Underground power cable management method and system, computer equipment and readable storage medium

Abstract

The invention relates to an underground power cable management method, system and device and a storage medium. The management efficiency of underground power cables is improved. The method comprises the following steps: carrying out regional division on an underground power cable, and obtaining data of sensors on each subarea; establishing a working well risk assessment model according to a working well structure and environmental factors, obtaining a working well risk assessment result by using the working well risk assessment model, inputting cable operation data into a fault prediction model to obtain a fault prediction result, determining maintenance task fields corresponding to the two results, and determining maintenance personnel matched with the task fields according to candidate maintenance personnel specialties; importing the three-dimensional point cloud data into a geographic information system, performing spatial position reconstruction to form a three-dimensional model of the cable, constructing a graph structure of a to-be-laid cable area based on the model, and obtaining a corresponding laying path based on nodes and edges in the graph structure; and visually displaying the three-dimensional model, the working well risk assessment result, the fault prediction result, the laying path and the maintenance personnel information.

Description

Technical Field

[0001] The present application relates to the technical field of cable management, and in particular to an underground power cable management method, system, computer equipment, computer-readable storage medium, and computer program product. Background Art

[0002] With the rapid development of cities, underground power cables have become increasingly important to the operation of urban infrastructure. The importance of the operation and maintenance of underground power cables is self-evident.

[0003] However, with the complex layout of cable lines, traditional management methods have many limitations in the increasingly complex operation and maintenance of underground power cable systems. Traditional methods are unable to deeply explore the potential value of cable data and lack the ability to comprehensively analyze complex data, resulting in inefficient operation and maintenance management of underground power cables. Summary of the invention

[0004] Based on this, it is necessary to provide an underground power cable management method, system, computer equipment, computer-readable storage medium and computer program product that can improve the intelligence level of underground power cable management in response to the above-mentioned technical problems.

[0005] In a first aspect, the present application provides an underground power cable management method, comprising:

[0006] Divide the underground power cable into regions, and obtain sensor data of each segmented region by setting sensors on each segmented region; the sensor data includes: three-dimensional point cloud data, well structure data, environmental data, and underground power cable operation data;

[0007] Establishing a work well risk assessment model according to the work well structure data and the environmental data, obtaining a work well risk assessment result using the work well risk assessment model, and inputting the underground power cable operation data into a trained fault prediction model to obtain a fault prediction result of the underground power cable output by the model;

[0008] Importing the three-dimensional point cloud data of each segmented area into a geographic information system, and having the geographic information system reconstruct the spatial position of the underground power cable according to the three-dimensional point cloud data to form a three-dimensional model of the underground power cable;

[0009] Based on the three-dimensional model, a graph structure corresponding to the area where the underground power cable is to be laid is constructed, and based on the node information and edge information in the graph structure, a laying path of the underground power cable is obtained;

[0010] Determine the task field of the maintenance task corresponding to the work well risk assessment result and the fault prediction result, and determine the target maintenance personnel matching the task field according to the maintenance professional field of the candidate maintenance personnel;

[0011] The three-dimensional model, the work well risk assessment result, the fault prediction result, the laying path and the maintenance personnel information are visualized.

[0012] In one embodiment, the step of dividing the underground power cable into regions and acquiring sensor data of each segmented region by setting sensors on each segmented region obtained by the division includes:

[0013] Setting a preset identifier for each of the segmented areas;

[0014] Identify the sensors installed in each of the segmented areas by using the preset identifiers, and trigger the sensors to collect data at preset time intervals;

[0015] Acquire the sensor data uploaded by the target sensor to the Internet of Things gateway; the target sensor is a sensor among the multiple sensors that communicates with the Internet of Things gateway, and the other sensors among the multiple sensors except the target sensor are used to send the collected sensor data to the target sensor.

[0016] In one embodiment, establishing a well risk assessment model according to the well structure data and the environment data, and obtaining a well risk assessment result using the well risk assessment model includes:

[0017] Obtaining the damage degree of each work well and the weight of the environmental data corresponding to each work well;

[0018] Performing weighted aggregation on the damage degree of the working well and the environmental data according to the weights to obtain a working well risk assessment model;

[0019] The risk assessment model for the work well is used to calculate a comprehensive risk value, which is compared with a preset risk level threshold to determine the risk level of the work well and form a risk assessment result for the work well.

[0020] In one embodiment, the fault prediction model is trained by the following steps, including:

[0021] Acquire historical underground power cable operation data, and determine characteristic data related to underground power cable fault prediction results in the historical underground power cable operation data;

[0022] Inputting the feature data related to the underground power cable fault prediction result in the historical underground power cable operation data into the support vector machine model to be trained, training the support vector machine model to be trained based on a preset kernel function and preset hyperparameters to obtain a support vector machine model to be evaluated;

[0023] If the support vector machine model to be evaluated meets the evaluation criteria, the support vector machine model to be evaluated is output to obtain the fault prediction model.

[0024] In one embodiment, the three-dimensional point cloud data of each segmented area is imported into a geographic information system, and the geographic information system reconstructs the spatial position of the underground power cable according to the three-dimensional point cloud data to form a three-dimensional model of the underground power cable, including:

[0025] Registering the three-dimensional point cloud data of each segmented area to the same coordinate system to obtain the registered three-dimensional point cloud data;

[0026] Inputting the registered three-dimensional point cloud data into the geographic information system, and the geographic information system identifying the location layout of the underground power cables according to the registered three-dimensional point cloud data and historical power cable data;

[0027] The location layout of the underground power cables is spatially reconstructed to form the three-dimensional model of the underground power cables.

[0028] In one of the embodiments, obtaining the laying path of the underground power cable to be laid based on the node information and edge information in the graph structure includes:

[0029] Determine the points where the underground power cable is to be laid based on the node information in the graph structure, determine the starting node and the target node from the points where the underground power cable is to be laid, and use the starting node as the current node;

[0030] Search for neighbor nodes of the current node;

[0031] For each of the neighbor nodes, determine the distance between the current node and the neighbor node, and determine the sum of the distance and a preset edge weight; the preset edge weight is the weight of the edge connecting the current node and the neighbor node, which is determined based on the edge information in the graph structure;

[0032] Determine the neighbor node with the smallest sum as a path access node;

[0033] The path access node is determined as the current node, and the step of searching for neighbor nodes of the current node is returned to execute until the neighbor nodes obtained by the search include the target node, and the laying path of the underground power cable to be laid is obtained according to each path access node.

[0034] In one embodiment, determining a target maintenance personnel matching the task field according to the maintenance professional field of the candidate maintenance personnel includes:

[0035] Performing a matching calculation between the maintenance professional field of the candidate maintenance personnel and the task field to generate a field matching degree;

[0036] Calculating the busyness of the candidate maintenance personnel according to the workload of the candidate maintenance personnel;

[0037] The target maintenance personnel is determined from the candidate maintenance personnel based on the field matching degree and the busyness.

[0038] In a second aspect, the present application also provides an underground power cable management system, comprising:

[0039] The data acquisition module is used to divide the underground power cable into regions, and obtain sensor data of each segmented region through sensors arranged on each segmented region; the sensor data includes: three-dimensional point cloud data, well structure data, environmental data, and underground power cable operation data;

[0040] A work well management module, used to establish a work well risk assessment model according to the work well structure data and the environmental data, obtain a work well risk assessment result using the work well risk assessment model, and input the underground power cable operation data into a trained fault prediction model to obtain a fault prediction result of the underground power cable output by the model;

[0041] A three-dimensional modeling module, used for importing the three-dimensional point cloud data of each segmented area into a geographic information system, and the geographic information system reconstructs the spatial position of the underground power cable according to the three-dimensional point cloud data to form a three-dimensional model of the underground power cable;

[0042] A path planning module, for constructing a graph structure corresponding to the area to be laid underground power cables based on the three-dimensional model, and obtaining a laying path for the underground power cables to be laid based on node information and edge information in the graph structure;

[0043] A maintenance scheduling module, used to determine the task field of the maintenance task corresponding to the work well risk assessment result and the fault prediction result, and determine the target maintenance personnel matching the task field according to the maintenance professional field of the candidate maintenance personnel;

[0044] A visualization display module is used to visualize the three-dimensional model, the work well risk assessment result, the fault prediction result, the laying path and the maintenance personnel information.

[0045] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0046] Divide the underground power cable into regions, and obtain sensor data of each segmented region by setting sensors on each segmented region; the sensor data includes: three-dimensional point cloud data, well structure data, environmental data, and underground power cable operation data;

[0047] Establishing a work well risk assessment model according to the work well structure data and the environmental data, obtaining a work well risk assessment result using the work well risk assessment model, and inputting the underground power cable operation data into a trained fault prediction model to obtain a fault prediction result of the underground power cable output by the model;

[0048] Importing the three-dimensional point cloud data of each segmented area into a geographic information system, and having the geographic information system reconstruct the spatial position of the underground power cable according to the three-dimensional point cloud data to form a three-dimensional model of the underground power cable;

[0049] Based on the three-dimensional model, a graph structure corresponding to the area where the underground power cable is to be laid is constructed, and based on the node information and edge information in the graph structure, a laying path of the underground power cable is obtained;

[0050] Determine the task field of the maintenance task corresponding to the work well risk assessment result and the fault prediction result, and determine the target maintenance personnel matching the task field according to the maintenance professional field of the candidate maintenance personnel;

[0051] The three-dimensional model, the work well risk assessment result, the fault prediction result, the laying path and the maintenance personnel information are visualized.

[0052] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0053] Divide the underground power cable into regions, and obtain sensor data of each segmented region by setting sensors on each segmented region; the sensor data includes: three-dimensional point cloud data, well structure data, environmental data, and underground power cable operation data;

[0054] Establishing a work well risk assessment model according to the work well structure data and the environmental data, obtaining a work well risk assessment result using the work well risk assessment model, and inputting the underground power cable operation data into a trained fault prediction model to obtain a fault prediction result of the underground power cable output by the model;

[0055] Importing the three-dimensional point cloud data of each segmented area into a geographic information system, and having the geographic information system reconstruct the spatial position of the underground power cable according to the three-dimensional point cloud data to form a three-dimensional model of the underground power cable;

[0056] Based on the three-dimensional model, a graph structure corresponding to the area where the underground power cable is to be laid is constructed, and based on the node information and edge information in the graph structure, a laying path of the underground power cable is obtained;

[0057] Determine the task field of the maintenance task corresponding to the work well risk assessment result and the fault prediction result, and determine the target maintenance personnel matching the task field according to the maintenance professional field of the candidate maintenance personnel;

[0058] The three-dimensional model, the work well risk assessment result, the fault prediction result, the laying path and the maintenance personnel information are visualized.

[0059] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0060] Divide the underground power cable into regions, and obtain sensor data of each segmented region by setting sensors on each segmented region; the sensor data includes: three-dimensional point cloud data, well structure data, environmental data, and underground power cable operation data;

[0061] Establishing a work well risk assessment model according to the work well structure data and the environmental data, obtaining a work well risk assessment result using the work well risk assessment model, and inputting the underground power cable operation data into a trained fault prediction model to obtain a fault prediction result of the underground power cable output by the model;

[0062] Importing the three-dimensional point cloud data of each segmented area into a geographic information system, and having the geographic information system reconstruct the spatial position of the underground power cable according to the three-dimensional point cloud data to form a three-dimensional model of the underground power cable;

[0063] Based on the three-dimensional model, a graph structure corresponding to the area where the underground power cable is to be laid is constructed, and based on the node information and edge information in the graph structure, a laying path of the underground power cable is obtained;

[0064] Determine the task field of the maintenance task corresponding to the work well risk assessment result and the fault prediction result, and determine the target maintenance personnel matching the task field according to the maintenance professional field of the candidate maintenance personnel;

[0065] The three-dimensional model, the work well risk assessment result, the fault prediction result, the laying path and the maintenance personnel information are visualized.

[0066] The above-mentioned underground power cable management method, system, computer device, computer-readable storage medium and computer program product divide the underground power cable into regions, and obtain sensor data of each segmented region by setting sensors on each segmented region; the sensor data includes: three-dimensional point cloud data, work well structure data, environmental data, and underground power cable operation data; a work well risk assessment model is established based on the work well structure data and environmental data, and the work well risk assessment results are obtained by using the work well risk assessment model, and the underground power cable operation data is input into the trained fault prediction model to obtain the fault prediction results of the underground power cable output by the model; each segmented region is divided into The three-dimensional point cloud data of the domain is imported into the geographic information system, and the geographic information system reconstructs the spatial position of the underground power cable according to the three-dimensional point cloud data to form a three-dimensional model of the underground power cable; based on the three-dimensional model, the graph structure corresponding to the area to be laid of the underground power cable is constructed, and the laying path of the underground power cable to be laid is obtained based on the node information and edge information in the graph structure; the task field of the maintenance task corresponding to the risk assessment results and fault prediction results of the work well is determined, and the target maintenance personnel matching the task field are determined according to the maintenance professional field of the candidate maintenance personnel; the three-dimensional model, the risk assessment results of the work well, the fault prediction results, the laying path and the maintenance personnel information are visualized. This application enables the system to monitor the operating status of the cable more finely through regional division and real-time acquisition of sensor data, thereby enhancing the accuracy of management; at the same time, the application of the work well risk assessment and fault prediction model provides the ability to warn of potential risks in advance, significantly reduces the possibility of failures, and improves overall safety. On this basis, the application of three-dimensional models and graph structures makes the planning of cable laying paths more scientific and reasonable, thereby optimizing construction plans and saving resources. In addition, intelligent allocation of maintenance tasks based on the risk assessment results and fault prediction of work wells ensures that the most suitable personnel can perform maintenance tasks efficiently, improving the operating efficiency of the system. Finally, by integrating all key data into a comprehensive visual interface, the system not only improves the convenience of operation and decision-making efficiency, but also makes the management of underground power cables more transparent and efficient. Through the regional division of underground power cables, real-time acquisition of sensor data, application of work well risk assessment and fault prediction models, construction and path planning of three-dimensional models, intelligent maintenance task allocation, and comprehensive visual display of technical features, refined management, efficient fault prediction, intelligent construction path planning, and maintenance task optimization of complex underground power cable systems are achieved, significantly improving the management efficiency of underground power cables. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0068] FIG1 is a schematic diagram of a process of an underground power cable management method in one embodiment;

[0069] FIG2 is a schematic diagram of a flow chart of a fault prediction model training step in one embodiment;

[0070] FIG3 is a structural block diagram of an underground power cable management system in one embodiment;

[0071] FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0072] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0073] In one embodiment, as shown in FIG1 , an underground power cable management method is provided. This embodiment is illustrated by applying the method to a server. It is understandable that the method can also be applied to a terminal, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0074] Step S102, the underground power cable is divided into regions, and sensor data of each segmented area is obtained by setting sensors on each segmented area; the sensor data includes: three-dimensional point cloud data, work well structure data, environmental data, and underground power cable operation data.

[0075] Among them, regional division refers to dividing the entire cable system into several smaller, independent areas based on the physical characteristics of underground power cables (such as length, structural complexity) and operating environment (such as geographical location, geological conditions).

[0076] In this step, the underground power cables are systematically divided into regions. This division operation is intended to decompose the complex cable network into several easy-to-handle segmented regions. Each segmented region is equipped with multiple sensors to obtain detailed data in the region. The acquired data includes but is not limited to three-dimensional point cloud data, well structure data, environmental data, and underground power cable operation data.

[0077] Step S104, establishing a work well risk assessment model based on the work well structure data and environmental data, using the work well risk assessment model to obtain the work well risk assessment results, and inputting the underground power cable operation data into the trained fault prediction model to obtain the underground power cable fault prediction results output by the model.

[0078] For example, a well risk assessment model is established based on the collected well structure data and environmental data. The model is used to analyze the physical conditions of the well and the impact of the surrounding environment, and then generate risk assessment results for the well. This risk assessment model is then used to quantify the various risks of the well and generate assessment results, which are used to determine the safety status of the well and provide possible maintenance recommendations.

[0079] In addition, the operation data of underground power cables can be input into the trained fault prediction model. The fault prediction model predicts the type, probability and time range of possible faults of underground power cables by analyzing the input data. The output results of the fault prediction model provide decision support for operation and maintenance management, helping operation and maintenance personnel to take protective measures in advance and reduce the occurrence of sudden faults.

[0080] Step S106, importing the three-dimensional point cloud data of each segmented area into a geographic information system, and the geographic information system reconstructs the spatial position of the underground power cable according to the three-dimensional point cloud data to form a three-dimensional model of the underground power cable.

[0081] Optionally, the 3D point cloud data obtained from each segmented area is imported into a Geographic Information System (GIS). The GIS system reconstructs the spatial position of the underground power cable distribution according to the actual spatial position of the cable and the environmental characteristics by parsing these 3D point cloud data. Through this reconstruction process, the GIS system generates a complete 3D model of the underground power cable. The model not only reflects the accurate position and direction of the cable, but also can intuitively show the spatial relationship between the cable and the surrounding environment.

[0082] Step S108, constructing a graph structure corresponding to the area where the underground power cable is to be laid based on the three-dimensional model, and obtaining a laying path for the underground power cable based on the node information and edge information in the graph structure.

[0083] In the specific implementation, the constructed three-dimensional model of underground power cables can be used to determine the area where underground power cables are to be laid. Based on the terrain, building distribution and other relevant factors in the area, the server generates a graph structure consisting of multiple nodes and edges. Each node represents a possible cable laying point, and the edge represents the connection path between nodes. Then, based on the node information and edge information in this graph structure, the server calculates and generates the optimal laying path for the underground power cables to be laid.

[0084] Step S110, determining the task field of the maintenance task corresponding to the well risk assessment result and the fault prediction result, and determining the target maintenance personnel matching the task field according to the maintenance professional field of the candidate maintenance personnel.

[0085] Optionally, the server analyzes the well risk assessment results and fault prediction results to determine the task areas of the maintenance tasks corresponding to these results. Task areas can include different categories such as electrical engineering, structural maintenance, and environmental control. Then, the maintenance professional fields of candidate maintenance personnel are analyzed, and based on these field information, the target maintenance personnel who best fit the task field are matched. Finally, the system will determine the most suitable maintenance personnel to perform a specific maintenance task based on the matching results.

[0086] Step S112, visually displaying the three-dimensional model, work well risk assessment results, fault prediction results, laying path and maintenance personnel information.

[0087] For example, the server first integrates the generated 3D model of underground power cables, risk assessment results of work wells, fault prediction results, laying paths, and maintenance personnel information into a visual interface. Through this interface, operation and maintenance personnel can view and analyze these key data in a comprehensive view, thereby improving decision-making efficiency and accuracy.

[0088] In the above-mentioned underground power cable management method, the underground power cable is divided into regions, and the sensor data of each segmented region is obtained by setting sensors on each segmented region; the sensor data includes: three-dimensional point cloud data, work well structure data, environmental data, and underground power cable operation data; a work well risk assessment model is established based on the work well structure data and environmental data, and the work well risk assessment results are obtained by using the work well risk assessment model, and the underground power cable operation data is input into the trained fault prediction model to obtain the fault prediction results of the underground power cable output by the model; the three-dimensional point cloud data of each segmented region is imported into the geographic information system The system reconstructs the spatial position of underground power cables according to the three-dimensional point cloud data by the geographic information system to form a three-dimensional model of underground power cables; based on the three-dimensional model, a graph structure corresponding to the area to be laid of underground power cables is constructed, and the laying path of the underground power cables to be laid is obtained based on the node information and edge information in the graph structure; the task field of the maintenance task corresponding to the risk assessment results and fault prediction results of the work well is determined, and the target maintenance personnel matching the task field are determined according to the maintenance professional field of the candidate maintenance personnel; the three-dimensional model, the risk assessment results of the work well, the fault prediction results, the laying path and the maintenance personnel information are visualized. This application enables the system to monitor the operating status of the cable more finely through regional division and real-time acquisition of sensor data, thereby enhancing the accuracy of management; at the same time, the application of the work well risk assessment and fault prediction model provides the ability to warn of potential risks in advance, significantly reduces the possibility of failures, and improves overall safety. On this basis, the application of three-dimensional models and graph structures makes the planning of cable laying paths more scientific and reasonable, thereby optimizing construction plans and saving resources. In addition, intelligent allocation of maintenance tasks based on the risk assessment results and fault prediction of work wells ensures that the most suitable personnel can perform maintenance tasks efficiently, improving the operating efficiency of the system. Finally, by integrating all key data into a comprehensive visual interface, the system not only improves the convenience of operation and decision-making efficiency, but also makes the management of underground power cables more transparent and efficient. Through the regional division of underground power cables, real-time acquisition of sensor data, application of work well risk assessment and fault prediction models, construction and path planning of three-dimensional models, intelligent maintenance task allocation, and comprehensive visual display of technical features, refined management, efficient fault prediction, intelligent construction path planning, and maintenance task optimization of complex underground power cable systems are achieved, significantly improving the management efficiency of underground power cables.

[0089] In an exemplary embodiment, step S102 divides the underground power cable into regions, and obtains sensor data of each segmented region by setting sensors on each segmented region obtained by the division, including:

[0090] A preset identifier is set for each segmented area; the sensors installed in each segmented area are identified through the preset identifier, and the sensors are triggered to collect data at preset time intervals; the sensor data uploaded by the target sensor to the IoT gateway is obtained; the target sensor is a sensor among multiple sensors that communicates with the IoT gateway, and the other sensors among the multiple sensors except the target sensor are used to send the collected sensor data to the target sensor.

[0091] Among them, the sensors provided may include: strain gauges, displacement gauges, humidity sensors, water level sensors, fiber grating sensors, vibration sensors, current transformers, voltage transformers, resistance testers, partial discharge detectors, manhole cover status monitoring devices, harmful gas detectors, positioning devices, dielectric loss factor testers, laser scanners, ground penetrating radars and acoustic wave sensors.

[0092] Sensor data may include wellbore deformation and displacement, temperature, humidity, water level, pressure, vibration, current, voltage, resistance, intensity and frequency changes of partial discharge signals, manhole cover status data, harmful gas concentration, cable laying location data, dielectric loss factor, sound wave signals generated by cables during operation, three-dimensional point cloud data and the specific location of underground power cables.

[0093] Specifically, in the process of underground power cable management, the cables are segmented according to the needs, and a unique preset identifier is set for each segment area to facilitate management and data collection. The system deploys a wireless sensor network in each segment area. The network consists of a large number of sensor nodes, which form a wireless network through multi-hop. Each sensor node collects the environmental data of the area in real time through the built-in sensor element and converts these raw data into digital signals.

[0094] According to the preset identification, the server identifies the sensor nodes installed in each segmented area and triggers these sensors to collect data at preset time intervals. Each sensor node performs real-time detection and collection of environmental data in the coverage area. The node performs preliminary processing on the collected raw data, including data cleaning, format conversion, and local compression to reduce the amount of data transmitted subsequently. Sensor nodes communicate with each other through wireless communication technologies (such as WIFI, ZigBee, Loga, etc.), and data can be transmitted directly or indirectly between nodes. When there is interference or poor communication quality between sensor nodes, the nodes can use collaborative strategies to perform reliable transmission of multi-hop transmission and relay forwarding to ensure stable and accurate data transmission.

[0095] The server obtains the sensor data uploaded by the target sensor to the IoT gateway. The target sensor is the node that communicates with the IoT gateway among multiple sensor nodes. Other sensor nodes collaborate to send the collected data to the target sensor, which is then uploaded to the IoT gateway by the target sensor. The IoT gateway transmits the data to the cloud database, which is deployed in a distributed manner through cloud acquisition technology, improving data acquisition efficiency while reducing the cost and maintenance requirements of local deployment.

[0096] After receiving data from the IoT gateway, the cloud database integrates data from different sensor nodes and time periods through the configured API interface. After the integrated data is pre-processed by cleaning, filtering, and standardization, an index is established for each partition, connecting the relevant data collected in real time, thereby achieving rapid retrieval and efficient management of data. It also provides reliable data support for subsequent risk assessment, fault prediction, path planning, and maintenance task allocation.

[0097] In this embodiment, by setting up regional segmented management of underground power cables and collecting sensor data, accurate monitoring of the segmented areas of underground power cables can be achieved. At the same time, the target sensors are set, the data transmission path is optimized, and the stability and reliability of data transmission are improved, so that the cable status of each area can be accurately and timely understood, providing a solid foundation for the efficient and safe operation of the entire underground power cable system.

[0098] In an exemplary embodiment, in step S104, a work well risk assessment model is established based on the work well structure data and the environmental data, and the work well risk assessment result is obtained using the work well risk assessment model, including: obtaining the weights of the work well damage degree and environmental data corresponding to each work well; performing weighted aggregation on the work well damage degree and environmental data according to the weights to obtain the work well risk assessment model; using the work well risk assessment model to calculate the comprehensive risk value, comparing the comprehensive risk value with a preset risk level threshold, determining the risk level of the work well, and forming the work well risk assessment result.

[0099] The damage degree of the well refers to the physical damage of the well structure caused by various factors during long-term use. The damage may include physical changes such as deformation, cracks, displacement of the well cover, corrosion, etc. of the wellbore, which will affect the structural integrity of the well. The data on the damage degree of the well can be collected in real time through sensors such as strain gauges and displacement gauges installed in the well.

[0100] Environmental data covers the physical environment parameters around the well, such as temperature, humidity, water level, harmful gas concentration, air pressure, etc. These data reflect the external environmental conditions of the well and directly affect the physical state and operational stability of the well.

[0101] Specifically, the damage degree data and environmental data corresponding to each well are obtained, and weights are set for these data. The damage degree of the well is mainly determined based on the wellbore displacement and deformation data collected by the strain gauge and displacement meter, as well as the state parameters of the manhole cover. Specifically, the calculation of the damage degree is based on the following formula:

[0102]

[0103] Among them, P represents the degree of damage of the work well; S is the measurement value of the strain gauge, D is the measurement value of the displacement meter, G is the manhole cover status parameter, a, b, c, e, f, g are coefficients determined according to the actual conditions of different work wells. These coefficients are used to adjust the weight and influence of the function on different factors, so as to quantify the degree of damage of each work well and provide basic data for subsequent risk assessment together with environmental factors.

[0104] After obtaining the damage degree and environmental data of each well, the server will perform weighted aggregation on these data to establish a well risk assessment model. Specifically, the server will set weights for each assessment indicator and quantify the scores. For example, indicators such as temperature, humidity, water level, and concentration of harmful gases in the environmental data will be given different weights according to their impact on well safety. These weights will be incorporated into the assessment model together with the damage degree data to form a comprehensive risk value.

[0105] In order to comprehensively calculate the risk value of the well, mathematical models such as weighted summation and fuzzy comprehensive evaluation can be used. Through these methods, the server can integrate various data to generate a value that reflects the overall risk of the well. Combined with the historical data collected in the cloud server, the server can also train and verify the model to improve the accuracy and reliability of the model. At the same time, the model will introduce dynamic factors, such as time series data, to reflect the changing trend of well risk over time. The server will also continuously adjust the parameters and weights of the model according to the actual situation to ensure that the model can always accurately reflect the current well status.

[0106] After the well risk assessment model is established, the server will use the model to calculate the comprehensive risk value of the well. The calculated comprehensive risk value will be compared with the preset risk level threshold to determine the risk level of the well. The server presets the level classification of the well structure condition. In some embodiments, 0-40 indicates high risk and requires immediate maintenance; 40-60 indicates danger and should be repaired as soon as possible; 60-80 indicates qualified and should be maintained regularly; 80-100 indicates excellent and relevant data should be checked regularly. The server generates the risk assessment results of the well from these analysis results and stores them in the database for further decision-making and scheduling.

[0107] In addition, the server will regularly update and optimize the risk assessment model to adapt to new data and situations to ensure the continued effectiveness of the assessment results. By continuously adjusting model parameters and weights, and introducing dynamic factors such as time series data, and combining historical data for verification, the server can effectively improve the accuracy and reliability of risk assessment and ensure the safety and efficiency of well management.

[0108] In this embodiment, a work well risk assessment model is established by weighted aggregation of the damage degree and environmental data of the work well, and a quantitative assessment of the overall risk of the work well is achieved, so as to accurately identify the risk level of the work well and timely warn of potential safety hazards, thereby ensuring the safety and operational stability of the underground power cable system.

[0109] In an exemplary embodiment, the fault prediction model in step S106 is trained by the following steps, including: obtaining historical underground power cable operation data, and determining feature data related to underground power cable fault prediction results in the historical underground power cable operation data; inputting the feature data related to the underground power cable fault prediction results in the historical underground power cable operation data into the support vector machine model to be trained, and training the support vector machine model to be trained based on a preset kernel function and preset hyperparameters to obtain a support vector machine model to be evaluated; if the support vector machine model to be evaluated meets the evaluation criteria, outputting the support vector machine model to be evaluated to obtain a fault prediction model.

[0110] Among them, the historical underground power cable operation data refers to the data record of the underground power cable during the actual operation of the cable. The historical underground power cable operation data record may include the current, voltage, temperature, operation time, load condition and other operating parameters of the underground power cable that reflect the health status of the cable, as well as the corresponding fault labels. The fault label indicates whether an underground power cable fault has occurred, and in the event of a fault, indicates its fault type. Fault types may include insulation breakdown, ground fault, leakage fault, short circuit fault, cable aging, single point fault and open circuit fault.

[0111] Feature data is a key parameter extracted from historical operating data that is highly correlated with cable fault prediction results. Feature data can include the rate of change of temperature, current fluctuations, abnormal increase in cable surface temperature, etc. Feature data is used to train the support vector machine model to help the model identify which operating parameters best reflect the potential faults of the cable. The selection and extraction of feature data can be achieved through data preprocessing algorithms, such as principal component analysis (PCA), feature selection algorithms, etc.

[0112] Hyperparameters are some control parameters in the support vector machine model that are used to affect the training process and final performance of the model. Hyperparameters can include penalty parameters C, kernel function parameters (such as γ of radial basis function), etc., and optimization can be performed through cross-validation, grid search, or random search. The penalty parameter can be selected by traversing different penalty coefficient values ​​within a range and selecting the parameter value that makes the model perform best on the validation set as the penalty parameter. The penalty parameter determines the model's tolerance for misclassified samples. A smaller penalty coefficient makes the model more tolerant to misclassified samples, but it may be too lenient; a larger penalty coefficient makes the model more strict to misclassification, but it may also lead to overfitting.

[0113] Evaluation criteria refer to the indicators used to measure the performance of the model after training. Evaluation criteria can include accuracy, precision, recall, F1 score, etc.

[0114] Optionally, as shown in FIG2 , the server first extracts the historical operation data of underground power cables from the cloud server and preprocesses the operation data. During the data preprocessing, the server cleans, annotates and normalizes the data to ensure the consistency and quality of the data.

[0115] Then, the preprocessed data is analyzed using a feature selection algorithm to select features that are relevant to the cable fault prediction results, which may be sudden changes in cable temperature, abnormal fluctuations in current, and drastic changes in external temperature and humidity.

[0116] After completing the feature data selection, the feature data set is divided into a training set, a validation set, and a test set. In some embodiments, the ratio of each set can be 60% training set, 20% validation set, and 20% test set. The training set of feature data is input into the support vector machine model to be trained, and the appropriate kernel function and hyperparameters are selected to perform model training, and the patterns and laws in the learning data are optimized to optimize its prediction ability. During the training process, the hyperparameters of the model are continuously adjusted by the cross-validation method, and the model is optimized by minimizing the training error. After the training is completed, the server will use the validation set and the test set to evaluate the performance of the support vector machine model according to the evaluation criteria. If the model does not meet the evaluation criteria, the hyperparameters will continue to be tuned, and features can be added or modified, and the model will be retrained until the model meets the evaluation criteria on the validation set and the test set. When the support vector machine model reaches the preset evaluation criteria in the evaluation, it will be used as the final fault prediction model, and the model will be saved to the cloud server. After receiving these results, the cloud server retrieves historical data according to the problem keywords and provides corresponding maintenance suggestions.

[0117] Specifically, the server obtains a set of historical data of underground power cables, which includes features such as current, temperature, partial discharge at different times, and marks whether a failure will occur in the future. The server first preprocesses this data and then selects appropriate features, such as current change rate, temperature anomalies, etc. Then, the support vector machine model is trained with the selected feature data, and the parameters are continuously adjusted to make the model perform well on the validation set. Finally, the trained model is deployed to the system. When new cable data is input, the server can use the model to predict whether it may fail and provide corresponding maintenance suggestions.

[0118] In this embodiment, by obtaining historical underground power cable operation data, extracting key feature data for fault prediction, and inputting it into the support vector machine model for training, an efficient fault prediction model is obtained. The model can accurately predict potential faults of underground power cables, provide early warnings, and provide fault types, locations, and probability of occurrence, thereby improving the safety and operational stability of the cable system.

[0119] In one embodiment, in step S108, the three-dimensional point cloud data of each segmented area is imported into a geographic information system, and the geographic information system reconstructs the spatial position of the underground power cable according to the three-dimensional point cloud data to form a three-dimensional model of the underground power cable, including: aligning the three-dimensional point cloud data of each segmented area to the same coordinate system to obtain the aligned three-dimensional point cloud data; inputting the aligned three-dimensional point cloud data into the geographic information system, and the geographic information system identifies the location layout of the underground power cable according to the aligned three-dimensional point cloud data and historical underground power cable data; and spatially reconstructing the location layout of the underground power cable to form a three-dimensional model of the underground power cable.

[0120] Among them, 3D point cloud data can be collected by laser scanning, ground penetrating radar (GPR) or other surveying and mapping equipment to represent objects or surfaces in space. Point cloud data consists of a large number of discrete points, each with 3D coordinates, which can accurately describe the shape and position of the object. In power cable management, 3D point cloud data is used to capture the spatial form of the cable and its surrounding environment.

[0121] Optionally, the server will register the 3D point cloud data obtained from each segmented area. Since data collection in different areas may be performed at different times, locations, and reference frames, the server aligns the 3D point cloud data into a unified global coordinate system. Through registration, the server merges multiple scan data sets to eliminate the displacement, rotation, and scaling differences between different data sets, ensuring that they have a consistent coordinate system in the same spatial reference frame.

[0122] After completing the registration, the server inputs these registered three-dimensional point cloud data into the GIS system. In the GIS system, the server combines the existing historical power cable data, which may include old drawings, construction records, and maintenance records, to conduct further spatial analysis of the three-dimensional point cloud data. In some embodiments, the server collects old drawings and related historical data in the geographic information platform, conducts a preliminary assessment of the quantity, type, quality, and integrity of these data, and formulates a detailed scanning work plan based on this, and determines the priority of scanning and digitization. The historical data that has not yet been digitized is converted into a digital format by scanning, optical character recognition, or manual input, and is associated with the index and metadata of the old drawings (such as title, date, number, etc.) to facilitate subsequent rapid positioning and retrieval.

[0123] The GIS system identifies the specific location and direction of underground power cables by analyzing the density, shape and characteristics of the three-dimensional point cloud data. After obtaining the location and direction of the underground power cables, the server uses the three-dimensional reconstruction algorithm in the GIS system to reconstruct the spatial position of the underground power cables and convert the identified cable location layout into a three-dimensional model with a surface structure. This three-dimensional model not only shows the geometric shape of the cable, but also reflects the spatial relationship between the cable and the surrounding geographical environment. The generated three-dimensional model is further optimized and adjusted by the server, including smoothing and removing redundant points, to ensure the accuracy and visualization of the model, and obtain a three-dimensional model of the underground power cables.

[0124] Exemplarily, the server establishes a connection with the cloud server to obtain the real-time collected data related to the underground power cable. By setting the corresponding interface, the server can associate the cloud data with the three-dimensional model. Specifically, the server determines the attachment method and location of the data on the model according to the attributes of the data. In the GIS system, the server sets a suitable rendering effect and sets a basic file for each section of the power cable. The basic file can digitally display the global data such as the underground location, depth, space size occupied, and completion drawing of the power cable.

[0125] The server can quickly search for basic archive information of the power cable in the corresponding segmented area according to the identifier. At the same time, the server can realize the visual display of data according to the mapping relationship between the relevant data collected in real time and the three-dimensional model based on the identifier and its index. In some embodiments, the server can set a corresponding icon mode for each segmented area to display electrical parameters such as current and voltage.

[0126] In this embodiment, by systematically collecting, processing and integrating old data and new data collected in real time, and importing these data into the GIS system for spatial analysis and three-dimensional modeling, the precise positioning and morphological display of underground power cables are achieved, which significantly improves the intelligent level of cable system management, maintenance and planning.

[0127] In an exemplary embodiment, in step S110, based on the node information and edge information in the graph structure, obtaining the laying path of the underground power cable to be laid includes:

[0128] Based on the node information in the graph structure, the points where underground power cables are to be laid are determined, the starting node and the target node are determined from the points where underground power cables are to be laid, and the starting node is used as the current node; the neighbor nodes of the current node are searched; for each neighbor node, the distance between the current node and the neighbor node is determined, and the sum of the distance and the preset edge weight is determined; the preset edge weight is the weight of the edge connecting the current node and the neighbor node, which is determined based on the edge information in the graph structure; the neighbor node with the smallest sum is determined as the path access node; the path access node is determined as the current node, and the step of searching the neighbor nodes of the current node is returned to execute, until the neighbor nodes obtained by the search include the target node, and the laying path of the underground power cable to be laid is obtained according to each path access node.

[0129] Specifically, the server analyzes the built 3D model and constructs the underground cable laying area into a graph structure. Each node in the graph structure represents a possible cable laying point, and the edge represents the connection relationship between these nodes. The setting of nodes can be based on geographical factors such as topography, urban construction planning, underground pipeline distribution, and existing power facilities, as well as human factors such as population density and electricity demand data.

[0130] After all nodes are determined, the server selects the starting node and the target node from the points where the underground power cables are to be laid. The starting node can be the starting point for laying the power cable, such as a power substation, and the target node can be the end point where the cable needs to be connected, such as a city block with high power consumption. The server sets the starting node as the current node and starts the path search process.

[0131] In the path search process, starting from the current node, the neighbor nodes directly connected to it are searched one by one. In the graph structure, the neighbor node is the node directly connected to the current node through an edge. The neighbor node represents the next step where the cable can be directly laid from the current node.

[0132] For each neighbor node found, the server calculates the distance between the current node and the neighbor node. At the same time, the server also calculates the sum of this distance and the preset edge weight. The edge weight is determined based on the edge information in the graph structure, which may include the laying cost, distance, complexity of geological conditions, and other possible related factors. In a specific embodiment, path A needs to pass through an underground water system or a densely populated area. According to the construction cost and risk of such areas, the corresponding edge weight of the edge in the area is adjusted.

[0133] After calculating the weighted distances between the current node and all neighboring nodes, the server will select the neighboring node with the smallest weighted distance as the next path visit node. This means that this node is not only the shortest distance to the current node, but also has the lowest overall path cost after comprehensively considering costs and other factors.

[0134] Next, the server sets the newly selected path access node as the current node and repeats the above process of searching for neighbor nodes. For each new current node, the server recalculates the sum of the distance and edge weights between its neighbor nodes and continues to search for the next optimal path access node. This process will continue to iterate until all nodes are visited or until the optimal path from the starting node to the target node is found. In each step of the selection, the server will combine the real-time data obtained from the GIS system to ensure that the selection of each node meets the current geographical and construction conditions.

[0135] When the target node is included in the neighbor nodes found by the server, it means that the optimal path has been found. The server will trace back from the target node to the starting node based on the information of the predecessor node, and finally build the shortest cable laying path. In this process, the server will record the path information of each node to form a complete path planning report.

[0136] In this embodiment, by constructing the node information and edge information of the graph structure of the underground power cable based on the three-dimensional model, the laying path of the power cable to be laid is determined, which significantly improves the efficiency and accuracy of the underground power cable laying, reduces the uncertainty and potential risks in the construction process, and provides reliable technical support and scientific decision-making basis for the planning and construction of urban power infrastructure.

[0137] In some embodiments, in step S112, determining a target maintenance personnel that matches the task field according to the maintenance professional field of the candidate maintenance personnel includes:

[0138] The maintenance professional field and task field of the candidate maintenance personnel are matched and calculated to generate the field matching degree; the busyness of the candidate maintenance personnel is calculated according to the workload of the candidate maintenance personnel; and the target maintenance personnel are determined from the candidate maintenance personnel based on the field matching degree and the busyness.

[0139] Optionally, the server extracts the specific field of the task from the evaluation results and fault prediction results output by the well management module. The task field may include multiple professional fields such as electrical engineering, cable technology, high voltage technology, detection and diagnosis, etc. The server then analyzes the professional fields of the candidate maintenance personnel and quantitatively scores the professional capabilities of the maintenance personnel in various maintenance professional fields based on the preset evaluation criteria. By comparing these scores, the field matching degree of each maintenance personnel in each task field is generated.

[0140] After determining the domain matching, the server evaluates the current workload of each maintenance staff. Work matching can be determined by comprehensively evaluating the number, type, estimated completion time, and remaining working time of the maintenance staff's current tasks. Combined with the workload, the server determines the busyness of each maintenance staff and determines whether they can accept and complete new tasks within the required time.

[0141] Based on the comprehensive analysis results of domain matching and busyness, combined with the urgency of the task, the server prioritizes assigning tasks to maintenance personnel with high domain matching and light current workload.

[0142] Exemplarily, there are three maintenance personnel A, B and C. The three maintenance personnel have different professional capabilities and current workload status. There are three underground power cable maintenance tasks that need to be assigned. The current maintenance task areas are determined. Task A is the electrical engineering field, Task B is the cable technology field, and Task C is the high voltage technology field.

[0143] According to the preset evaluation criteria, the professional capabilities of maintenance personnel in various fields are scored. For example, Person A scored 85 in the field of electrical engineering, 80 in the field of cable technology, 75 in the field of high voltage technology, and 70 in the field of detection and diagnosis; Person B scored 70 in the field of electrical engineering, 75 in the field of cable technology, 80 in the field of high voltage technology, and 65 in the field of detection and diagnosis; Person C scored 60 in the field of electrical engineering, 65 in the field of cable technology, 70 in the field of high voltage technology, and 75 in the field of detection and diagnosis. It can be determined that Person A has the highest task field matching degree in the electrical field, Person B has the highest task field matching degree in the field of high voltage electricity, and Person C has the highest task field matching degree in the field of detection and diagnosis.

[0144] Continuing to examine the workload of maintenance personnel, A currently has 2 electrical engineering tasks and 1 cable technology task to be processed, which is expected to be completed in 6 hours; B has 1 high voltage technology task and 1 detection and diagnosis task, which is expected to be completed in 4 hours; C has no tasks to be processed. According to the maintenance personnel's working hours and vacation information. A can still work 4 hours today; B has 3 hours of work time today; C can work all day today.

[0145] Combining the urgency of the three maintenance tasks, Task A belongs to the field of electrical engineering and has a high urgency, Task B belongs to the field of cable technology and has a medium urgency, and Task C belongs to the field of high voltage technology and has a low urgency.

[0146] Comprehensive analysis shows that for Task A, after comparing the matching degrees of A, B, and C in the field of electrical engineering, A has the highest matching degree, and A still has working time, so Task A is assigned to A; for Task B, in the field of cable technology, A and B have a high matching degree, but A is currently busy, so Task B is assigned to B; for Task C, C has a relatively high matching degree in the field of high voltage technology and is free, so Task C is assigned to C.

[0147] In this embodiment, by accurately calculating the domain matching degree of each maintenance personnel and combining their current workload and busyness, it is ensured that the task can be handled by the most suitable personnel in a timely manner. This scheduling method not only improves the utilization rate of resources, but also significantly reduces the time cost of fault handling and enhances the overall operation and maintenance efficiency.

[0148] In order to enable those skilled in the art to better understand the above steps, the embodiment of the present application is illustrated below by using an example, but it should be understood that the embodiment of the present application is not limited to this.

[0149] In the implementation of the underground power cable management method, a preset identifier is first set for each segment area so that the system can identify and manage the data collection tasks of each area. Through the preset identifier, the system identifies the sensors installed in each segment area and triggers these sensors to collect data at preset time intervals. The system obtains sensor data from the target sensor that communicates with the IoT gateway. These data are uploaded to the central server for further analysis.

[0150] Next, the system establishes a risk assessment model for the well based on the well structure data and environmental data, calculates the comprehensive risk value of the well through the model, and then evaluates the risk level of the well. At the same time, the system obtains historical underground power cable operation data and extracts feature data related to faults, inputs these data into the support vector machine model for training, and forms a fault prediction model. After the real-time operation data is input into the model, the system can predict the fault condition of the cable and provide early warning information.

[0151] After completing data collection and risk assessment, the system imports the 3D point cloud data into the geographic information system, and uses the geographic information system to spatially reconstruct the location of underground power cables and generate a 3D model of the cable. To ensure the accuracy of the model, the system first aligns the point cloud data of each segmented area and unifies them to the same coordinate system, then combines historical cable data to identify the location and layout of the cable, and finally generates a complete 3D model to display the geometric shape and spatial distribution of the cable.

[0152] Based on the generated 3D model, the system further constructs the graph structure of the cable laying area and plans the optimal cable laying path through node information and edge information. In this process, the system selects the starting node and the target node, and calculates the weighted distance between these nodes, and finally determines the laying plan with the best path and the lowest cost, ensuring the efficiency and economy of the construction.

[0153] In addition, the system will combine the results of well risk assessment and fault prediction to determine the task areas of relevant maintenance tasks, and select the most suitable maintenance personnel to perform the tasks based on the professional areas and current workload of the candidate maintenance personnel. By calculating the field matching degree and busyness of each maintenance personnel, the system can intelligently assign tasks, giving priority to assigning urgent tasks to maintenance personnel with high field matching degree and light workload, thereby improving the efficiency of maintenance work.

[0154] The system integrates all key data into a visualization platform for display, including 3D models, well risk assessment results, fault prediction results, laying paths, and maintenance personnel information.

[0155] Specifically, the system outputs the 3D model in GIS on the visualization platform and loads the model into the view (Scene). Users can adjust the display effect by setting layer properties, including color, transparency, etc., and add annotation layers for annotation, and then use functions such as Export to output the 3D scene for further analysis and application.

[0156] In the visualization platform, the basic archive information and real-time collected data of each section of underground power cable can be accurately indexed by preset identifiers. The data includes but is not limited to basic information such as cable specifications, installation time, operating status, related ledgers, completion drawings, and real-time monitored dynamic data such as current, voltage, and temperature.

[0157] Furthermore, the relevant staff triggers the corresponding operation by clicking on the underground power cable node in the visualization interface. When a node is clicked, the system will immediately display the real-time data of the cable section, such as the current current value, temperature, etc., and call its basic archive information at the same time, including past operation data and maintenance records. The method also includes clearly displaying the evaluation results, prediction results and corresponding maintenance suggestions in the work well management in the form of a report, so that the relevant staff can obtain the status information of the work well and the measures to be taken, and check whether the maintenance personnel have been dispatched for maintenance.

[0158] At the same time, in the interface with the path planning of the visualization platform, relevant staff can input specific node information; and provide maintenance personnel with an interface for uploading maintenance data and pictures. After completing the intelligently assigned maintenance tasks, maintenance personnel can upload relevant data through this interface. The uploaded information is accurately associated with the relevant underground power cable basic archives according to the index. The data is uploaded to the cloud server in real time for storage to ensure the security and traceability of the data, thereby realizing the full life cycle ledger management of underground cables from construction to decommissioning, and providing support for subsequent analysis and decision-making.

[0159] In this embodiment, a number of technical effects are achieved, including refined management of underground power cables, risk warning and fault prediction, three-dimensional space visualization, path optimization and intelligent maintenance scheduling. It can identify and respond to potential risks in advance, optimize cable laying paths, and improve the efficiency of maintenance work. At the same time, through comprehensive visual management, the convenience of operation and the accuracy of decision-making are improved, ultimately ensuring the safety and efficient operation of the cable system.

[0160] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0161] Based on the same inventive concept, the embodiment of the present application also provides an underground power cable management system for implementing the underground power cable management method involved above. The implementation scheme for solving the problem provided by the system is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more underground power cable management system embodiments provided below can refer to the limitations of the underground power cable management method above, and will not be repeated here.

[0162] In an exemplary embodiment, as shown in FIG3 , an underground power cable management system is provided, comprising:

[0163] The data acquisition module 302 is used to divide the underground power cable into regions, and obtain sensor data of each segmented region by setting sensors on each segmented region; the sensor data includes: three-dimensional point cloud data, well structure data, environmental data, and underground power cable operation data;

[0164] A work well management module 304 is used to establish a work well risk assessment model according to the work well structure data and the environmental data, obtain a work well risk assessment result using the work well risk assessment model, and input the underground power cable operation data into a trained fault prediction model to obtain a fault prediction result of the underground power cable output by the model;

[0165] A three-dimensional modeling module 306 is used to import the three-dimensional point cloud data of each segmented area into a geographic information system, and the geographic information system reconstructs the spatial position of the underground power cable according to the three-dimensional point cloud data to form a three-dimensional model of the underground power cable;

[0166] A path planning module 308 is used to construct a graph structure corresponding to the area to be laid underground power cables based on the three-dimensional model, and obtain a laying path for the underground power cables to be laid based on node information and edge information in the graph structure;

[0167] The maintenance scheduling module 310 is used to determine the task field of the maintenance task corresponding to the well risk assessment result and the fault prediction result, and determine the target maintenance personnel matching the task field according to the maintenance professional field of the candidate maintenance personnel;

[0168] The visualization display module 312 is used to visualize the three-dimensional model, the work well risk assessment result, the fault prediction result, the laying path and the maintenance personnel information.

[0169] In one embodiment, the data acquisition module 302 is used to:

[0170] Set preset labels for each segment area;

[0171] By using preset labels, the sensors installed in each segment area are identified, and the sensors are triggered to collect data at preset time intervals;

[0172] The sensor data uploaded by the target sensor to the IoT gateway is obtained; the target sensor is a sensor among multiple sensors that communicates with the IoT gateway, and the other sensors among the multiple sensors except the target sensor are used to send the collected sensor data to the target sensor.

[0173] In one embodiment, the well management module 304 is used to:

[0174] Obtain the weight of the damage degree and environmental data of each work well;

[0175] The damage degree of the well and the environmental data are weighted and aggregated according to the weights to obtain the well risk assessment model;

[0176] The comprehensive risk value is calculated using the well risk assessment model, and the comprehensive risk value is compared with the preset risk level threshold to determine the risk level of the well and form the well risk assessment result.

[0177] In one embodiment, the well management module 304 is used to:

[0178] Acquire historical underground power cable operation data, and determine characteristic data in the historical underground power cable operation data that is related to underground power cable fault prediction results;

[0179] Inputting feature data related to underground power cable fault prediction results in historical underground power cable operation data into the support vector machine model to be trained, training the support vector machine model to be trained based on a preset kernel function and preset hyperparameters, and obtaining a support vector machine model to be evaluated;

[0180] If the support vector machine model to be evaluated meets the evaluation criteria, the support vector machine model to be evaluated is output to obtain a fault prediction model.

[0181] In one embodiment, the three-dimensional modeling module 306 is used to:

[0182] The three-dimensional point cloud data of each segmented area are registered to the same coordinate system to obtain the registered three-dimensional point cloud data;

[0183] The registered 3D point cloud data is input into the geographic information system, and the geographic information system identifies the location layout of underground power cables based on the registered 3D point cloud data and historical power cable data;

[0184] The spatial position layout of underground power cables is reconstructed to form a three-dimensional model of underground power cables.

[0185] In one embodiment, the path planning module 308 is used to:

[0186] Determine the points where underground power cables are to be laid based on the node information in the graph structure, determine the starting node and the target node from the points where underground power cables are to be laid, and use the starting node as the current node;

[0187] Search for neighbor nodes of the current node;

[0188] For each neighbor node, determine the distance between the current node and the neighbor node, and determine the sum of the distance and the preset edge weight; the preset edge weight is the weight of the edge connecting the current node and the neighbor node determined based on the edge information in the graph structure;

[0189] Determine the neighbor node with the smallest sum as the path access node;

[0190] The path access node is determined as the current node, and the step of searching for neighbor nodes of the current node is returned to execute until the neighbor nodes obtained by the search include the target node, and the laying path of the underground power cable to be laid is obtained according to each path access node.

[0191] In one embodiment, the maintenance scheduling module 310 is used to:

[0192] Perform matching calculation on the maintenance professional field and task field of candidate maintenance personnel to generate field matching degree;

[0193] Calculate the busyness of the candidate maintenance personnel according to their workload;

[0194] Based on the domain matching and busyness, target maintainers are identified from the candidate maintainers.

[0195] Each module in the above-mentioned underground power cable management system can be implemented in whole or in part by software, hardware and their combination. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.

[0196] In an exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be shown in FIG4. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store visualization application data, and the data may include: three-dimensional models, well risk assessment results, fault prediction results, laying paths and maintenance personnel information. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for managing underground power cables is implemented.

[0197] Those skilled in the art will understand that the structure shown in FIG. 4 is merely a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0198] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0199] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0200] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0201] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0202] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database:. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0203] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0204] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for managing underground power cables, characterized in that: The method comprises: Divide the underground power cable into regions, and obtain sensor data of each segmented region by setting sensors on each segmented region; the sensor data includes: three-dimensional point cloud data, well structure data, environmental data, and underground power cable operation data; Establishing a work well risk assessment model according to the work well structure data and the environmental data, obtaining a work well risk assessment result using the work well risk assessment model, and inputting the underground power cable operation data into a trained fault prediction model to obtain a fault prediction result of the underground power cable output by the model; Importing the three-dimensional point cloud data of each segmented area into a geographic information system, and having the geographic information system reconstruct the spatial position of the underground power cable according to the three-dimensional point cloud data to form a three-dimensional model of the underground power cable; Based on the three-dimensional model, a graph structure corresponding to the area where the underground power cable is to be laid is constructed, and based on the node information and edge information in the graph structure, a laying path of the underground power cable is obtained; Determine the task field of the maintenance task corresponding to the work well risk assessment result and the fault prediction result, and determine the target maintenance personnel matching the task field according to the maintenance professional field of the candidate maintenance personnel; The three-dimensional model, the work well risk assessment result, the fault prediction result, the laying path and the maintenance personnel information are visualized.

2. The method according to claim 1, characterized in that The step of dividing the underground power cable into regions and acquiring sensor data of each segmented region by setting sensors on each segmented region obtained by the division includes: Setting a preset identifier for each of the segmented areas; Identify the sensors installed in each of the segmented areas by using the preset identifiers, and trigger the sensors to collect data at preset time intervals; Acquire the sensor data uploaded by the target sensor to the Internet of Things gateway; the target sensor is a sensor among the multiple sensors that communicates with the Internet of Things gateway, and the other sensors among the multiple sensors except the target sensor are used to send the collected sensor data to the target sensor.

3. The method according to claim 1, characterized in that The step of establishing a work well risk assessment model according to the work well structure data and the environment data, and obtaining a work well risk assessment result using the work well risk assessment model includes: Obtaining the damage degree of each work well and the weight of the environmental data corresponding to each work well; Performing weighted aggregation on the damage degree of the working well and the environmental data according to the weights to obtain a working well risk assessment model; The risk assessment model for the work well is used to calculate a comprehensive risk value, which is compared with a preset risk level threshold to determine the risk level of the work well and form a risk assessment result for the work well.

4. The method according to claim 1, characterized in that: The fault prediction model is trained by the following steps, including: Acquire historical underground power cable operation data, and determine characteristic data related to underground power cable fault prediction results in the historical underground power cable operation data; Inputting the feature data related to the underground power cable fault prediction result in the historical underground power cable operation data into the support vector machine model to be trained, training the support vector machine model to be trained based on a preset kernel function and preset hyperparameters to obtain a support vector machine model to be evaluated; If the support vector machine model to be evaluated meets the evaluation criteria, the support vector machine model to be evaluated is output to obtain the fault prediction model.

5. The method according to claim 1, characterized in that The method of importing the three-dimensional point cloud data of each segmented area into a geographic information system, and reconstructing the spatial position of the underground power cable by the geographic information system according to the three-dimensional point cloud data to form a three-dimensional model of the underground power cable, comprises: Registering the three-dimensional point cloud data of each segmented area to the same coordinate system to obtain the registered three-dimensional point cloud data; Inputting the registered three-dimensional point cloud data into the geographic information system, and the geographic information system identifying the location layout of the underground power cables according to the registered three-dimensional point cloud data and historical underground power cable data; The location layout of the underground power cables is spatially reconstructed to form the three-dimensional model of the underground power cables.

6. The method according to claim 1, characterized in that The obtaining, based on the node information and edge information in the graph structure, a laying path of the underground power cable to be laid comprises: Determine the points where the underground power cable is to be laid based on the node information in the graph structure, determine the starting node and the target node from the points where the underground power cable is to be laid, and use the starting node as the current node; Search for neighbor nodes of the current node; For each of the neighbor nodes, determine the distance between the current node and the neighbor node, and determine the sum of the distance and a preset edge weight; the preset edge weight is the weight of the edge connecting the current node and the neighbor node, which is determined based on the edge information in the graph structure; Determine the neighbor node with the smallest sum as a path access node; The path access node is determined as the current node, and the step of searching for neighbor nodes of the current node is returned to execute until the neighbor nodes obtained by the search include the target node, and the laying path of the underground power cable to be laid is obtained according to each path access node.

7. The method according to claim 1, characterized in that The step of determining a target maintenance personnel matching the task field according to the maintenance professional field of the candidate maintenance personnel includes: Performing a matching calculation between the maintenance professional field of the candidate maintenance personnel and the task field to generate a field matching degree; Calculating the busyness of the candidate maintenance personnel according to the workload of the candidate maintenance personnel; The target maintenance personnel is determined from the candidate maintenance personnel based on the field matching degree and the busyness.

8. An underground power cable management system, characterized in that: The system comprises: The data acquisition module is used to divide the underground power cable into regions, and obtain sensor data of each segmented region through sensors arranged on each segmented region; the sensor data includes: three-dimensional point cloud data, well structure data, environmental data, and underground power cable operation data; A work well management module, used to establish a work well risk assessment model according to the work well structure data and the environmental data, obtain a work well risk assessment result using the work well risk assessment model, and input the underground power cable operation data into a trained fault prediction model to obtain a fault prediction result of the underground power cable output by the model; A three-dimensional modeling module, used for importing the three-dimensional point cloud data of each segmented area into a geographic information system, and the geographic information system reconstructs the spatial position of the underground power cable according to the three-dimensional point cloud data to form a three-dimensional model of the underground power cable; A path planning module, for constructing a graph structure corresponding to the area to be laid underground power cables based on the three-dimensional model, and obtaining a laying path for the underground power cables to be laid based on node information and edge information in the graph structure; A maintenance scheduling module, used to determine the task field of the maintenance task corresponding to the work well risk assessment result and the fault prediction result, and determine the target maintenance personnel matching the task field according to the maintenance professional field of the candidate maintenance personnel; A visualization display module is used to visualize the three-dimensional model, the work well risk assessment result, the fault prediction result, the laying path and the maintenance personnel information.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images