluation dimensions: pipe segment physical factors, environmental factors, hydraulic conditions, pipe defects, and rainwater collection conditions. The second level selects 17 key evaluation indicators, as follows: ① Four physical factors: pipe material, pipe diameter, burial depth, and pipe age; ② Three environmental factors: road grade, geological hazard risk, and subway impact; ③ Four hydraulic conditions: daily cumulative flow, overload status, duration of surface flooding during rainy days, and depth of accumulated water; ④ Three pipeline defect factors: pipe segment damage rate, pipe segment siltation rate, and network rainwater-sewage mixing rate; ⑤ Three rainwater collection conditions: stormwater inlet blockage rate, manhole integrity rate, and rainwater storage rate.

[0072] S105: For the first-level risk and the second-level risk, analyze the relationship between paired variables to find key indicators that affect the risk.

[0073] Specifically, the first level of risk indicates that there are serious defects in the pipe section, which poses a greater threat to the safety of pipeline network operation; the second level of risk is second; and the third level of risk indicates that the defects in the pipe section are relatively minor.

[0074] S106: Match corresponding response strategies based on key indicators affecting the risk and display the response strategies.

[0075] In one embodiment, the method further includes: a topological analysis step of the drainage hydraulic model, specifically including:

[0076] The various drainage facilities in the drainage system are classified into three types of objects: pipelines, nodes, and regions. Pipelines are used to represent drainage pipes; nodes are used to represent connection points, inspection wells, and pumping stations in drainage pipes; and regions are used to represent catchment areas and receiving bodies.

[0077] Constructing an urban drainage topology logic model based on the classified object categories of drainage facilities; the urban drainage topology logic model is used to sort out the topological relationships between various types of facilities in the drainage system;

[0078] A drainage hydraulic model is constructed, wherein the drainage hydraulic model is used to simulate the movement and changes of water flow in the drainage system.

[0079] Specifically, in this method, drainage facilities are divided into three types of objects: pipelines, nodes and areas.

[0080] Pipeline: Primarily used to represent drainage pipes, the primary channels through which water is transported within a drainage system. Pipelines, made of different materials (such as reinforced concrete and plastic), diameters, lengths, and slopes, each have varying drainage capacities and flow characteristics, playing a crucial role in the overall drainage system.

[0081] Nodes: Nodes represent drainage pipe connection points, manholes, pumping stations, and other structures. Drainage pipe connection points ensure smooth water flow between different sections; manholes facilitate pipeline inspection, maintenance, and cleaning; and pumping stations boost water flow energy, overcoming pipeline resistance and ensuring smooth delivery to sewage treatment plants or collection points. These node facilities play a crucial role in connecting, monitoring, and boosting power within the drainage system.

[0082] Area: Areas are used to represent catchment areas and receiving bodies. A catchment area is an area that collects rainwater or sewage. Factors such as topography, landforms, and land use type influence the amount of rainwater or sewage generated and the path it takes into the drainage system. Receiving bodies are the final destinations of drainage system water, such as rivers and lakes. Understanding the characteristics of catchments and receiving bodies is crucial for analyzing the source and destination of water in a drainage system.

[0083] Based on the above classification of drainage facility objects, an urban drainage topology logic model is constructed. The main purpose of this model is to sort out the topological relationships between various types of facilities in the drainage system, that is, the connection methods and relationships between them.

[0084] Data processing and optimization: correction and improvement are carried out at four levels: data expression, data storage, data space analysis and data call.

[0085] Data representation: Drainage engineering and geological characteristics are combined to provide a more detailed and accurate description of the topological characteristics of the drainage system and related facilities. For example, by considering the impact of terrain slope on water flow direction, the spatial analysis results of the intelligent pipe network platform are more accurate and the simulations are closer to reality. This can more realistically reflect the operation of the drainage system in different geographical environments.

[0086] Data storage: Traditional drainage system data structures have limited scalability, and information retrieval relies excessively on adding data attributes. This study addresses this issue by adopting a more rational data storage structure to effectively store city-level pipe network data. Furthermore, the data storage logic is optimized to facilitate the execution of corresponding algorithms, enabling efficient spatial query and analysis and improving data processing efficiency.

[0087] Data spatial analysis: Analyze the sequence of events and algorithms for spatial analysis based on drainage business flows. For example, based on the flow sequence and processing flow of water in the drainage system, determine the steps and methods for spatial analysis to ensure the rationality and accuracy of the analysis results. This allows for a better understanding of the movement patterns of water in the drainage system and the interactions between facilities.

[0088] Data call layer: Based on the data access characteristics, we optimize data access methods and improve data access efficiency. By rationally designing data interfaces and call mechanisms, we reduce the time overhead of data acquisition, thereby effectively improving the efficiency of topology analysis and making the construction and operation of the entire model more efficient.

[0089] Model Construction and Relationship Expression: A topological logical model of urban drainage was constructed to clarify the topological relationships between various drainage system facilities. Detailed descriptions of the three object types, domains, nodes, and pipelines, were provided to clarify their connections and interactions. These relationships were expressed topologically using the Unified Modeling Language (UML), creating an intuitive and clear model structure. This model clearly demonstrated the location, connections, and flow direction of each facility in the drainage system, providing a foundation for subsequent hydraulic modeling and drainage capacity analysis.

[0090] A drainage hydraulic model was constructed to simulate the movement and changes of water flow in the drainage system. The model was calibrated using actual operational monitoring data from the drainage system to more accurately reflect the actual situation.

[0091] Model Construction Principle: The drainage hydraulic model is based on the principles of hydraulics and considers the flow characteristics of water in pipes, such as velocity, flow rate, and pressure. By establishing mathematical equations to describe the movement of water in the drainage system, it simulates the changes in water flow under different operating conditions.

[0092] Model calibration: Utilizing actual operational monitoring data from the drainage system, such as flow and water level data, the model is calibrated. Model parameters are continuously adjusted to align simulation results with actual monitoring data, improving model accuracy. For example, based on actual monitored flow and water level data for a specific pipe section, parameters such as the resistance coefficient of that pipe can be adjusted in the model to more accurately simulate the flow within that pipe.

[0093] Data simulation and acquisition: The calibrated drainage hydraulic model can be used to simulate and derive hydraulic data for the main drainage pipe. By setting different boundary conditions, such as rainfall and sewage discharge, the changes in hydraulic parameters such as flow rate, flow velocity, and pressure of the main drainage pipe under different operating conditions can be simulated.

[0094] The drainage capacity of the drainage system is evaluated based on the hydraulic data of the drainage trunk pipe obtained through simulation. The evaluation indicators include the total time of pipe section overload within the unit evaluation period and the total overflow water volume of the node within the unit evaluation period. The total time of pipe section overload within the unit evaluation period: Pipe section overload refers to the situation where the flow rate within the pipe section exceeds its designed drainage capacity. The total time of pipe section overload within the unit evaluation period reflects the length of time that the pipe section is subjected to a load exceeding the design load within a certain period of time. If this time is too long, the risk of pipe section rupture, leakage, etc. will increase, affecting the normal operation of the drainage system. By analyzing the simulation data, counting the time periods when the flow rate of the pipe section exceeds its designed drainage capacity, and accumulating these time periods, the total time of pipe section overload within the unit evaluation period can be obtained.

[0095] Total node overflow volume within a unit evaluation period: Node overflow refers to the overflow of water at nodes (such as manholes and pumping stations) due to poor drainage. The total node overflow volume within a unit evaluation period reflects the drainage system's insufficient drainage capacity at the node. Excessive overflow can lead to problems such as groundwater accumulation and environmental pollution. By simulating data, the overflow volume of each node within a unit evaluation period is calculated and accumulated to obtain the total node overflow volume within the unit evaluation period.

[0096] In one embodiment, the step of generating the security hierarchy model includes:

[0097] Use one or more combinations of convolutional neural networks, recurrent neural networks, and long short-term memory networks to build the initial model;

[0098] The pipe section data of the first-level risk, second-level risk, and third-level risk are divided into a training set, a validation set, and a test set in proportion. The training set is used to train the initial model so that it learns the characteristics corresponding to different defect types; the validation set is used to adjust the initial model parameters to prevent the model from overfitting; and the test set is used to evaluate the performance of the initial model;

[0099] Use the training set to train the initial model, and continuously adjust the initial model parameters during the training process to continuously improve the model's ability to identify pipeline defects. Use the validation set to verify the initial model during training, and optimize the initial model based on the verification results.

[0100] The trained initial model is used as a safety hierarchy model to process pipeline defects, identify different types of defects, and count the number and location information of each type of defects based on the identification results.

[0101] In one embodiment, the pipe section damage rate, pipe section siltation rate, and rainwater-sewage mixing rate of the pipe network are obtained, including:

[0102] The pipe section damage rate, pipe section siltation rate and pipe network rainwater and sewage mixing rate are obtained, including:

[0103] The calculation formula of pipe section damage rate P is: Where P is the pipe section damage rate; LP is the damaged pipe section length; LZ is the total pipe section length; the pipe section damage rate is calculated by dividing the identified damaged pipe section length by the total pipe section length;

[0104] The calculation formula of pipe section siltation rate S is: Where D is the outer diameter of the pipeline, d is the inner diameter of the pipeline, L is the length of the pipeline, ρ is the silt density, and Vpipe is the volume of the pipeline. The siltation rate of the pipeline section is calculated based on the identified internal siltation of the pipeline and the size parameters of the pipeline;

[0105] For the stormwater pipe network, the calculation formula for sewage mixing density is: Mixed water ratio Where n is the number of sewage mixing points or users in the stormwater pipe network, N is the total number of drainage users in the drainage pipe network service area, q is the total amount of sewage mixing water in the stormwater pipe network obtained from the survey, and Q is the total sewage generation in the surveyed area;

[0106] For sewage pipe networks, the formula for calculating rainwater mixing density is: Mixed water ratio Where n is the number of users with mixed rainwater connections in the sewage network, Qrain is the amount of water delivered by the sewage network on rainy days, and Q is the total sewage generated in the surveyed area.

[0107] 11. In one embodiment, for the first-level risk and the second-level risk, analyzing the relationship between paired variables to find key indicators affecting the risk includes:

[0108] Extract variables related to first- and second-level risks from the drainage network GIS database, defect detection results, and data from topological analysis and hydraulic modeling. These variables include pipeline physical characteristics, environmental factors, hydraulic conditions, and pipeline defect-related variables.

[0109] The extracted variable data were cleaned to remove outliers and missing values; missing values ​​were processed by filling in the mean;

[0110] Standardize different types of variables;

[0111] According to the type and distribution characteristics of the variables, the corresponding correlation analysis method was selected; for continuous variables, the Pearson correlation coefficient method was used; for non-normally distributed continuous variables or ordered categorical variables, the Spearman rank correlation coefficient method was used; for nominal categorical variables, the chi-square test was used to analyze the association between variables;

[0112] Combine the selected variables in pairs and calculate the correlation coefficient between each pair of variables;

[0113] The calculated correlation coefficient is tested for significance according to the pre-set significance level; pairs of variables that pass the significance test and whose absolute value of the correlation coefficient is greater than the set threshold are determined to be significantly correlated variables;

[0114] Based on significantly correlated paired variables, a variable association network is constructed. In the network, each variable is a node, and the lines between nodes represent the significant correlation between the variables. The thickness of the lines is set according to the size of the correlation coefficient.

[0115] Using network analysis methods, we conducted a structural analysis of the constructed variable association network. We calculated the degree centrality, betweenness centrality, and closeness centrality of the nodes. Degree centrality reflects the number of connections a node has with other nodes. Nodes with high degree centrality have significant connections with multiple other nodes in the network. Betweenness centrality measures a node's ability to act as an intermediary for the shortest path between other nodes in the network. Closeness centrality indicates the degree of proximity of a node to other nodes in the network.

[0116] Based on the physical significance of the variables in the actual operation of the drainage network and the structural characteristics of the variable association network, the importance of each variable is evaluated; a variable importance evaluation model is established to combine the physical significance weight of the variable and the network structure index weight to calculate the importance score of each variable;

[0117] All variables are ranked according to their importance scores; a preset proportion of variables ranked high are selected as key indicators affecting risk.

[0118] Specifically, the operational risk of urban drainage networks is affected by a variety of factors. In order to comprehensively analyze these influencing factors, it is necessary to extract variables related to the first-level and second-level risks from multiple data sources. These data sources include the drainage network GIS database, defect detection results, and data obtained from topological analysis and hydraulic modeling. Pipeline physical characteristic variables, such variables reflect the physical properties of the pipeline itself, including pipe material, pipe diameter, burial depth, pipe age, etc. Different pipe materials (such as reinforced concrete pipes, plastic pipes, etc.) have different strength, corrosion resistance and service life, which will affect the stability and safety of the pipeline; the pipe diameter determines the water transmission capacity of the pipeline; the burial depth affects the degree to which the pipeline is affected by external loads and geological conditions; the pipe age reflects the service life of the pipeline. As the pipe age increases, the probability of pipeline damage, aging and other problems increases. Environmental factor variables: including road grade, geological disaster risk, subway impact, etc. In areas with high road grades, traffic volume is high, which has a greater impact on the vibration and pressure of underground drainage pipes, potentially accelerating pipe damage. In areas with high geological disaster risks (such as areas prone to frequent earthquakes and landslides), pipes are easily damaged by geological activities. Excavation, vibration and other activities during subway construction and operation may also have an impact on surrounding drainage pipes. Hydraulic condition variables include: such as daily cumulative flow, overload status, duration of surface waterlogging during rainy days, and depth of accumulated water. Daily cumulative flow and overload status reflect the load of water flow in the pipe. Excessive flow or long-term overload will increase the pressure in the pipe, leading to pipe damage, leakage and other problems. The duration of surface waterlogging and depth of accumulated water during rainy days are closely related to the drainage capacity of the rainwater pipe network. Excessive accumulation of water for too long and too deep may indicate that the pipe network is not draining smoothly, and there are problems such as blockage or insufficient drainage capacity.

[0119] Pipeline defect-related variables include pipe segment breakage rate, pipe segment siltation rate, and rainwater-sewage mixing rate in the pipeline network. These variables directly reflect the condition of pipeline defects. A high pipe segment breakage rate indicates severe structural damage to the pipeline; a high pipe segment siltation rate affects the pipeline's water flow capacity and increases flow resistance; a high rainwater-sewage mixing rate in the pipeline network can lead to sewage overflows, environmental pollution, and other problems, while also increasing the processing burden on sewage treatment plants.

[0120] Variable data extracted from multiple data sources may contain outliers and missing values, which will affect the accuracy of the analysis results, so data cleaning is required.

[0121] Outliers are data points that differ significantly from the rest of the data. They may be caused by data collection errors, equipment failure, or special circumstances. For example, sudden extreme values ​​in flow monitoring data may be caused by sensor failure. Statistical analysis methods (such as the 3σ principle) can be used to identify and remove these outliers.

[0122] For missing values, this method uses mean filling. Mean filling refers to filling missing data points with the mean value of the variable. For example, if there are missing values ​​in the diameter data of a certain section of pipeline, the mean value of the diameters of other similar pipelines can be calculated and used to fill the missing values. This method is simple and easy to implement, and can maintain the integrity and continuity of the data to a certain extent, providing a basis for subsequent analysis. After data cleaning, since different types of variables have different dimensions and value ranges, in order to make different variables comparable, they need to be standardized. Standardization converts the data of the variables to the same scale. Commonly used methods include Z-score standardization and Min-Max standardization. For example, Z-score standardization subtracts the mean of the variable from its value and then divides it by the standard deviation, so that the mean of the processed data is 0 and the standard deviation is 1.

[0123] Based on the type and distribution characteristics of the variables, select an appropriate correlation analysis method to explore the relationship between the variables. The Pearson correlation coefficient method is applicable to continuous variables and is used to measure the degree of linear correlation between two variables. Its value range is between -1 and 1, and the closer the absolute value is to 1, the stronger the linear relationship between the two variables. For example, when analyzing the relationship between the pipe section breakage rate and the cumulative flow rate per day, if the Pearson correlation coefficient is 0.8, it indicates that there is a strong positive linear correlation between the two, that is, the greater the cumulative flow rate per day, the higher the pipe section breakage rate is likely to be.

[0124] The Spearman rank correlation coefficient method is applicable to continuous variables with non-normal distributions or ordered categorical variables. It does not depend on the distribution of the variables, but instead calculates correlation based on the rank (i.e., the position after sorting). For example, the Spearman rank correlation coefficient method can be used to analyze the relationship between geological disaster risk (categorized as high, medium, and low) and pipeline damage.

[0125] The chi-square test is used to analyze the association between nominal categorical variables. Nominal categorical variables are categorical variables without an order, such as pipe type (reinforced concrete pipe, plastic pipe, etc.). The chi-square test can determine whether there is a significant association between different pipe types and pipe breakage rates.

[0126] The selected variables are paired together, and the correlation coefficient between each pair of variables is calculated using the selected correlation analysis method. For example, the pipe diameter (a variable related to pipeline physical characteristics) is combined with the daily cumulative flow rate (a variable related to hydraulic conditions) to calculate the Pearson correlation coefficient between them; the road grade (an environmental factor variable) is combined with the pipe section breakage rate (a variable related to pipeline defects) to calculate the Spearman rank correlation coefficient. After calculating the correlation coefficient, it is necessary to perform a significance test based on a pre-set significance level (usually set at 0.05). The significance test is used to determine whether the correlation coefficient is significantly different from 0, that is, whether there is a true association between the variables. If the significance test passes and the absolute value of the correlation coefficient is greater than the set threshold (such as 0.6), the pair of variables is determined to be significantly correlated. The threshold is set to screen out variable pairs with strong correlations to facilitate a more accurate analysis of key influencing factors.

[0127] Constructing a variable association network and structural analysis: Based on significantly correlated pairs of variables, a variable association network is constructed. In this network, each variable serves as a node, and the lines connecting the nodes represent the significant correlation between the variables. The thickness of the lines is set according to the correlation coefficient. The larger the correlation coefficient, the thicker the line, which intuitively demonstrates the closeness of the association between the variables. Network analysis methods are used to perform structural analysis on the constructed variable association network, calculating the degree centrality, betweenness centrality, and closeness centrality of the nodes.

[0128] Degree centrality reflects the number of connections a node has with other nodes. Nodes with high degree centrality have significant associations with multiple other nodes in the network, indicating that the variable is closely related to many other variables and may play a key role in the overall risk impact mechanism. For example, if the pipe segment breakage rate variable has a high degree centrality, it indicates that it is significantly associated with many other variables (such as daily cumulative flow rate and pipe material), and has a broad impact on drainage network risk.

[0129] Betweenness centrality measures a node's ability to act as an intermediary for the shortest paths between other nodes in a network. Nodes with high betweenness centrality play a significant role in information transfer and the interaction between variables within the network, potentially acting as key factors influencing risk. For example, a high betweenness centrality for the overload status variable within hydraulic conditions indicates that it occupies a key position in the interaction paths between many variables, significantly influencing the propagation and evolution of drainage network risk.

[0130] Closeness centrality: This indicates the proximity of a node to other nodes in the network. Nodes with high closeness centrality can quickly influence other nodes in the network. During the risk propagation process, the variable represented by that node may more quickly trigger changes in other variables. For example, if the closeness centrality of the rainwater-sewage mixing ratio in a pipeline network is high, any change in this mixing will quickly affect other related variables, significantly impacting the operational safety of the pipeline network.

[0131] The importance of each variable is assessed based on its physical significance in actual drainage network operation and its structural characteristics within the variable-correlated network. A variable importance assessment model is developed, combining the variable's physical significance weight with the network structure indicator weight to calculate each variable's importance score. The physical significance weight of a variable can be determined based on expert experience, industry standards, and actual project conditions. For example, the pipe breakage rate, which has a significant direct impact on network safety, can be assigned a higher physical significance weight. The network structure indicator weight is determined based on the calculated results of degree centrality, betweenness centrality, and closeness centrality. All variables are ranked based on their importance scores. A predetermined proportion of variables (e.g., the top 30%) are selected as key indicators influencing risk. These key indicators can largely explain the causes of first- and second-level risks, providing an important basis for developing effective response strategies. For example, if variables such as pipe breakage rate, daily cumulative flow rate, and overload status rank highly after calculation and ranking, then these variables are key indicators influencing drainage network operational risk. When formulating maintenance and management strategies, it is important to focus on the changes in these indicators and take appropriate regulatory measures.

[0132] 12. In one embodiment, matching corresponding response strategies based on key indicators affecting risk and displaying the response strategies include:

[0133] Collect and organize relevant experience, industry standards, expert advice, and historical cases in urban drainage network operation and maintenance to build a knowledge base of response strategies;

[0134] Classify and annotate the response strategies in the knowledge base, and categorize them according to the type of key indicators and risk level;

[0135] Develop corresponding matching rules for each key indicator that affects risk;

[0136] According to the key indicators affecting the risk and their current values, the corresponding response strategies are selected from the response strategy knowledge base according to the matching rules.

[0137] Specifically, to provide effective response measures for different risk scenarios, it is necessary to extensively collect and organize diverse information to build a knowledge base of response strategies. Over time, a wealth of practical experience has been accumulated in the operation and maintenance of urban drainage networks. For example, in a specific area, pipe section breakages frequently occurred due to aging pipe materials. Through repeated repairs, a set of effective repair methods for pipes made of this material has been developed. This experience is a crucial component of the response strategy knowledge base, grounded in practical experience and highly practical. The drainage industry has developed a series of standards and specifications that define requirements for design, construction, and maintenance of drainage networks. For example, regarding the control standards for pipe section siltation rates, industry standards clearly define the allowable siltation rate ranges for pipes of different diameters and at different service lives. These standards provide an important basis and reference for developing response strategies. Experts in the drainage field are invited to provide expert advice on potential operational issues and response methods based on their extensive expertise and practical experience. Experts can provide unique insights and solutions for specific risk scenarios, such as how to address excessive drainage pressure in stormwater networks in areas prone to heavy rain. Collect case studies of various problems that have arisen in the operation of urban drainage networks and their corresponding solutions. For example, one city, in addressing the problem of mixed rainwater and sewage, implemented a zoning investigation and source control approach, achieving positive results. These historical cases provide practical operational examples for addressing current risk situations. This information is systematically organized to form a knowledge base of response strategies.

[0138] To facilitate rapid retrieval and application of response strategies, the response strategies in the knowledge base need to be categorized and labeled. This categorization and labeling is performed based on the type of key indicator and risk level. Classification by key indicator type: As previously mentioned, key indicators influencing drainage network operational risk include pipeline physical property variables (such as pipe material, diameter, burial depth, and age), environmental factors (such as road grade, geological hazard risk, and subway impact), hydraulic condition variables (such as daily cumulative flow, overload status, duration of surface flooding during rainy days, and depth of accumulated water), and pipeline defect-related variables (such as pipe segment breakage rate, pipe segment siltation rate, and the network's rainwater-sewage mixing rate). For each key indicator category, the associated response strategies are grouped together. For example, for the key indicator of pipe segment breakage rate, all response strategies for pipeline damage, such as repair and replacement, are grouped together. Classification by risk level: Risk levels are generally categorized into Level 1, Level 2, and Level 3. Response strategies corresponding to different risk levels have varying degrees of urgency and approach. Level 1 risks require more urgent and robust response measures; Level 2 risks require less urgency and intensity; and Level 3 risks can be handled with a more moderate approach. Categorizing strategies by risk level helps quickly identify appropriate response strategies for different risk situations. This classification and labeling approach ensures that each response strategy in the response strategy knowledge base is clearly labeled, facilitating rapid screening based on actual key indicators and risk levels.

[0139] Develop matching rules for each key indicator influencing risk. Matching rules bridge the gap between key indicators and response strategies. They determine the most appropriate response strategy based on the key indicator's value range, changing trend, and correlation with other indicators. Matching rules based on the key indicator's value range: For example, when the pipe segment breakage rate exceeds a certain threshold (e.g., 10%), indicating severe pipeline damage, the matching response strategy may be to completely replace the damaged pipe segment. When the pipe segment breakage rate is within a certain range (e.g., 5%-10%), a localized repair strategy can be adopted. Matching rules based on the changing trend of key indicators: If the pipe segment siltation rate shows a sustained upward trend, even if the current siltation rate has not yet reached the danger threshold, a corresponding response strategy, such as increasing the frequency of siltation removal, is necessary to prevent further desilting. Matching rules based on the correlation of key indicators: When the pipe segment breakage rate is high and the cumulative daily flow rate is also high, simply repairing the pipeline may not be sufficient to solve the problem. Optimizing drainage scheduling and reducing pipeline flow to reduce pipeline operating pressure are also necessary. Formulating matching rules requires comprehensive consideration of multiple factors to ensure the scientific nature and rationality of the rules, and to accurately match effective response strategies for different key indicator situations.

[0140] Based on the identified key risk-influencing indicators and their current values, matching rules are used to select corresponding response strategies from the response strategy knowledge base. Determining key indicators and their values: Through the previous risk assessment process, key risk-influencing indicators, such as pipe breakage rate and overload status, have been identified and their current values ​​obtained. For example, a certain section of the drainage network currently has a pipe breakage rate of 8% and an overload status of 1.2 (indicating that the hydraulic gradient is greater than the pipe slope). Filtering strategies based on matching rules: Based on pre-defined matching rules, the response strategy knowledge base is searched. For a pipe breakage rate of 8%, the matching rules might select a strategy for local pipeline repair; for an overload status of 1.2, strategies might select for optimizing drainage scheduling or adding temporary drainage facilities. This screening process enables rapid identification of specific response strategies tailored to the current drainage network risk situation from the vast response strategy knowledge base.

[0141] In one embodiment, a topological logic model of urban drainage is constructed based on the classified object categories of drainage facilities, including:

[0142] A graph data structure is used to represent the topological relationship of the drainage system; pipelines are regarded as edges in the graph, nodes as vertices in the graph, and regions as attribute information associated with nodes or pipelines;

[0143] Based on the actual operation logic of the drainage system, the topological relationship between various facilities is sorted out; the flow direction of the pipeline is clarified for the connection relationship between pipelines and nodes; for the relationship between the area, pipelines and nodes, the distribution of pipelines in the catchment area and the connection location between the receiving body and the pipeline are determined;

[0144] Verify the constructed urban drainage topology logic model using known actual operation data of the drainage system or historical cases; check whether the connection relationship between pipelines and nodes in the model conforms to the actual water flow path, and whether the association between the area and drainage facilities is accurate;

[0145] Use hydraulic simulation software to simulate the flow path of water in the drainage system based on the constructed topological logic model; compare the simulation results with the actual monitored water flow data to check whether the water flows according to the topological relationship set by the model, and whether there is any abnormal water flow convergence or diversion; if the simulation results do not match the actual situation, check the errors in the topological relationship in the model and correct them.

[0146] Reference Figure 2 The second embodiment of the present invention provides an urban drainage network operation safety assessment device, comprising:

[0147] The first processing module is used to obtain the pipe network operation status data and the pipe network physical structure data to build a drainage pipe network GIS database;

[0148] The second processing module is used to obtain pipeline defect detection images based on CCTV television detection and QV video detection technology and import them into the GIS system to obtain the pipeline structure health index;

[0149] The third processing module is used to: perform model calibration and dynamic simulation on the constructed drainage hydraulic model based on the data in the GIS system and the real-time operation monitoring data of the drainage network to obtain the drainage pipe hydraulic data;

[0150] The fourth processing module is configured to: perform defect assessments on the sewage pipe network, the rainwater pipe network, and the combined pipe network using different safety hierarchy models based on the hydraulic data of the drainage pipes; and classify the defects into first-level risk, second-level risk, and third-level risk based on the corresponding defect probabilities; the first-level risk has a greater risk level than the second-level risk; the second-level risk has a greater risk level than the third-level risk;

[0151] A fifth processing module is configured to: for the first-level risk and the second-level risk, analyze the relationship between paired variables to find key indicators that affect the risk;

[0152] The sixth processing module is used to match corresponding response strategies based on key indicators affecting risks and display the response strategies.

[0153] It should be noted that the urban drainage network operation safety assessment device provided in an embodiment of the present invention is used to execute all the process steps of the urban drainage network operation safety assessment method of the above embodiment. The working principles and beneficial effects of the two correspond one to one, so they will not be repeated here.

[0154] An embodiment of the present invention further provides an electronic device. The electronic device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, such as a data acquisition program. When the processor executes the computer program, the steps in each of the above-mentioned embodiments of the method for evaluating the operation safety of a city drainage network are implemented, such as Figure 1 Alternatively, when the processor executes the computer program, the functions of the modules / units in the above-mentioned device embodiments are realized, such as the first processing module.

[0155] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program in the electronic device.

[0156] The electronic device may be a computing device such as a desktop computer, notebook, PDA, or smart tablet. The electronic device may include, but is not limited to, a processor and memory. Those skilled in the art will appreciate that the aforementioned components are merely examples of electronic devices and do not constitute a limitation of the electronic device. The electronic device may include more or fewer components than those described above, or a combination of certain components, or different components. For example, the electronic device may also include input / output devices, network access devices, buses, and the like.

[0157] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the electronic device, connecting various parts of the entire electronic device using various interfaces and lines.

[0158] The memory can be used to store the computer programs and / or modules, and the processor realizes various functions of the electronic device by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function (such as a sound playback function, an image playback function, etc.); the data storage area can store data created based on the use of the mobile phone (such as audio data, a phone book, etc.). In addition, the memory can include a high-speed random access memory and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage device.

[0159] Wherein, if the module / unit integrated in the electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the process in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, it can implement the steps of the above-mentioned various method embodiments. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0160] It should be noted that the device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed across multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment. In addition, in the drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art can understand and implement the present invention without inventive effort.

[0161] The specific embodiments described above further illustrate the objectives, technical solutions, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. In particular, it should be noted that any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included within the scope of protection of the present invention for those skilled in the art.

Claims

1. A method for evaluating the operation safety of an urban drainage network, characterized in that: include: Obtain the pipe network operation status data and pipe network physical structure data to build the drainage pipe network GIS database; Obtain pipeline defect detection images based on CCTV television detection and QV video detection technology and import them into the GIS system to obtain the pipeline structural health index; Based on the data in the GIS system and the real-time operation monitoring data of the drainage network, the constructed drainage hydraulic model is calibrated and dynamically simulated to obtain the drainage pipe hydraulic data; Based on drainage pipe hydraulic data, different safety hierarchical models are used to conduct defect assessments on sewage pipe networks, stormwater pipe networks, and combined pipe networks. Based on the corresponding defect probabilities, these risks are divided into first-level, second-level, and third-level risks. The first-level risk is more risky than the second-level risk; the second-level risk is more risky than the third-level risk. For the first and second level risks, analyze the relationship between paired variables to find the key indicators that affect the risks; Match corresponding response strategies based on key indicators that affect risks and display the response strategies.

2. A method for evaluating the operation safety of an urban drainage network according to claim 1, characterized in that: The method further comprises: a topological analysis step of the drainage hydraulic model, specifically comprising: The various drainage facilities in the drainage system are classified into three types of objects: pipelines, nodes, and regions. Pipelines are used to represent drainage pipes; nodes are used to represent connection points, inspection wells, and pumping stations in drainage pipes; and regions are used to represent catchment areas and receiving bodies. Constructing an urban drainage topology logic model based on the classified object categories of drainage facilities; the urban drainage topology logic model is used to sort out the topological relationships between various types of facilities in the drainage system; A drainage hydraulic model is constructed, wherein the drainage hydraulic model is used to simulate the movement and changes of water flow in the drainage system.

3. A method for evaluating the operation safety of an urban drainage network according to claim 2, characterized in that: The steps of generating the security hierarchy model include: Use one or more combinations of convolutional neural networks, recurrent neural networks, and long short-term memory networks to build the initial model; The pipe section data of the first-level risk, second-level risk, and third-level risk are divided into a training set, a validation set, and a test set in proportion. The training set is used to train the initial model so that it learns the characteristics corresponding to different defect types; the validation set is used to adjust the initial model parameters to prevent the model from overfitting; and the test set is used to evaluate the performance of the initial model; Use the training set to train the initial model, and continuously adjust the initial model parameters during the training process to continuously improve the model's ability to identify pipeline defects. Use the validation set to verify the initial model during training, and optimize the initial model based on the verification results. The trained initial model is used as a safety hierarchy model to process pipeline defects, identify different types of defects, and count the number and location information of each type of defects based on the identification results.

4. A method for evaluating the operation safety of an urban drainage network according to claim 3, characterized in that: The pipe section damage rate, pipe section siltation rate and pipe network rainwater and sewage mixing rate are obtained, including: The calculation formula of pipe section damage rate P is: Where P is the pipe breakage rate; L P is the length of the damaged pipe section; L Z is the total pipe length; the pipe damage rate is calculated by adding the length of the identified damaged pipe section to the total pipe length; The calculation formula of pipe section siltation rate S is: pipe × 100%; where D is the outer diameter of the pipe, d is the inner diameter of the pipe, L is the length of the pipe, ρ is the silt density, V 管 is the pipe volume; the pipe section siltation rate is calculated based on the identified internal siltation of the pipe and the size parameters of the pipe; For the stormwater pipe network, the calculation formula for sewage mixing density is: Mixed water ratio C Where n is the number of sewage mixing points or users in the stormwater pipe network, N is the total number of drainage users in the drainage pipe network service area, q is the total amount of sewage mixing water in the stormwater pipe network obtained from the survey, and Q is the total sewage generation in the surveyed area; For sewage pipe networks, the formula for calculating rainwater mixing density is: Mixed water ratio Where n is the number of rainwater mixed users in the sewage network, Q 雨 is the amount of water delivered by the sewage network on rainy days, and Q is the total sewage generated in the surveyed area.

5. A method for evaluating the operation safety of an urban drainage network according to claim 4, characterized in that: For the first and second level risks, analyze the relationship between paired variables to find the key indicators that affect the risks, including: Extract variables related to first- and second-level risks from the drainage network GIS database, defect detection results, and data from topological analysis and hydraulic modeling. These variables include pipeline physical characteristics, environmental factors, hydraulic conditions, and pipeline defect-related variables. The extracted variable data were cleaned to remove outliers and missing values; missing values ​​were processed by filling in the mean; Standardize different types of variables; According to the type and distribution characteristics of the variables, the corresponding correlation analysis method was selected; for continuous variables, the Pearson correlation coefficient method was used; for non-normally distributed continuous variables or ordered categorical variables, the Spearman rank correlation coefficient method was used; for nominal categorical variables, the chi-square test was used to analyze the association between variables; Combine the selected variables in pairs and calculate the correlation coefficient between each pair of variables; The calculated correlation coefficient is tested for significance according to the pre-set significance level; pairs of variables that pass the significance test and whose absolute value of the correlation coefficient is greater than the set threshold are determined to be significantly correlated variables; Based on significantly correlated paired variables, a variable association network is constructed. In the network, each variable is a node, and the lines between nodes represent the significant correlation between the variables. The thickness of the lines is set according to the size of the correlation coefficient. Using network analysis methods, we conducted a structural analysis of the constructed variable association network. We calculated the degree centrality, betweenness centrality, and closeness centrality of the nodes. Degree centrality reflects the number of connections a node has with other nodes. Nodes with high degree centrality have significant connections with multiple other nodes in the network. Betweenness centrality measures a node's ability to act as an intermediary for the shortest path between other nodes in the network. Closeness centrality indicates the degree of proximity of a node to other nodes in the network. Based on the physical significance of the variables in the actual operation of the drainage network and the structural characteristics of the variable association network, the importance of each variable is evaluated; a variable importance evaluation model is established to combine the physical significance weight of the variable and the network structure index weight to calculate the importance score of each variable; All variables are ranked according to their importance scores; a preset proportion of variables ranked high are selected as key indicators affecting risk.

6. A method for evaluating the operation safety of an urban drainage network according to claim 5, characterized in that: Match corresponding response strategies based on key indicators affecting risks and present the response strategies, including: Collect and organize relevant experience, industry standards, expert advice, and historical cases in urban drainage network operation and maintenance to build a knowledge base of response strategies; Classify and annotate the response strategies in the knowledge base, and categorize them according to the type of key indicators and risk level; Develop corresponding matching rules for each key indicator that affects risk; According to the key indicators affecting the risk and their current values, the corresponding response strategies are selected from the response strategy knowledge base according to the matching rules.

7. A method for evaluating the operation safety of an urban drainage network according to claim 6, characterized in that: Based on the classified object categories of drainage facilities, the urban drainage topology logic model is constructed, including: A graph data structure is used to represent the topological relationship of the drainage system; pipelines are regarded as edges in the graph, nodes as vertices in the graph, and regions as attribute information associated with nodes or pipelines; Based on the actual operation logic of the drainage system, the topological relationship between various facilities is sorted out; the flow direction of the pipeline is clarified for the connection relationship between pipelines and nodes; for the relationship between the area, pipelines and nodes, the distribution of pipelines in the catchment area and the connection location between the receiving body and the pipeline are determined; Verify the constructed urban drainage topology logic model using known actual operation data of the drainage system or historical cases; check whether the connection relationship between pipelines and nodes in the model conforms to the actual water flow path, and whether the association between the area and drainage facilities is accurate; Use hydraulic simulation software to simulate the flow path of water in the drainage system based on the constructed topological logic model; compare the simulation results with the actual monitored water flow data to check whether the water flows according to the topological relationship set by the model, and whether there is any abnormal water flow convergence or diversion; if the simulation results do not match the actual situation, check the errors in the topological relationship in the model and correct them.

8. A device for evaluating the operation safety of an urban drainage network, characterized in that: include: The first processing module is used to obtain the pipe network operation status data and the pipe network physical structure data to build a drainage pipe network GIS database; The second processing module is used to obtain pipeline defect detection images based on CCTV television detection and QV video detection technology and import them into the GIS system to obtain the pipeline structure health index; The third processing module is used to: perform model calibration and dynamic simulation on the constructed drainage hydraulic model based on the data in the GIS system and the real-time operation monitoring data of the drainage network to obtain the drainage pipe hydraulic data; The fourth processing module is configured to: perform defect assessments on the sewage pipe network, the rainwater pipe network, and the combined pipe network using different safety hierarchy models based on the hydraulic data of the drainage pipes; and classify the defects into first-level risk, second-level risk, and third-level risk based on the corresponding defect probabilities; the first-level risk has a greater risk level than the second-level risk; the second-level risk has a greater risk level than the third-level risk; A fifth processing module is configured to: analyze the relationship between paired variables for the first-level risk and the second-level risk to identify key indicators that affect the risk; The sixth processing module is used to match corresponding response strategies based on key indicators affecting risks and display the response strategies.

9. An electronic device, characterized in that: It includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements a method for evaluating the operation safety of an urban drainage network as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the urban drainage network operation safety assessment method according to any one of claims 1 to 7.

Images