Operation and maintenance management method and system for railway power supply and distribution

Abstract

The invention relates to the technical field of railway power supply and distribution, particularly provides an operation and maintenance management method and system for railway power supply and distribution, and is used for solving the problem of low operation and maintenance management efficiency caused by poor accuracy of fault identification and positioning. The method comprises the following steps: receiving equipment operation data of a railway power supply and distribution system collected by a sensor network through the Internet of Things; inputting the data into a pre-trained graph neural network model, and identifying a fault equipment identifier and a fault mode; determining a target fault propagation path according to the fault equipment identifier, the fault mode and the multi-level power supply and distribution knowledge graph; wherein the multi-level power supply and distribution mapping knowledge domain comprises an equipment level mapping knowledge domain, a region level mapping knowledge domain and a system level mapping knowledge domain which are associated with one another; according to the target fault propagation path, a fault severity evaluation model is adopted to predict the fault severity, a corresponding operation and maintenance management report is determined, and corresponding processing is carried out according to the operation and maintenance management report. According to the technical scheme provided by the invention, the operation and maintenance management efficiency is improved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical field of railway power supply and distribution, and in particular to an operation and maintenance management method and system for railway power supply and distribution. Background Art

[0002] The railway power supply and distribution system is a key infrastructure for railway transportation, responsible for providing reliable power supply to various equipment along the railway. With the continuous expansion of the railway network and the advancement of technology, the complexity and importance of the railway power supply and distribution system are increasing. In order to ensure railway safety, how to quickly and accurately realize the operation and maintenance management of the railway power supply and distribution system is particularly important in this scenario.

[0003] Traditional operation and maintenance management methods can often only identify the failure of a single device and then perform operation and maintenance management on the single device. However, the railway power supply and distribution system is a complex network that contains a large number of devices with complex relationships between them. Therefore, traditional operation and maintenance management methods cannot accurately analyze the propagation path of the fault in the entire railway power supply and distribution system. This limitation further leads to major problems: the failure to accurately locate the source of the fault, resulting in blind and inefficient maintenance work; the failure to accurately predict the scope of the fault may cause the fault to spread and affect a wider range of equipment. Summary of the invention

[0004] The embodiment of the present invention provides an operation and maintenance management method and system for railway power supply and distribution, which are used to solve the problem of low operation and maintenance management efficiency caused by poor accuracy of fault identification and positioning in the prior art.

[0005] In a first aspect, an embodiment of the present invention provides an operation and maintenance management method for railway power supply and distribution, comprising: Receive the operating data of equipment in the railway power supply and distribution system collected by the sensor network through the Internet of Things technology; Inputting the operating data of the device into a pre-trained graph neural network model to identify the faulty device identification and the fault mode; Determine a target fault propagation path according to the faulty device identification, the fault mode and the multi-level power supply and distribution knowledge graph; the target fault propagation path is a propagation path of the faulty device corresponding to the faulty device identification in the railway power supply and distribution system; the multi-level power supply and distribution knowledge graph includes mutually related device-level knowledge graphs, regional-level knowledge graphs and system-level knowledge graphs; According to the target fault propagation path, a fault severity assessment model is used to predict the fault severity, a corresponding operation and maintenance management report is determined according to the fault severity, and corresponding processing is performed according to the operation and maintenance management report.

[0006] Optionally, the target fault propagation path is determined according to the faulty device identifier, the fault mode and the multi-level power supply and distribution knowledge graph; the target fault propagation path is the propagation path of the faulty device corresponding to the faulty device identifier in the railway power supply and distribution system; the multi-level power supply and distribution knowledge graph includes mutually related device-level knowledge graphs, regional-level knowledge graphs and system-level knowledge graphs, including: Construct a multi-level power supply and distribution knowledge graph including interrelated equipment-level knowledge graph, region-level knowledge graph and system-level knowledge graph; An association rule mining algorithm is used to establish an association rule system based on the multi-level power supply and distribution knowledge graph; the association rule system includes: local association rules, cross-regional association rules and global association rules; The local association rules are verified by using the device-level knowledge graph, the cross-regional association rules are verified by using the region-level knowledge graph, and the global association rules are verified by using the system-level knowledge graph; When all verification results are passed, the fault mode is processed based on the faulty device identification and the association rule system to obtain a target fault propagation path.

[0007] Optionally, the constructing includes a multi-level power supply and distribution knowledge graph including an interrelated device-level knowledge graph, a region-level knowledge graph, and a system-level knowledge graph, including: A first node and a first edge are defined, and a device-level knowledge graph is constructed based on the first node and the first edge; wherein the attribute information of the first node includes: basic information of the device, performance parameters of the device, historical operation data of the device, historical fault data of the device, and historical operation and maintenance data of the device; and the first edge includes connection information between devices, device standards and specifications, and expert knowledge about the device; Define a second node and a second edge, and construct a regional hierarchical knowledge graph based on the second node and the second edge; wherein the attribute information of the second node includes: regional basic information, regional equipment list, regional historical operation data, regional historical fault data, and regional historical operation and maintenance data; the second edge includes inter-regional connection information, regional standards and specifications, and expert knowledge of the region; Define a third node and a third edge, and construct a system-level knowledge graph based on the third node and the third edge; wherein the attribute information of the third node includes: basic system information, system equipment list, system historical operation data, system historical fault data and system historical operation and maintenance data, and the third edge includes inter-system connection information, system standard specifications and expert knowledge of the system; The device-level knowledge graph, the region-level knowledge graph and the system-level knowledge graph are hierarchically associated to obtain the multi-level power supply and distribution knowledge graph.

[0008] Optionally, the processing the fault mode based on the faulty device identifier and the association rule system to obtain a target fault propagation path includes: According to the faulty device identifier, a fault mode analysis algorithm is used to analyze the fault mode to obtain the fault type of the faulty device, and a fault impact analysis algorithm is used to determine the fault impact range according to the fault type and the multi-level power supply and distribution knowledge graph; Selecting at least one of a local association rule, a cross-region association rule and a global association rule as a target rule according to the fault impact range; Use the rule matching algorithm to find the target association result corresponding to the faulty device from the target rule; Based on the target association result, a graph algorithm is used to determine a target fault propagation path.

[0009] Optionally, the determining the target fault propagation path by using a graph algorithm based on the target association result includes: Constructing an initial multi-level graph structure according to the multi-level power supply and distribution knowledge graph; adding the association information in the target association result to the initial multi-level graph structure to obtain an intermediate multi-level graph structure; Setting corresponding priority weights for each node and edge in the intermediate multi-level graph structure to obtain a target multi-level graph structure; Based on the target multi-level graph structure, a graph algorithm is used to search for paths and obtain preliminary fault propagation paths; The preliminary fault propagation path is optimized by using a path optimization algorithm to obtain a target fault propagation path.

[0010] Optionally, predicting the fault severity by using a fault severity assessment model according to the target fault propagation path, determining a corresponding operation and maintenance management report according to the fault severity, and performing corresponding processing according to the operation and maintenance management report include: An initial evaluation model is constructed using a machine learning algorithm, and the initial evaluation model is trained using a cross-validation method to obtain a trained initial evaluation model; and parameters of the trained initial evaluation model are optimized using a grid search algorithm to obtain a fault severity evaluation model; Using a fault severity assessment model to analyze the target fault propagation path to obtain the fault severity; Determine a target operation and maintenance management strategy according to the severity of the fault, and generate an operation and maintenance management report corresponding to the target operation and maintenance management strategy using a natural language generation algorithm; An operation and maintenance instruction is sent to the relevant control device, so that the relevant control device performs corresponding processing according to the operation and maintenance management report based on the operation and maintenance instruction.

[0011] Optionally, determining a target operation and maintenance management strategy according to the fault severity includes: Selecting a corresponding initial operation and maintenance management strategy from an operation and maintenance management rule library according to the severity of the fault; Receive user operation and maintenance feedback information on fault identification, fault severity, target fault propagation path and operation and maintenance management report, as well as environmental information of the railway power supply and distribution system, and dynamically adjust the initial operation and maintenance management strategy based on the operation and maintenance feedback information and the environmental information of the railway power supply and distribution system in combination with the sliding window and online stochastic gradient descent method to determine the target operation and maintenance management strategy.

[0012] In a second aspect, an embodiment of the present invention provides an operation and maintenance management system for railway power supply and distribution, including: A receiving module, used to receive the operation data of the equipment in the railway power supply and distribution system collected by the sensor network through the Internet of Things technology; An input module, used to input the operation data of the device into a pre-trained graph neural network model to identify the faulty device identification and the fault mode; A determination module, used to determine a target fault propagation path according to the faulty device identification, the fault mode and the multi-level power supply and distribution knowledge graph; the target fault propagation path is a propagation path of the faulty device corresponding to the faulty device identification in the railway power supply and distribution system; the multi-level power supply and distribution knowledge graph includes mutually related device-level knowledge graphs, regional-level knowledge graphs and system-level knowledge graphs; The processing module is used to predict the fault severity according to the target fault propagation path using a fault severity assessment model, determine a corresponding operation and maintenance management report according to the fault severity, and perform corresponding processing according to the operation and maintenance management report.

[0013] In a third aspect, an embodiment of the present invention provides a computing device, comprising a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a railway power supply and distribution operation and maintenance management method as described in any one of the first aspects.

[0014] In a fourth aspect, an embodiment of the present invention provides a computer storage medium storing a computer program, which, when executed by a computer, implements a railway power supply and distribution operation and maintenance management method as described in any one of the first aspects.

[0015] Beneficial effects of the present invention: In an embodiment of the present invention, a method for operation and maintenance management of railway power supply and distribution is provided, including: receiving operation data of equipment in the railway power supply and distribution system collected by a sensor network through the Internet of Things technology; inputting the operation data of the equipment into a pre-trained graph neural network model to identify the faulty equipment identification and fault mode; determining a target fault propagation path according to the faulty equipment identification, the fault mode and the multi-level power supply and distribution knowledge graph; the target fault propagation path is the propagation path of the faulty equipment corresponding to the faulty equipment identification in the railway power supply and distribution system; the multi-level power supply and distribution knowledge graph includes mutually related equipment-level knowledge graphs, regional-level knowledge graphs and system-level knowledge graphs; according to the target fault propagation path, a fault severity assessment model is used to predict the fault severity, a corresponding operation and maintenance management report is determined according to the fault severity, and corresponding processing is performed according to the operation and maintenance management report.

[0016] (1) Through the graph neural network model, this embodiment can efficiently and accurately identify the faulty device identification and fault mode, reducing missed alarms and false alarms.

[0017] (2) Combined with the multi-level power supply and distribution knowledge graph, it can accurately locate the location of faulty equipment and quickly identify the source of the fault.

[0018] (3) The multi-level power supply and distribution knowledge graph can comprehensively and accurately describe the relationships between equipment and the fault propagation paths.

[0019] (4) The fault severity assessment model can be used to predict the severity of faults based on historical fault data and real-time operation data. Based on the fault severity assessment results, operation and maintenance personnel can prioritize serious faults and improve the efficiency of fault handling. Timely detection and handling of faults can reduce train delays, suspensions, and even safety accidents caused by equipment failures, thereby improving the safety of railway transportation.

[0020] (5) Based on the analysis results of the multi-level power supply and distribution knowledge graph and the fault severity assessment model, it can provide scientific decision support for operation and maintenance managers and optimize operation and maintenance strategies. Furthermore, through the association rule system, it can dynamically analyze the propagation path of faults between different levels and predict the equipment and areas that may be affected by the faults.

[0021] These and other aspects of the present invention will become more apparent from the following description of the embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0023] Figure 1 A flow chart of a railway power supply and distribution operation and maintenance management method provided by an embodiment of the present invention; Figure 2 A schematic diagram of the structure of an operation and maintenance management system for railway power supply and distribution provided by an embodiment of the present invention; Figure 3 A schematic diagram of the structure of a computing device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0024] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0025] In some of the processes described in the specification and claims of the present invention and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 11, 12, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to different types.

[0026] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0027] Figure 1 A flowchart of a railway power supply and distribution operation and maintenance management method provided by an embodiment of the present invention, such as Figure 1 As shown, the method includes: Step S11, receiving the operating data of the equipment in the railway power supply and distribution system collected by the sensor network through the Internet of Things technology. Among them, the Internet of Things technology collects the operating data of the equipment in real time, such as current, voltage, temperature, humidity, etc., through sensors installed on the equipment, and transmits these data to the central management system. The sensor network is a network composed of multiple sensors, which can sense and transmit operating data. Exemplarily, the sensor network is composed of various sensors installed on equipment such as transformers, circuit breakers, cables, etc. These sensors are responsible for real-time monitoring of the operating status of the equipment and transmitting the data to the central management system.

[0028] Step S12: Input the operation data of the equipment into the pre-trained graph neural network model to identify the faulty equipment identification and failure mode. The graph neural network model can efficiently and accurately identify the faulty equipment identification and failure mode by modeling the connection relationship between the equipment. The faulty equipment identification refers to the unique identifier of the equipment that may have a fault. The faulty equipment identification can be represented by the equipment number, location information, etc., and is used to mark the equipment that may have a fault. The failure mode refers to the type or form of failure that may occur in the equipment. Failure modes may include overheating, short circuit, insulation damage, etc., which can be identified by the graph neural network model.

[0029] Step S13, determine the target fault propagation path according to the faulty equipment identification, fault mode and multi-level power supply and distribution knowledge graph; the target fault propagation path is the propagation path of the faulty equipment corresponding to the faulty equipment identification in the railway power supply and distribution system; the multi-level power supply and distribution knowledge graph includes mutually related equipment-level knowledge graphs, regional-level knowledge graphs and system-level knowledge graphs.

[0030] Among them, the equipment-level knowledge graph includes basic equipment information, equipment performance parameters, historical equipment operation data, historical equipment failure data and historical equipment operation and maintenance data, equipment connection information, equipment standards and specifications, and expert knowledge about equipment. The regional-level knowledge graph includes basic regional information, regional equipment list, regional historical operation data, regional historical failure data and regional historical operation and maintenance data, regional connection information, regional standards and specifications, and expert knowledge about regions. The system-level knowledge graph includes basic system information, system equipment list, system historical operation data, system historical failure data, and system historical operation and maintenance data. The third side includes system connection information, system standards and specifications, and expert knowledge about systems. The target fault propagation path is determined by a multi-level power supply and distribution knowledge graph and an association rule system, which can accurately predict the equipment and areas that may be affected by the fault.

[0031] Step S14: According to the target fault propagation path, a fault severity assessment model is used to predict the fault severity, a corresponding operation and maintenance management report is determined according to the fault severity, and corresponding processing is performed according to the operation and maintenance management report.

[0032] Among them, the fault severity assessment model is built through machine learning algorithms, which can predict the severity of faults based on historical fault data and real-time operation data. The operation and maintenance management report includes faulty equipment identification, fault mode, fault propagation path, fault severity, and corresponding handling suggestions.

[0033] Through the above steps, this embodiment can efficiently and accurately identify the faulty equipment identification and fault mode based on the graph neural network model, reducing missed reports and false alarms. Combined with the multi-level power supply and distribution knowledge graph, the location of the faulty equipment can be accurately located and the source of the fault can be quickly locked. The multi-level power supply and distribution knowledge graph can comprehensively and accurately describe the relationship between equipment and the fault propagation path. Using the fault severity assessment model, the severity of the fault can be predicted based on historical fault data and real-time operation data. According to the fault severity assessment results, operation and maintenance personnel can give priority to serious faults and improve the efficiency of fault handling. Timely discovery and handling of faults can reduce train delays, suspensions and even safety accidents caused by equipment failures, and improve the safety of railway transportation. Based on the analysis results of the multi-level power supply and distribution knowledge graph and the fault severity assessment model, scientific decision support can be provided for operation and maintenance managers to optimize operation and maintenance strategies.

[0034] In some possible embodiments, step S13, determining a target fault propagation path according to the faulty device identification, the fault mode and the multi-level power supply and distribution knowledge graph; the target fault propagation path is a propagation path of the faulty device corresponding to the faulty device identification in the railway power supply and distribution system; the multi-level power supply and distribution knowledge graph includes mutually related device-level knowledge graphs, regional-level knowledge graphs and system-level knowledge graphs, including: Step 131: Construct a multi-level power supply and distribution knowledge graph including an interrelated device-level knowledge graph, a region-level knowledge graph, and a system-level knowledge graph.

[0035] Step 132: Establish an association rule system based on the multi-level power supply and distribution knowledge graph using an association rule mining algorithm; the association rule system includes: local association rules, cross-regional association rules, and global association rules. The association rule mining algorithm analyzes the data in the multi-level power supply and distribution knowledge graph to discover the associations between devices, regions, and systems. These association rules can help predict the propagation path of faults. For example, through the association rule mining algorithm, it can be found that the failure of a transformer may cause the overload of adjacent circuit breakers, thereby further affecting the stability of the entire power supply area.

[0036] Step 133, local association rules are verified using the device-level knowledge graph, cross-regional association rules are verified using the region-level knowledge graph, and global association rules are verified using the system-level knowledge graph. Local association rules describe the mutual influence between devices in the same area. For example, the failure of a transformer may cause overheating of multiple devices in the same area. Cross-regional association rules describe the mutual influence of equipment between different areas. For example, a failure in a certain area may cause equipment in an adjacent area to overload. Global association rules describe the mutual influence between different devices and areas in the system. For example, a failure in a system may cause unstable power supply to the entire railway network. The verification process is used to confirm the correctness and effectiveness of association rules at different levels.

[0037] Step 134: When all verification results are passed, the fault mode is processed based on the faulty device identification and the association rule system to obtain the target fault propagation path.

[0038] In this embodiment, the multi-level power supply and distribution knowledge graph can fully and accurately describe the relationship between devices and the fault propagation path. The association rule system established by the association rule mining algorithm in this embodiment can dynamically analyze the fault propagation path between different levels.

[0039] In the above embodiment, as a possible implementation method, step 131, constructing a multi-level power supply and distribution knowledge graph including an interrelated device-level knowledge graph, a regional-level knowledge graph, and a system-level knowledge graph, includes: Step a1, define the first node and the first edge, and build a device hierarchical knowledge graph based on the first node and the first edge; wherein the attribute information of the first node includes: basic information of the equipment, equipment performance parameters, historical operation data of the equipment, historical fault data of the equipment and historical operation and maintenance data of the equipment, and the first edge includes connection information between devices, equipment standards and specifications and expert knowledge about the equipment.

[0040] The first node represents a specific device, such as a transformer, circuit breaker, cable, etc. The first edge can represent the connection information between devices, equipment standards and specifications, and expert knowledge of the equipment. For example, the connection relationship between a transformer and a cable.

[0041] Step a2, define the second node and the second edge, and construct a regional hierarchical knowledge graph based on the second node and the second edge; wherein the attribute information of the second node includes: regional basic information, regional equipment list, regional historical operation data, regional historical fault data and regional historical operation and maintenance data, and the second edge includes inter-regional connection information, regional standards and specifications, and expert knowledge of the region.

[0042] The second node represents a specific area, such as a substation, a power supply section, etc. Each second node contains basic information of the area, equipment list, historical operation data, historical fault data, and historical operation and maintenance data. The second edge can represent the connection information between areas, regional standards and specifications, and expert knowledge of the area. For example, the connection relationship between a substation and another substation.

[0043] Step a3, define the third node and the third edge, and build a system-level knowledge graph based on the third node and the third edge; wherein the attribute information of the third node includes: basic system information, system equipment list, system historical operation data, system historical fault data and system historical operation and maintenance data, and the third edge includes inter-system connection information, system standard specifications and expert knowledge of the system.

[0044] The third node represents a part of the whole system, such as a power supply system, a railway line, etc. Each third node contains basic information of the system, equipment list, historical operation data, historical fault data, and historical operation and maintenance data. The third edge can represent the connection information between systems, system standards and specifications, and expert knowledge of the system. For example, the connection relationship between a power supply system and another power supply system.

[0045] Step a4: Hierarchically associate the device-level knowledge graph, the regional-level knowledge graph, and the system-level knowledge graph to obtain a multi-level power supply and distribution knowledge graph. The device-level knowledge graph records the specific information of each device in detail, which can help to deeply analyze the status and failure mode of a single device. The regional-level knowledge graph focuses on the overall performance of the region, which can help analyze the mutual influence and fault propagation path between devices in the region. The system-level knowledge graph provides an overall view of the system, which can help to macro-analyze the operating status of the system and the scope of fault impact.

[0046] Through the above steps a1 to a4, this embodiment can construct a multi-level power supply and distribution knowledge graph to comprehensively and accurately describe the relationships between devices and the fault propagation paths. This can not only help operation and maintenance personnel accurately locate the location of faulty equipment and quickly lock the source of the fault, but also dynamically analyze the propagation path of the fault between different levels and predict the scope of the fault impact. In addition, the multi-level power supply and distribution knowledge graph provides rich data support for the fault severity assessment model, helping operation and maintenance personnel to scientifically formulate operation and maintenance management strategies and improve the efficiency of fault handling and the reliability of the system. These effects work together to ensure the efficient, safe and reliable operation of the railway power supply and distribution system.

[0047] In the above embodiment, in step 134, the fault mode is processed based on the fault device identification and the association rule system to obtain the target fault propagation path, including: Step b1: According to the faulty equipment identification, a fault mode analysis algorithm is used to analyze the fault mode to obtain the fault type of the faulty equipment. According to the fault type and the multi-level power supply and distribution knowledge graph, a fault impact analysis algorithm is used to determine the fault impact range.

[0048] Among them, the failure mode analysis algorithm can adopt the following formula: ; In the formula, is the fault type of the faulty device, , represents the operation data of the equipment, and n is the total number of operation data; is the set of all possible fault types; Is the given running data The following fault types The probability of can be calculated by Bayes' theorem: ; In the formula, Is the fault type The following operation data is observed The likelihood probability of ; Is the fault type The prior probability of It is the operating data The marginal probability can be calculated by the total probability formula: ; The fault mode analysis algorithm analyzes the operating data of the equipment to identify the fault type of the faulty equipment, such as overheating, short circuit, insulation damage, etc. The fault impact analysis algorithm analyzes the impact of the faulty equipment on the surrounding equipment and systems through the multi-level power supply and distribution knowledge graph to determine the fault impact range. The fault impact range can be the impact range at the equipment level, the impact range at the regional level, or the impact range at the system level.

[0049] Step b2: selecting at least one of a local association rule, a cross-region association rule and a global association rule as a target rule according to the fault impact range.

[0050] Step b3: Use a rule matching algorithm to search for a target association result corresponding to the faulty device from the target rule.

[0051] Step b4: Based on the target association result, a graph algorithm is used to determine the target fault propagation path.

[0052] Among them, the graph algorithm is an algorithm for processing graph structure data, which is often used for path search, shortest path and other problems. In this embodiment, the graph algorithm is used to search and optimize the fault propagation path in the multi-level power supply and distribution knowledge graph.

[0053] Through the above steps b1~b4, this embodiment can efficiently and accurately determine the target fault propagation path based on the faulty equipment identification and the association rule system. Specifically, the fault mode analysis algorithm can accurately identify the fault type of the faulty equipment, the fault impact analysis algorithm can comprehensively evaluate the fault impact range, the rule matching algorithm can scientifically select association rules, and the graph algorithm can quickly determine the fault propagation path. These steps work together to ensure that operation and maintenance personnel can quickly and accurately locate the fault impact range, take timely and effective measures, avoid fault spread, reduce unnecessary losses, and improve the safety and reliability of the railway power supply and distribution system.

[0054] As an optional implementation mode, step b4, based on the target association result, using a graph algorithm to determine the target fault propagation path, includes: Step b41, construct an initial multi-level graph structure based on the multi-level power supply and distribution knowledge graph; add the association information in the target association result to the initial multi-level graph structure to obtain an intermediate multi-level graph structure.

[0055] The initial multi-level graph structure represents the connection relationship between devices, regions, and systems, providing a basis for subsequent fault propagation path analysis. The intermediate multi-level graph structure contains the specific association relationship between devices, such as other devices and regions that may be affected by a certain device failure.

[0056] Step b42: Set corresponding priority weights for each node and edge in the intermediate multi-level graph structure to obtain the target multi-level graph structure.

[0057] Among them, the priority weight can represent factors such as the importance of the equipment and the scope of fault impact, helping the graph algorithm to prioritize important nodes and edges during the path search process.

[0058] Step b43: Based on the target multi-level graph structure, a graph algorithm is used to search for a path to obtain a preliminary fault propagation path, wherein the graph algorithm may be a Dijkstra algorithm or an A* algorithm, which is not specifically limited in this embodiment.

[0059] Step b44: Use a path optimization algorithm to optimize the preliminary fault propagation path to obtain a target fault propagation path.

[0060] Among them, the path optimization algorithm can be a depth-first search algorithm, a breadth-first search algorithm, a backtracking method, a dynamic programming, etc. The path optimization algorithm is used to optimize the preliminary fault propagation path, ensure that all relevant fault propagation paths are found, and reduce unnecessary path search and processing time.

[0061] Through the above steps, this embodiment can efficiently and accurately determine the target fault propagation path and reduce missed reports and false alarms. Combined with the multi-level power supply and distribution knowledge graph and graph algorithm, it can comprehensively and accurately describe the relationship between devices and the fault propagation path. The setting of priority weights ensures the efficiency and accuracy of path search, and the path optimization algorithm further optimizes the fault propagation path to ensure that relevant paths are found. These effects work together to improve the efficiency of fault handling, reduce train delays, shutdowns and even safety accidents caused by equipment failures, and improve the safety and reliability of railway transportation. At the same time, scientific path analysis and optimization results provide strong decision-making support for operation and maintenance managers, optimize operation and maintenance strategies, and improve the efficiency of operation and maintenance management.

[0062] In the above embodiment, step S14, according to the target fault propagation path, using the fault severity assessment model to predict the fault severity, determining the corresponding operation and maintenance management report according to the fault severity, and performing corresponding processing according to the operation and maintenance management report, includes: Step 141: Use a machine learning algorithm to build an initial evaluation model, use a cross-validation method to train the initial evaluation model, and obtain a trained initial evaluation model; use a grid search algorithm to optimize the parameters of the trained initial evaluation model to obtain a fault severity evaluation model.

[0063] Among them, cross-validation is a method for evaluating the performance of machine learning models. It can divide the data set into several subsets, take one of the subsets as the test set and the other subsets as the training set in turn, and evaluate the performance of the model through multiple training and testing. The cross-validation method is used to evaluate the accuracy of the fault severity assessment model to ensure that the model can stably predict the fault severity on different data subsets. Grid search is a hyperparameter optimization method that finds the parameter settings that make the model perform best by exhaustively searching for predefined hyperparameter value combinations.

[0064] Step 142: Use a fault severity assessment model to analyze the target fault propagation path to obtain the fault severity.

[0065] Step 143: Determine a target operation and maintenance management strategy according to the severity of the fault, and use a natural language generation algorithm to generate an operation and maintenance management report corresponding to the target operation and maintenance management strategy. Natural language generation is an artificial intelligence technology that can automatically generate natural language text from data.

[0066] Step 144: Send an operation and maintenance instruction to the relevant control device, so that the relevant control device performs corresponding processing according to the operation and maintenance management report based on the operation and maintenance instruction.

[0067] Through step 141 to step 144, this embodiment can use machine learning technology and natural language generation technology to build a highly automated fault severity assessment and operation and maintenance management process. Specifically, this embodiment optimizes the fault severity assessment model through cross-validation and grid search algorithms to ensure that the model has high accuracy and stability and can effectively predict the severity of the fault. The automatic generation of operation and maintenance management reports using natural language generation algorithms not only improves the efficiency of report generation, but also ensures the professionalism and accuracy of the report content. Finally, the automatic sending of operation and maintenance instructions to relevant control equipment achieves a rapid response to fault handling and reduces the time and cost of manual intervention. This process helps to prevent and handle faults in advance and in a timely manner, reduce the risks and losses caused by faults, ensure the stable operation and safety of the railway power supply and distribution system, and at the same time improve the overall efficiency and service quality of operation and maintenance management.

[0068] In the above embodiment, as an optional implementation mode, in step 143, determining the target operation and maintenance management strategy according to the severity of the fault includes: Step c1: Select the corresponding initial operation and maintenance management strategy from the operation and maintenance management rule base according to the severity of the fault. The operation and maintenance management rule base is a set of predefined operation and maintenance management strategies and rules used to guide operation and maintenance personnel to take appropriate actions in different situations. In the operation and maintenance management of railway power supply and distribution, the operation and maintenance management rule base contains handling suggestions for different fault types and severity, such as replacing faulty equipment, isolating faulty areas, and performing temporary repairs.

[0069] Step c2: receiving operation and maintenance feedback information from users regarding fault identification, fault severity, target fault propagation path and operation and maintenance management report, as well as environmental information of the railway power supply and distribution system, and dynamically adjusting the initial operation and maintenance management strategy based on the operation and maintenance feedback information and the environmental information of the railway power supply and distribution system, in combination with the sliding window and online stochastic gradient descent method, to determine the target operation and maintenance management strategy.

[0070] Among them, operation and maintenance feedback information refers to the feedback provided by operation and maintenance personnel after executing the operation and maintenance management strategy, including the results of fault handling, problems encountered and suggestions, etc. Operation and maintenance feedback information can help optimize the operation and maintenance management strategy and improve the efficiency and accuracy of fault handling. The environmental information of the railway power supply and distribution system refers to various external conditions that affect the operation of the system, such as weather conditions, geographical location, operating load, etc. Environmental information can help operation and maintenance personnel better understand the causes and possible impacts of the fault, so as to take more appropriate measures. Sliding window is a data processing technology that dynamically updates and analyzes the changing trends of data by processing data within a fixed-size time window. Sliding window technology can be used to monitor the operating status of equipment in real time, detect abnormal changes in time, and improve the accuracy of fault prediction.

[0071] The online stochastic gradient descent method can be used to dynamically adjust the operation and maintenance management strategy, continuously optimize the strategy based on real-time data and feedback information, and improve the efficiency and accuracy of fault handling.

[0072] Through the above steps, this embodiment can dynamically adjust the operation and maintenance management strategy according to the severity of the fault, and improve the efficiency and accuracy of fault handling. Specifically, the operation and maintenance management rule base provides a scientific initial operation and maintenance management strategy, operation and maintenance feedback information and environmental information help optimize the strategy, the sliding window technology monitors the equipment status in real time, and the online stochastic gradient descent rule dynamically adjusts the strategy according to real-time data. These measures work together to ensure the efficient, safe and reliable operation of the railway power supply and distribution system, reduce train delays, outages and even safety accidents caused by equipment failures, and improve the safety and reliability of railway transportation.

[0073] Figure 2 A schematic diagram of the structure of a railway power supply and distribution operation and maintenance management system provided by an embodiment of the present invention, such as Figure 2 As shown, the system includes: The receiving module 21 is used to receive the operation data of the equipment in the railway power supply and distribution system collected by the sensor network through the Internet of Things technology.

[0074] The input module 22 is used to input the operating data of the equipment into a pre-trained graph neural network model to identify the faulty equipment identification and the fault mode.

[0075] Determination module 23, used to determine the target fault propagation path according to the faulty equipment identification, the fault mode and the multi-level power supply and distribution knowledge graph; the target fault propagation path is the propagation path of the faulty equipment corresponding to the faulty equipment identification in the railway power supply and distribution system; the multi-level power supply and distribution knowledge graph includes mutually related equipment-level knowledge graphs, regional-level knowledge graphs and system-level knowledge graphs.

[0076] The processing module 24 is used to predict the fault severity according to the target fault propagation path using a fault severity assessment model, determine a corresponding operation and maintenance management report according to the fault severity, and perform corresponding processing according to the operation and maintenance management report.

[0077] Figure 2 The railway power supply and distribution operation and maintenance management system can execute Figure 1 The implementation principle and technical effect of the operation and maintenance management method for railway power supply and distribution described in the illustrated embodiment will not be described in detail. The specific manner in which each module and unit performs operations in the operation and maintenance management system for railway power supply and distribution in the above embodiment has been described in detail in the embodiment of the method, and will not be described in detail here.

[0078] In one possible design, Figure 2The operation and maintenance management system of the railway power supply and distribution in the embodiment shown can be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32 .

[0079] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0080] The processing component 32 is used to: receive the operating data of the equipment in the railway power supply and distribution system collected by the sensor network through the Internet of Things technology; input the operating data of the equipment into a pre-trained graph neural network model to identify the faulty equipment identification and the fault mode; determine the target fault propagation path according to the faulty equipment identification, the fault mode and the multi-level power supply and distribution knowledge graph; the target fault propagation path is the propagation path of the faulty equipment corresponding to the faulty equipment identification in the railway power supply and distribution system; the multi-level power supply and distribution knowledge graph includes mutually related equipment-level knowledge graphs, regional-level knowledge graphs and system-level knowledge graphs; according to the target fault propagation path, a fault severity assessment model is used to predict the fault severity, a corresponding operation and maintenance management report is determined according to the fault severity, and corresponding processing is performed according to the operation and maintenance management report.

[0081] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0082] The storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as random access memory (RAM), static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0083] Of course, the computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0084] The input / output interface provides an interface between the processing component and the peripheral interface module, which may be an output device, an input device, etc.

[0085] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0086] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0087] The embodiment of the present invention further provides a computer storage medium storing a computer program, which can achieve the above-mentioned Figure 1 The operation and maintenance management method of railway power supply and distribution of the embodiment shown.

[0088] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0089] The system embodiment described above is merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art may understand and implement it without creative work.

[0090] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0091] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for operation and maintenance management of railway power supply and distribution, characterized in that: include: Receive the operating data of equipment in the railway power supply and distribution system collected by the sensor network through the Internet of Things technology; Inputting the operating data of the device into a pre-trained graph neural network model to identify the faulty device identification and the fault mode; Determine a target fault propagation path according to the faulty device identification, the fault mode and the multi-level power supply and distribution knowledge graph; the target fault propagation path is a propagation path of the faulty device corresponding to the faulty device identification in the railway power supply and distribution system; the multi-level power supply and distribution knowledge graph includes mutually related device-level knowledge graphs, regional-level knowledge graphs and system-level knowledge graphs; According to the target fault propagation path, a fault severity assessment model is used to predict the fault severity, a corresponding operation and maintenance management report is determined according to the fault severity, and corresponding processing is performed according to the operation and maintenance management report.

2. The method according to claim 1, characterized in that The target fault propagation path is determined according to the faulty device identification, the fault mode and the multi-level power supply and distribution knowledge graph; the target fault propagation path is the propagation path of the faulty device corresponding to the faulty device identification in the railway power supply and distribution system; The multi-level power supply and distribution knowledge graph includes an interrelated equipment level knowledge graph, a region level knowledge graph and a system level knowledge graph, including: Construct a multi-level power supply and distribution knowledge graph including interrelated equipment-level knowledge graph, region-level knowledge graph and system-level knowledge graph; An association rule mining algorithm is used to establish an association rule system based on the multi-level power supply and distribution knowledge graph; the association rule system includes: local association rules, cross-regional association rules and global association rules; The local association rules are verified by using the device-level knowledge graph, the cross-regional association rules are verified by using the region-level knowledge graph, and the global association rules are verified by using the system-level knowledge graph; When all verification results are passed, the fault mode is processed based on the faulty device identification and the association rule system to obtain a target fault propagation path.

3. The method according to claim 2, characterized in that The construction includes a multi-level power supply and distribution knowledge graph including an interrelated device-level knowledge graph, a region-level knowledge graph, and a system-level knowledge graph, including: A first node and a first edge are defined, and a device-level knowledge graph is constructed based on the first node and the first edge; wherein the attribute information of the first node includes: basic information of the device, performance parameters of the device, historical operation data of the device, historical fault data of the device, and historical operation and maintenance data of the device; and the first edge includes connection information between devices, device standards and specifications, and expert knowledge about the device; Define a second node and a second edge, and construct a regional hierarchical knowledge graph based on the second node and the second edge; wherein the attribute information of the second node includes: regional basic information, regional equipment list, regional historical operation data, regional historical fault data, and regional historical operation and maintenance data; the second edge includes inter-regional connection information, regional standards and specifications, and expert knowledge of the region; Define a third node and a third edge, and construct a system-level knowledge graph based on the third node and the third edge; wherein the attribute information of the third node includes: basic system information, system equipment list, system historical operation data, system historical fault data and system historical operation and maintenance data, and the third edge includes inter-system connection information, system standard specifications and expert knowledge of the system; The device-level knowledge graph, the region-level knowledge graph and the system-level knowledge graph are hierarchically associated to obtain the multi-level power supply and distribution knowledge graph.

4. The method according to claim 2, characterized in that: The processing of the fault mode based on the fault device identifier and the association rule system to obtain a target fault propagation path includes: According to the faulty device identifier, a fault mode analysis algorithm is used to analyze the fault mode to obtain the fault type of the faulty device, and a fault impact analysis algorithm is used to determine the fault impact range according to the fault type and the multi-level power supply and distribution knowledge graph; Selecting at least one of a local association rule, a cross-region association rule and a global association rule as a target rule according to the fault impact range; Use the rule matching algorithm to find the target association result corresponding to the faulty device from the target rule; Based on the target association result, a graph algorithm is used to determine a target fault propagation path.

5. The method according to claim 4, characterized in that The step of using a graph algorithm to determine a target fault propagation path based on the target association result includes: Constructing an initial multi-level graph structure according to the multi-level power supply and distribution knowledge graph; adding the association information in the target association result to the initial multi-level graph structure to obtain an intermediate multi-level graph structure; Setting corresponding priority weights for each node and edge in the intermediate multi-level graph structure to obtain a target multi-level graph structure; Based on the target multi-level graph structure, a graph algorithm is used to search for paths and obtain preliminary fault propagation paths; The preliminary fault propagation path is optimized using a path optimization algorithm to obtain a target fault propagation path.

6. The method according to claim 1, characterized in that The method of predicting the fault severity by using a fault severity assessment model according to the target fault propagation path, determining a corresponding operation and maintenance management report according to the fault severity, and performing corresponding processing according to the operation and maintenance management report includes: An initial evaluation model is constructed using a machine learning algorithm, and the initial evaluation model is trained using a cross-validation method to obtain a trained initial evaluation model; and parameters of the trained initial evaluation model are optimized using a grid search algorithm to obtain a fault severity evaluation model; Using a fault severity assessment model to analyze the target fault propagation path to obtain the fault severity; Determine a target operation and maintenance management strategy according to the severity of the fault, and generate an operation and maintenance management report corresponding to the target operation and maintenance management strategy using a natural language generation algorithm; An operation and maintenance instruction is sent to the relevant control device, so that the relevant control device performs corresponding processing according to the operation and maintenance management report based on the operation and maintenance instruction.

7. The method according to claim 6, characterized in that Determining a target operation and maintenance management strategy according to the severity of the fault includes: Selecting a corresponding initial operation and maintenance management strategy from an operation and maintenance management rule library according to the severity of the fault; Receive user operation and maintenance feedback information on fault identification, fault severity, target fault propagation path and operation and maintenance management report, as well as environmental information of the railway power supply and distribution system, and dynamically adjust the initial operation and maintenance management strategy based on the operation and maintenance feedback information and the environmental information of the railway power supply and distribution system in combination with the sliding window and online stochastic gradient descent method to determine the target operation and maintenance management strategy.

8. A railway power supply and distribution operation and maintenance management system, characterized in that: include: A receiving module, used to receive the operation data of the equipment in the railway power supply and distribution system collected by the sensor network through the Internet of Things technology; An input module, used to input the operation data of the device into a pre-trained graph neural network model to identify the faulty device identification and the fault mode; A determination module, used to determine a target fault propagation path according to the faulty device identification, the fault mode and the multi-level power supply and distribution knowledge graph; the target fault propagation path is a propagation path of the faulty device corresponding to the faulty device identification in the railway power supply and distribution system; the multi-level power supply and distribution knowledge graph includes mutually related device-level knowledge graphs, regional-level knowledge graphs and system-level knowledge graphs; The processing module is used to predict the fault severity according to the target fault propagation path using a fault severity assessment model, determine a corresponding operation and maintenance management report according to the fault severity, and perform corresponding processing according to the operation and maintenance management report.

9. A computing device, characterized in that It comprises a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a railway power supply and distribution operation and maintenance management method as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a computer, an operation and maintenance management method for railway power supply and distribution as described in any one of claims 1 to 7 is implemented.

Images