Method and system for checking electrical fault high-risk points of underground pipe gallery

Abstract

The invention discloses a troubleshooting method and system for an electrical fault high-risk point of an underground pipe gallery, and relates to the technical field of fire prevention. According to the invention, various sensor data are collected, historical equipment operation and maintenance data are combined, an electrical topology network is generated based on a cable path and an equipment connection relation, a three-dimensional model of the pipe gallery is constructed, fire prediction simulation is carried out, a fire occurrence point is effectively predicted and positioned, the equipment maintenance cost is saved, part of manual inspection is replaced, and the invalid troubleshooting workload is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of fire prevention, and particularly to a method and system for detecting high-risk points of electrical faults in an underground utility tunnel. Background Art

[0002] As the "lifeline" of urban infrastructure, the underground utility tunnel significantly solves the problem of "road zipper" caused by traditional directly buried pipelines by centrally laying pipelines such as electricity, communication, water supply and drainage, improves urban resilience and land utilization rate, and has been widely used in China. However, fires in underground utility tunnels are often caused by electrical faults, and their impacts spread exponentially. Repairing underground utility tunnels requires a large amount of cost, and causes a large number of public services to stagnate, leading to collapse risks and serious social impacts. Therefore, there is an urgent need for a prediction method for fires caused by electrical faults in underground utility tunnels. Summary of the Invention

[0003] The purpose of the present invention is to provide a method and system for detecting high-risk points of electrical faults in an underground utility tunnel to improve the above technical problems.

[0004] To achieve the above invention purpose, the embodiments of the present invention provide the following technical solutions:

[0005] A method for detecting high-risk points of electrical faults in an underground utility tunnel, which includes:

[0006] Obtain the operation environment data of the underground utility tunnel in real time; the operation environment data includes modeling environment parameters, historical sensor data, real-time operation data, historical equipment operation and maintenance management data, and tunnel structure parameters; the modeling environment parameters include the spatial coordinate information of the underground utility tunnel and the comprehensive sensor data;

[0007] Construct a three-dimensional model of the tunnel based on the tunnel structure parameters and the modeling environment parameters;

[0008] Analyze the electrical evolution law of the underground utility tunnel based on the historical equipment operation and maintenance management data and the historical sensor data, and construct an electrical spatio-temporal evolution function;

[0009] Based on the electrical spatio-temporal evolution function, input the modeling environment parameters and the real-time operation data into the three-dimensional model of the tunnel and conduct simulations to obtain simulation results;

[0010] Based on the simulation results, determine the high-risk points of electrical faults; based on the principle of proximity, dispatch maintenance personnel to repair the high-risk points of electrical faults.

[0011] Further, the sensor data includes temperature, current, humidity, and wind speed;

[0012] The real-time operation data includes electrical parameters and equipment status parameters; the equipment status parameters include the start-stop status and vibration data of the equipment;

[0013] The historical equipment operation and maintenance management data includes historical equipment management data and historical real-time operation data; the historical equipment management data includes historical fault records, maintenance logs, and historical weather data;

[0014] The pipe gallery structure parameters include the design drawing data of the underground comprehensive pipe gallery, equipment ID, equipment spatial coordinate data, and equipment parameters; the design drawing data includes spatial structure parameters, electrical equipment size data, cable paths, and equipment connection relationships; the equipment parameters include cable models, insulation material characteristics, rated current and voltage, etc.

[0015] Furthermore, the real-time acquisition of the operation environment data of the underground comprehensive pipe gallery includes:

[0016] Deploy different types of sensors to the underground comprehensive pipe gallery to build an Internet of Things sensor network;

[0017] Collect pipe gallery structure parameters, real-time operation parameters, historical equipment operation and maintenance management data, and historical sensor raw data;

[0018] Real-time collect the original modeling environment parameters of the underground comprehensive pipe gallery through the Internet of Things sensor network;

[0019] Use wavelet transform to denoise the original modeling environment parameters. By decomposing the signal into wavelet basis functions of different scales, separate and remove the high-frequency noise components to obtain the initial modeling environment parameters;

[0020] Fill in the gaps for the initial modeling environment parameters and historical sensor raw data through a generative adversarial network to obtain the modeling environment parameters and historical sensor data.

[0021] Furthermore, the construction of the pipe gallery three-dimensional model includes:

[0022] Based on the pipe gallery structure parameters, construct an original pipe gallery three-dimensional model;

[0023] Based on the design drawing data and equipment ID, set nodes, edges, and edge weights, and connect the spatial coordinate data of the original pipe gallery three-dimensional model to construct an electrical topology network;

[0024] Fuse the electrical topology network and the original pipe gallery three-dimensional model through spatial matching and attribute merging operations to obtain an initial pipe gallery three-dimensional model;

[0025] Calculate the characteristic diameter; calculate the grid size based on the characteristic diameter;

[0026] Apply the grid size to the initial pipe gallery three-dimensional model to obtain the pipe gallery three-dimensional model.

[0027] Further, the construction of the electrical spatio-temporal evolution function includes:

[0028] Construct a full-scale model of the power cabin in the underground utility tunnel and conduct a fire scenario simulation to obtain corresponding fire simulation results; the fire simulation results include the extinguishing time, flame spread image, and heat release simulation rate curve;

[0029] Fuse and analyze the fire simulation results, historical equipment operation and maintenance management data, and historical sensor data to obtain a fire fusion original feature matrix;

[0030] Fuse the fire simulation results, historical equipment operation and maintenance management data, and historical real-time operation data to obtain fire fusion status data;

[0031] Construct a time-varying function of the electrical insulation material; calculate the time-varying correction term based on the time-varying function of the electrical insulation material;

[0032] Based on the time-varying correction term, use the LSTM-Transformer hybrid network to analyze the fire fusion original feature matrix and construct the electrical spatio-temporal evolution function.

[0033] Further, the process of obtaining the simulation results includes:

[0034] Input the modeling environment parameters and real-time operation data into the 3D model of the utility tunnel;

[0035] Based on the electrical spatio-temporal evolution function, conduct real-time scenario simulation through the 3D model of the utility tunnel, adopt Monte Carlo simulation to simulate the fire spread process under different scenarios, and record the corresponding fire source occurrence points and extinguishing times;

[0036] Record the fire spread process under different scenarios and draw the corresponding fire spread heat map; the simulation results include the fire source occurrence points, extinguishing times, and fire spread heat map.

[0037] Further, the dispatch of maintenance personnel to repair high-risk electrical fault points includes:

[0038] Feedback the spatial coordinates corresponding to the fire source occurrence points through the 3D model of the utility tunnel;

[0039] Based on each spatial coordinate, calculate the distance between each fire source occurrence point and each fire door;

[0040] Based on each extinguishing time, each distance, and each fire spread heat map, determine the risk level of each fire source occurrence point;

[0041] Based on the risk level, determine the high-risk electrical fault points; dispatch different maintenance personnel to repair the high-risk electrical fault points according to the principle of proximity.

[0042] Further, it also includes feedback processing, including:

[0043] Upload and pack the maintenance results and electrical data after maintenance in real time, and feedback them to the three-dimensional model of the utility tunnel and the LSTM-Transformer hybrid network, update the hyperparameters of the LSTM-Transformer hybrid network in real time, and update the structural parameters of the three-dimensional model of the utility tunnel.

[0044] An inspection system for high-risk electrical fault points in an underground utility tunnel, which includes:

[0045] An operating environment data acquisition module for obtaining the operating environment data of the underground utility tunnel in real time; the operating environment data includes modeling environment parameters, historical sensor data, real-time operating data, historical equipment operation and maintenance management data, and utility tunnel structure parameters; the modeling environment parameters include the spatial coordinate information of the underground utility tunnel and the comprehensive sensor data;

[0046] A three-dimensional model construction module of the utility tunnel for constructing a three-dimensional model of the utility tunnel based on the utility tunnel structure parameters and the modeling environment parameters;

[0047] An electrical spatio-temporal evolution function construction module for analyzing the electrical evolution law of the underground utility tunnel based on the historical equipment operation and maintenance management data and the historical sensor data, and constructing an electrical spatio-temporal evolution function;

[0048] A three-dimensional model simulation module of the utility tunnel, based on the electrical spatio-temporal evolution function, inputs the modeling environment parameters and the real-time operating data into the three-dimensional model of the utility tunnel and conducts simulations to obtain simulation results;

[0049] An electrical fault high-risk point determination and troubleshooting path planning module for determining electrical fault high-risk points based on the simulation results; and dispatching maintenance personnel to repair the electrical fault high-risk points based on the principle of proximity.

[0050] The beneficial effects of the present invention are:

[0051] The present invention discloses a method and system for inspecting high-risk electrical fault points in an underground utility tunnel, which relates to the technical field of fire prevention. The present invention collects a variety of sensor data, combines historical equipment operation and maintenance data, generates an electrical topological network based on the cable path and equipment connection relationship, constructs a three-dimensional model of the utility tunnel and conducts fire prediction simulations, effectively predicts and locates the fire occurrence point, saves equipment maintenance costs, and replaces part of the manual inspection to reduce the workload of ineffective inspections. Description of the Drawings

[0052] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other relevant drawings can also be obtained based on these drawings.

[0053] Figure 1 It is the flowchart of the method in the embodiments of the present invention;

[0054] Figure 2 It is the system structure diagram in the embodiments of the present invention. Detailed implementation manners

[0055] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Usually, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed present invention, but only represents the selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present invention.

[0056] Please refer to Figure 1 , a method for detecting high-risk points of electrical faults in an underground utility tunnel provided in this embodiment includes:

[0057] S1. Obtain the operation environment data of the underground utility tunnel in real time; the operation environment data includes modeling environment parameters, historical sensor data, real-time operation data, historical equipment operation and maintenance management data, and utility tunnel structure parameters.

[0058] The modeling environment parameters include the spatial coordinate information of the underground utility tunnel and the comprehensive sensor data; the comprehensive sensor data includes sensor position data, sensor data, and acquisition timestamps; the sensor data includes temperature, current, humidity, wind speed, and carbon dioxide concentration.

[0059] The real-time operation data includes electrical parameters (power, power factor, and frequency) and equipment status parameters. The equipment status parameters include the start-stop status and vibration data of the equipment.

[0060] Historical equipment operation and maintenance management data includes historical equipment management data and historical real-time operation data. Historical equipment management data includes historical fault records, maintenance logs and historical weather data; extract historical fault records (fault time, type, location, maintenance measures, etc.) and maintenance logs (maintenance time, personnel, content, etc.) from the equipment operation and maintenance management system; obtain historical weather data (temperature, humidity, rainfall, wind speed, etc.) from the meteorological department.

[0061] The pipe gallery structural parameters include the design drawing data, equipment ID, equipment space coordinate data and equipment parameters of the underground integrated pipe gallery. The design drawing data includes the space structure parameters, electrical equipment size data, cable path and equipment connection relationship. Equipment parameters include cable model, insulation material characteristics, rated current and voltage, etc.

[0062] In this embodiment, the cables in the underground integrated pipe gallery include YC cables and RVV cables.

[0063] The S1 includes:

[0064] S1-1. Deploy different types of sensors to the underground integrated pipe gallery to build an IoT sensor network. Arrange temperature sensors in a circular pattern at cable joints and distribution cabinets at intervals of 5m, and place a temperature sensor at the top, bottom and side wall of the cable tray at intervals of 12m along the longitudinal direction of the corridor. Place current sensors at key nodes of the distribution circuit; key nodes of the distribution circuit include but are not limited to the inlet and outlet terminals of the ring network cabinet, the middle joints of the cable, and the power supply branches with a load rate exceeding 80%. Install humidity sensors in the water-prone areas of the pipe gallery, vents, and the bottom of the cable shaft. Place wind speed sensors at the intersection of the vents of the pipe gallery (1.5m from the entrance / exit of the main channel), the boundaries of the fire partitions (on both sides of each partition door), and the cable area. Place a carbon dioxide concentration sensor at both ends and in the middle of the cable tray.

[0065] S1-2, collect pipe gallery structural parameters, real-time operation parameters, historical equipment operation and maintenance management data and historical sensor raw data;

[0066] S1-3. Collect the original modeling environmental parameters of the underground integrated pipeline corridor in real time through the Internet of Things sensor network.

[0067] S1-4. Use wavelet transform to denoise the original modeling environment parameters. By decomposing the signal into wavelet basis functions of different scales, separate and remove the high-frequency noise components to obtain the initial modeling environment parameters.

[0068] S1-5. The initial modeling environment parameters and historical sensor raw data are supplemented by a generative adversarial network to obtain the modeling environment parameters and historical sensor data.

[0069] S2. Build a 3D model of the utility tunnel based on the structure parameters and modeling environment parameters of the utility tunnel.

[0070] The S2 includes:

[0071] S2-1. Build an original 3D model of the utility tunnel based on the structure parameters of the utility tunnel.

[0072] The S2-1 includes:

[0073] S2-1-1. Input the design drawing data, equipment ID, and equipment parameters in the structure parameters of the utility tunnel into the BIM software to build a 3D structure model of the utility tunnel. The BIM software can be Autodesk Revit or Bentley MicroStation.

[0074] S2-1-2. Import the 3D structure model of the utility tunnel into the GIS software, and perform annotation based on the sensor position data and spatial coordinate information in the modeling environment parameters to build an original 3D model of the utility tunnel, that is, the BIM-GIS utility tunnel model.

[0075] S2-2. Based on the design drawing data and equipment ID, set nodes, edges, and edge weights, and connect the spatial coordinate data of the original 3D model of the utility tunnel to build an electrical topology network.

[0076] The S2-2 includes:

[0077] S2-2-1. Extract the cable path and equipment connection relationship in the design drawing data, and use the equipment and cable connection relationship as nodes and edges , respectively, and use the cable impedance as the edge weight to build an electrical diagram structure . The equipment is the electrical device of the underground utility tunnel, such as cable joints, distribution cabinets, etc.

[0078] S2-2-2. Input the equipment spatial coordinate data, equipment ID, and spatial coordinate data into the electrical diagram structure, analyze the connection relationship between the equipment, and build an electrical topology network.

[0079] S2-3. Perform fusion on the electrical topology network and the original 3D model of the utility tunnel through spatial matching and attribute merging operations to obtain an initial 3D model of the utility tunnel. The spatial matching uses the R-tree index to achieve precise alignment of equipment coordinates; the attribute merging operation is to merge the BIM-GIS attributes of the 3D model of the utility tunnel and the topological attributes of the electrical topology network one by one; for example, unify and fuse the coordinate data in BIM-GIS and the node coordinate data of the electrical topology network.

[0080] S2-4. Calculate the characteristic diameter; calculate the grid size based on the characteristic diameter, and the corresponding formula is:

[0081] ;

[0082] ;

[0083] Among them, represents the characteristic diameter, represents the fire heat release rate, with the unit of kW, , , respectively represent the ambient air concentration, the specific heat capacity of air at constant pressure, and the ambient air temperature, and their units are kg / m 3 , kJ / (kg·k), K, represents the acceleration due to gravity, with the unit of m / s 2 . represents the grid size, represents the parameter for controlling the grid resolution, and its value range is [4, 16].

[0084] S2-5. Apply the grid size to the initial 3D model of the utility tunnel to obtain the 3D model of the utility tunnel.

[0085] S3. Based on the historical equipment operation and maintenance management data and historical sensor data, analyze the electrical evolution law of the underground utility tunnel and construct an electrical spatio-temporal evolution function.

[0086] The said S3 includes:[[]]

[0087] S3-1. Construct a full-scale model of the power cabin of the underground utility tunnel and conduct a fire scenario simulation to obtain the corresponding fire simulation results; the fire simulation results include the extinguishing time, the flame spread image, and the heat release simulation rate curve.

[0088] S3-2. Integrate and analyze the fire simulation results, historical equipment operation and maintenance management data, and historical sensor data to obtain the fire integration original feature matrix.

[0089] Integrate the fire simulation results, historical equipment operation and maintenance management data, and historical sensor data to obtain the fire integration status data. Conduct data mining and feature extraction on the fire integration status data, extract the features related to temperature and current changes during the fire, and obtain the fire integration original feature matrix.

[0090] S3-3. Construct a time-varying function of the electrical insulating material; calculate the time-varying correction term based on the time-varying function of the electrical insulating material.

[0091] S3-4. Based on the time-varying correction term, use the LSTM-Transformer hybrid network to analyze the fire integration original feature matrix and construct an electrical spatio-temporal evolution function.

[0092] The LSTM-Transformer hybrid network is used to extract the electrical evolution law of temperature and current in the pipe gallery during a fire. Thus, the formula corresponding to the electrical spatio-temporal evolution function is:

[0093] ;

[0094] ;

[0095] ;

[0096] ;

[0097] ;

[0098] Among them, represents the integral function, represents the output of the LSTM neural network, and represent the Transformer network function and its output respectively, represents the current moment of the fire fusion original feature matrix, represents the first temperature prediction value at the current moment , and represent the uncertainty coupling coefficient and the Joule heat coefficient respectively, represents the square of the current within the time , represents the resistance value within the time , represents the splicing function, represents the time-varying correction term at the current moment , represents the initial time-varying correction term, represents the natural constant, and represent the uncertainty attenuation coefficient and the heat diffusion coefficient respectively, represents the second temperature prediction value, and represent the device temperature and the ambient temperature (temperature measured by the sensor) at the time respectively, represents the initial temperature, represents the Laplace operator of the temperature field, represents the mass of the pipe gallery equipment, represents the specific heat capacity, represents the heat dissipation coefficient, represents the fusion weight, represents the residual noise term.

[0099] S4. Input the modeling environment parameters and real-time operation data into the three-dimensional model of the utility tunnel based on the electrical spatio-temporal evolution function and perform simulations to obtain simulation results.

[0100] The above S4 includes:

[0101] S4-1. Input the sensor data and its timestamps in the modeling environment parameters and the real-time operation data into the three-dimensional model of the utility tunnel.

[0102] S4-2. Based on the electrical spatio-temporal evolution function, perform real-time scene simulations through the three-dimensional model of the utility tunnel, adopt Monte Carlo to simulate the fire spread process under different scenarios, and record the corresponding fire source occurrence points and extinguishing times.

[0103] S4-3. Record the fire spread processes under different scenarios and draw the corresponding fire spread heat maps.

[0104] Divide the temperature field data, smoke concentration field, and structural damage status (0 means intact, 0.5 means partially damaged, 1 means completely damaged) in each fire spread process at 10s intervals, and integrate the divided data to obtain the corresponding fire spread data.

[0105] Calculate the comprehensive heat value corresponding to the fire spread data. The existing method is used to calculate the comprehensive heat value. For example, the temperature weight, smoke weight, and damage weight are multiplied by the corresponding data and added together to obtain the corresponding value, which is the comprehensive heat value. Setting the temperature weight, smoke weight, and damage weight needs to follow the setting conditions. For example, in the initial stage of the fire or in the first half minute after the fire occurs, the temperature weight can be set to 0.8 because in the initial stage of the fire, the temperature rises faster, there is only a little smoke, and only some equipment catches fire, and the damage degree is not high; in the middle stage of the fire, the ratio of the temperature weight to the smoke weight can be close to 1:1, and the set value is larger than the damage weight because in the middle stage of development, the temperature may tend to be stable, with little change, a large amount of smoke is generated, and equipment is burned or damaged; in the later stage of the fire, the fire intensity decreases and the smoke fills the air. At this time, the smoke weight is the largest, followed by the damage weight and the temperature weight.

[0106] Based on the comprehensive heat value, perform three-dimensional visualization rendering on the fire spread process to obtain the corresponding rendering diagram, that is, obtain the fire spread heat map.

[0107] The above simulation results include the fire source occurrence points, extinguishing times, and fire spread heat maps.

[0108] S5. Based on the simulation results, determine the high-risk points of electrical faults; based on the principle of proximity, dispatch maintenance personnel to repair the high-risk points of electrical faults.

[0109] S5-1. Feedback the spatial coordinates corresponding to the fire source occurrence points through the three-dimensional model of the utility tunnel.

[0110] S5-2. Calculate the distances between each fire source occurrence point and each fire door based on each spatial coordinate.

[0111] If a fire breaks out in the middle position of each pipe gallery, this position can be regarded as a high-risk point because the middle position is far from the openings of the fire doors on both sides, making it difficult for fire rescue and unable to control the fire in the shortest time. Therefore, when determining the high-risk points of electrical faults, the distance factor needs to be considered.

[0112] S5-3. Determine the risk levels of each fire source occurrence point based on each extinguishing time, each distance, and each fire spread heat map.

[0113] Set a color threshold, extract the heat area greater than the color threshold through an edge extraction algorithm; calculate the heat area of the heat area; calculate the ratio of the heat area to the area of the fire spread heat map and use it as the heat risk level.

[0114] Based on the heat risk level of each fire source occurrence point and extinguishing time and distance , calculate the risk level .

[0115] The formula corresponding to the risk level:

[0116] ;

[0117] where and represent the risk coefficient.

[0118] S5-4. Determine the high-risk points of electrical faults based on the risk level; dispatch different maintenance personnel to repair the high-risk points of electrical faults according to the principle of proximity.

[0119] Set the first risk threshold, the second risk threshold, and the third risk threshold; if the risk level reaches the first risk threshold, regard the occurrence of this fire source as a high-risk point of electrical fault. If the risk level reaches the second risk threshold, regard the occurrence of this fire source as a medium-risk point of electrical fault. If the risk level reaches the third risk threshold, regard the occurrence of this fire source as a non-electrical fault point.

[0120] During the repair, specifically, obtain the location information of the repair site and the repair types of the maintenance personnel; calculate the distance between the repair site and the maintenance opening of the pipe gallery, and based on the distance, dispatch the maintenance personnel belonging to the electrical fault type in the nearest repair site to enter the maintenance opening for repair. Based on the high-risk points of electrical faults, use a path planning algorithm to determine the repair paths of each maintenance personnel.

[0121] Path planning algorithms can adopt ant colony optimization algorithm, particle swarm optimization algorithm, and dynamic programming algorithm (DP). Taking the ant colony optimization algorithm as an example, each maintenance opening of the utility tunnel is used as the initial position of the ant colony, and each initial position includes several ants. The high-risk points of electrical faults are used as nodes; calculate the distance and pheromone from each ant to the next node; select the running routes of each ant according to the pheromone until all nodes are selected. The path of each ant is used as the inspection path for the maintenance personnel. According to the maintenance path, each maintenance personnel repairs the high-risk points.

[0122] In addition, the dangerous points in electrical faults can also be regarded as nodes, and the same method as the path planning method for high-risk points of electrical faults is adopted to plan the inspection paths of idle maintenance personnel.

[0123] In addition, step S5 also includes feedback processing. The feedback processing is as follows:

[0124] The maintenance results and the electrical data after maintenance are uploaded and packaged in real time and fed back to the 3D model of the utility tunnel for updating. It is also fed back to the LSTM-Transformer hybrid network to update the hyperparameters of the LSTM-Transformer hybrid network in real time, making it closer to the real situation, improving the ability of the LSTM-Transformer hybrid network to accurately capture the electrical spatio-temporal evolution process of the utility tunnel, and facilitating the subsequent determination of high-risk points of electrical faults.

[0125] The maintenance results include whether the equipment is working properly, the degree of equipment aging, whether the equipment is replaced, whether the electrical components are replaced, and the equipment ID or location information of the equipment that is not regarded as a high-risk point of electrical faults detected.

[0126] As Figure 2 shown, a system for detecting high-risk points of electrical faults in an underground utility tunnel includes:

[0127] An operating environment data acquisition module for obtaining the operating environment data of the underground utility tunnel in real time; the operating environment data includes modeling environment parameters, historical sensor data, real-time operating data, historical equipment operation and maintenance management data, and utility tunnel structure parameters; the modeling environment parameters include the spatial coordinate information and sensor comprehensive data of the underground utility tunnel.

[0128] A utility tunnel 3D model construction module for constructing a 3D model of the utility tunnel based on the utility tunnel structure parameters and modeling environment parameters.

[0129] An electrical spatio-temporal evolution function construction module for analyzing the electrical evolution law of the underground utility tunnel based on the historical equipment operation and maintenance management data and historical sensor data, and constructing an electrical spatio-temporal evolution function.

[0130] The three-dimensional model simulation module of the utility tunnel is based on the electrical spatio-temporal evolution function. It inputs the modeling environment parameters and real-time operation data into the three-dimensional model of the utility tunnel and conducts simulations to obtain simulation results.

[0131] The electrical fault high-risk point determination and troubleshooting path planning module is used to determine the electrical fault high-risk points based on the simulation results. According to the principle of proximity, it dispatches maintenance personnel to repair the electrical fault high-risk points.

[0132] This system also includes a real-time feedback module, which is used to upload and package the maintenance results and the electrical data after maintenance in real time, and feedback them to the three-dimensional model of the utility tunnel and the LSTM-Transformer hybrid network, updating the structure of the three-dimensional model of the utility tunnel (such as the replaced equipment name, ID) and adjusting the hyperparameters of the LSTM-Transformer hybrid network.

[0133] In summary, the present invention discloses a method and system for troubleshooting electrical fault high-risk points in an underground utility tunnel, which relates to the technical field of fire prevention. The present invention collects a variety of sensor data, combines historical equipment operation and maintenance data, generates an electrical topology network based on the cable path and equipment connection relationship, constructs a three-dimensional model of the utility tunnel and conducts fire prediction simulations, effectively predicting and locating the fire occurrence point, saving equipment maintenance costs, and replacing part of the manual inspection, reducing the workload of ineffective troubleshooting.

[0134] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be determined by the protection scope of the claims.

Claims

1. A method for detecting high-risk points of electrical faults in an underground pipe gallery, characterized in that, include: Obtain the operating environment data of underground integrated pipeline corridors in real time; The operating environment data includes modeling environment parameters, historical sensor data, real-time operating data, historical equipment operation and maintenance management data, and pipe gallery structure parameters; Modeling environment parameters include spatial coordinate information of underground utility corridors and comprehensive sensor data; Construct a three-dimensional model of the corridor based on the corridor structure parameters and modeling environment parameters; Based on historical equipment operation and maintenance management data and historical sensor data, the electrical evolution law of the underground utility corridor is analyzed and the electrical spatiotemporal evolution function is constructed; Based on the electrical spatiotemporal evolution function, the modeling environment parameters and real-time operation data are input into the three-dimensional model of the pipeline corridor and simulated to obtain the simulation results; Based on the simulation results, identify high-risk points for electrical faults; Based on the principle of proximity, maintenance personnel are dispatched to inspect high-risk points for electrical failures.

2. The troubleshooting method for high-risk electrical fault points in an underground pipe gallery according to claim 1, wherein, Sensor data includes temperature, current, humidity, and wind speed; Real-time operation data includes electrical parameters and equipment status parameters; equipment status parameters include equipment start / stop status and vibration data; Historical equipment operation and maintenance management data includes historical equipment management data and historical real-time operation data; historical equipment management data includes historical fault records, maintenance logs and historical weather data; The corridor structure parameters include the design drawing data, equipment ID, equipment space coordinate data and equipment parameters of the underground integrated corridor; the design drawing data includes the space structure parameters, electrical equipment size data, cable paths and equipment connection relationships; the equipment parameters include cable model, insulation material characteristics, and rated current and voltage.

3. The troubleshooting method for high-risk electrical fault points in an underground pipe gallery according to claim 1, characterized in that, The real-time acquisition of the operating environment data of the underground integrated pipe gallery includes: Deploy different types of sensors to underground utility tunnels to build an IoT sensor network; Collect the pipe gallery structure parameters, real-time operation parameters, historical equipment operation and maintenance management data, and historical sensor raw data; The original modeling environmental parameters of the underground utility corridor are collected in real time through the IoT sensor network; The original modeling environment parameters are denoised using wavelet transform. By decomposing the signal into wavelet basis functions of different scales, the high-frequency noise components are separated and removed to obtain the initial modeling environment parameters. The initial modeling environment parameters and historical sensor raw data are supplemented by generative adversarial networks to obtain modeling environment parameters and historical sensor data.

4. The troubleshooting method for high-risk electrical fault points in an underground pipe gallery according to claim 2, wherein The construction of the three-dimensional model of the pipe gallery includes: Based on the corridor structure parameters, construct the original corridor 3D model; Based on the design drawing data and equipment ID, set nodes, edges and edge weights, connect the spatial coordinate data of the original pipeline corridor 3D model, and build an electrical topology network; The electrical topology network and the original three-dimensional model of the pipe gallery are fused through spatial matching and attribute merging operations to obtain the initial three-dimensional model of the pipe gallery. Calculate feature diameter; Calculate mesh size based on feature diameter; The grid size is applied to the initial three-dimensional model of the pipeline corridor to obtain the three-dimensional model of the pipeline corridor.

5. The troubleshooting method for high-risk electrical fault points in an underground pipe gallery according to claim 2, wherein The constructing of the electrical spatiotemporal evolution function comprises: Construct a full-scale model of the power compartment of the underground integrated pipeline corridor and perform fire scenario simulation to obtain corresponding fire simulation results; the fire simulation results include flameout time, flame spread image and heat release simulation rate curve; Fuse and analyze the fire simulation results, historical sensor data, and historical equipment operation and maintenance management data to obtain the original fire fusion feature matrix; Fuse the fire simulation results, historical equipment operation and maintenance management data, and historical real-time operation data to obtain the fire fusion status data; Construct a time-varying function for electrical insulating materials; calculate the time-varying correction term based on the time-varying function of electrical insulating materials; Based on the time-varying correction term, use the LSTM-Transformer hybrid network to analyze the original fire fusion feature matrix and construct an electrical spatio-temporal evolution function.

6. The troubleshooting method for high-risk electrical fault points in an underground pipe gallery according to claim 2, wherein The process of obtaining the simulation results includes: Input the modeling environment parameters and real-time operation data into the three-dimensional model of the utility tunnel; Based on the electrical spatio-temporal evolution function, perform real-time scenario simulation through the three-dimensional model of the utility tunnel, use Monte Carlo to simulate the fire spread process under different scenarios, and record the corresponding fire source occurrence points and extinguishing times; Record the fire spread process under different scenarios and draw the corresponding fire spread heat map; the simulation results include the fire source occurrence points, extinguishing times, and fire spread heat map.

7. The troubleshooting method for high-risk electrical fault points in an underground pipe gallery according to claim 2, wherein The dispatch of maintenance personnel to repair high-risk electrical fault points includes: Feedback the spatial coordinates corresponding to the fire source occurrence point through the three-dimensional model of the utility tunnel; Based on each spatial coordinate, calculate the distance between each fire source occurrence point and each fire door; Based on each extinguishing time, each distance, and each fire spread heat map, determine the risk level of each fire source occurrence point; Based on the risk level, determine the high-risk electrical fault points; according to the principle of proximity, dispatch different maintenance personnel to repair the high-risk electrical fault points.

8. The troubleshooting method for high-risk electrical fault points in an underground pipe gallery according to claim 2, wherein, It also includes feedback processing, including: Real-time upload and package the maintenance results and the electrical data after maintenance, and feedback them to the three-dimensional model of the utility tunnel and the LSTM-Transformer hybrid network, real-time update the hyperparameters of the LSTM-Transformer hybrid network, and update the structural parameters of the three-dimensional model of the utility tunnel.

9. A troubleshooting system for high-risk electrical fault points in an underground pipe gallery, which is used to implement the troubleshooting method for high-risk electrical fault points in an underground pipe gallery according to any one of claims 1 to 8, characterized in that, It includes: An operating environment data acquisition module for real-time acquisition of the operating environment data of the underground utility tunnel; The operating environment data includes modeling environment parameters, historical sensor data, real-time operation data, historical equipment operation and maintenance management data, and utility tunnel structure parameters; The modeling environment parameters include the spatial coordinate information of the underground utility tunnel and the integrated sensor data; A three-dimensional model construction module of the utility tunnel for constructing a three-dimensional model of the utility tunnel based on the utility tunnel structure parameters and modeling environment parameters; An electrical spatio-temporal evolution function construction module for analyzing the electrical evolution law of the underground utility tunnel based on historical equipment operation and maintenance management data and historical sensor data, and constructing an electrical spatio-temporal evolution function; A three-dimensional model simulation module of the utility tunnel, based on the electrical spatio-temporal evolution function, inputs the modeling environment parameters and real-time operation data into the three-dimensional model of the utility tunnel and conducts simulations to obtain simulation results; An electrical high-risk fault point determination and troubleshooting path planning module for determining electrical high-risk fault points based on the simulation results; Based on the principle of proximity, dispatch maintenance personnel to repair high-risk electrical fault points.

Images