Model-based fault solution generation method and apparatus

Abstract

The present disclosure relates to the technical field of medium wave rebroadcast equipment fault processing, and particularly relates to a model-based fault solution generation method and device, the method comprising: in response to monitoring that a medium wave rebroadcast equipment has a fault, collecting fault-related data, determining a fault type based on the fault-related data; calling a preset fault strategy model to match the fault type, obtaining a fault processing strategy; the fault strategy model contains a maintenance log, an equipment manual, and relevant materials for processing medium wave rebroadcast fault problems, and the technical materials in the fault strategy model are stored in categories according to a reception system, a program transmission system, a transmission system, a power distribution system, and an automation system; based on the fault processing strategy obtained by matching the fault type based on the fault strategy model, a processing object is determined in combination with a preset work cooperation relationship; early warning information containing the fault type and the fault processing strategy is generated, and the early warning information is sent to the processing object.

Description

Technical Field

[0001] This disclosure relates to the field of fault handling technology for medium-wave broadcasting equipment, specifically to a model-based fault solution generation method and apparatus. Background Technology

[0002] Medium wave relay relies on the coordinated operation of multiple core systems, including the receiving system, transmission system, power distribution system, and automation system. Medium wave relay equipment often operates under high load for extended periods, making it susceptible to various malfunctions due to factors such as abnormal parameters, component wear and tear, and environmental interference.

[0003] In existing technologies, fault handling for medium-wave broadcasting equipment faces numerous problems: First, technical data is scattered across different media, and matching technical solutions relies on keyword searches, making it difficult to handle complex or novel faults. Searching for maintenance logs and equipment manuals is time-consuming and labor-intensive, and the lack of unified classification and management leads to low efficiency in matching fault handling solutions. Second, fault type identification relies on manual judgment, making it difficult to pinpoint the root cause of cross-system cascading faults and prone to misjudgment due to differences in experience, affecting the accuracy of handling. Third, fault warning information transmission channels are fragmented, and the location of the target for handling is inaccurate, often resulting in problems such as missed information transmission and delayed reception. Fourth, therefore... The lack of a closed-loop feedback mechanism for fault handling makes it impossible to optimize subsequent solutions based on historical processing data, resulting in the need to re-explore processing paths when similar faults recur; fourth, it often only identifies and matches faults in a single device or a single system. However, medium wave transmission is a systematic project. A fault in a subsystem (such as unstable voltage in the power distribution system) may quickly trigger a chain reaction, causing signal distortion in the transmission system and ultimately manifesting as abnormal output of the transmission system. Existing technologies lack the ability to model and predict such cross-system, multi-level fault propagation paths, which may result in processing solutions that are "treating the symptoms but not the root cause" or ignoring the fundamental cause.

[0004] The aforementioned problems directly lead to a prolonged troubleshooting cycle for medium-wave broadcasting equipment, seriously affecting the safe broadcasting of medium-wave broadcasts. Currently, there is no effective solution available on the market. Summary of the Invention

[0005] To address the problems existing in the prior art, this disclosure proposes a model-based fault solution generation method and apparatus to solve at least one of the aforementioned technical problems. The technical solution adopted in this disclosure is as follows: In a first aspect, this disclosure provides a model-based fault solution generation method, the method comprising: S100: In response to detecting a fault in the medium-wave relay equipment, collect fault-related data and determine the fault type based on the fault-related data; S200: The preset fault strategy model is invoked to match the fault type and obtain the fault handling strategy; the fault strategy model includes maintenance logs, equipment manuals and relevant information on handling medium wave transmission faults, and the technical information in the fault strategy model is classified and stored according to receiving system, transmission system, transmitting system, power distribution system and automation system, etc. S300. Based on the fault strategy model, the fault handling strategy obtained by matching the fault type is combined with the preset work collaboration relationship to determine the handling object. S400: Generate early warning information containing the fault type and fault handling strategy, and send the early warning information to the processing object.

[0006] Preferably, in S100, the fault-related data includes the equipment operating parameters of the medium-wave relay equipment when the fault occurs, the description of the fault phenomenon, the time of the fault occurrence, the system identifiers involved in the fault, and the assessment data of the scope of the fault impact.

[0007] Preferably, in step S100, determining the fault type based on the fault-related data specifically includes: inputting the fault-related data into a preset fault type identification model, wherein the fault type identification model is trained on historical fault data using a machine learning algorithm, and outputting the fault type that has the highest matching degree with the fault-related data.

[0008] Preferably, in step S300, the fault handling strategy obtained by matching the fault type based on the fault strategy model specifically includes: Based on the fault type, keywords are extracted, and relevant information is filtered from the classified and stored technical documents using keyword retrieval technology. Semantic analysis is performed on the filtered relevant data to generate a standardized fault handling strategy. The fault handling strategy includes fault investigation steps, fault solutions, handling precautions, and expected handling time.

[0009] Preferably, the method may further include: S500: Receive fault handling result data fed back by the processing object, and update the fault strategy model with the result data to optimize the fault strategy model; the result data includes whether the fault is resolved, cost, risk avoidance degree, actual processing time, problems encountered during the processing, etc.

[0010] A second aspect of this disclosure provides a model-based fault solution generation apparatus, the apparatus comprising: The fault type determination module is configured to collect fault-related data and determine the fault type based on the fault-related data in response to detecting a fault in the medium wave relay equipment. The technical data retrieval module is configured to call a preset fault strategy model to match the fault type and obtain a fault handling strategy. The fault strategy model includes maintenance logs, equipment manuals, and relevant information on handling medium wave transmission faults. The technical data in the fault strategy model is stored in categories such as receiving system, transmission system, transmitting system, power distribution system, and automation system. The solution matching module is configured to determine the processing object based on the fault handling strategy obtained by matching the fault type according to the fault strategy model and combined with the preset work collaboration relationship. The early warning information sending module is configured to generate early warning information containing the fault type and fault handling strategy, and send the early warning information to the processing object; The strategy model optimization module is configured to receive fault handling result data fed back by the processing object, update the fault strategy model with the result data, and optimize the fault strategy model; the result data includes whether the fault is resolved, cost, risk avoidance degree, actual processing time, problems encountered in the processing, etc.

[0011] Preferably, the fault type determination module may include: The data acquisition unit is configured to collect equipment operating parameters and fault-related feedback data in real time. The type identification unit is configured to have a built-in machine learning model trained on historical fault data, and to determine the fault type through the machine learning model.

[0012] Preferably, the device may further include: The access control module is configured to perform hierarchical control over access permissions to the fault strategy model, allowing only authorized users to access technical data and handling strategies for the corresponding fault type.

[0013] In a third aspect, this disclosure provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the model-based fault solution generation method described above.

[0014] In a fourth aspect, this disclosure provides an electronic device including a processor and a memory, the processor being configured to execute a computer program stored in the memory to implement the model-based fault solution generation method described above.

[0015] The beneficial effects of this disclosure are as follows: By integrating relevant technical data on medium-wave broadcasting and establishing a categorized and stored fault strategy model, combined with the visualization resources of the material center, this disclosure solves the problems of scattered data and low search efficiency in traditional fault handling, making fault handling strategies more intuitive and easy to understand. This disclosure utilizes a fault type identification model to achieve intelligent identification of fault types, avoiding the subjectivity and risk of misjudgment inherent in manual judgment, and improving the accuracy of fault type identification. This disclosure ensures rapid and effective transmission of fault handling instructions by accurately locating the handling object and sending early warning information through multi-channel communication, coupled with status tracking and secondary reminder mechanisms. This disclosure also constructs a closed-loop feedback mechanism for fault handling effects, continuously optimizing the model and algorithm based on historical processing data, and achieving dynamic iterative upgrades to the fault strategy model and fault handling strategies. This avoids the existing technical problem of lacking a closed-loop feedback mechanism for fault handling effects, being unable to optimize subsequent solutions based on historical processing data, and having to re-explore handling paths when similar faults recur.

[0016] This disclosure effectively improves the efficiency, accuracy, and intelligence of medium-wave broadcast fault handling, significantly shortens the fault handling cycle, and provides reliable protection for the normal operation of medium-wave broadcast equipment and safe broadcasting. This disclosure solves the problems in existing medium-wave broadcast fault handling, such as difficulty in data retrieval, low accuracy in type identification, slow solution matching, inaccurate early warning, and lack of feedback optimization mechanisms, thereby improving the efficiency and accuracy of fault handling and ensuring the stable operation of medium-wave broadcasting. Attached Figure Description

[0017] The accompanying drawings, which form part of this application, are used to provide a further understanding of this disclosure. The illustrative embodiments of this disclosure and their descriptions are used to explain this disclosure and do not constitute an undue limitation of this disclosure.

[0018] Figure 1 The flowchart of a model-based fault solution generation method in Embodiment 1 of this disclosure Figure 1 .

[0019] Figure 2 This is an architecture diagram of the adaptive optimization module described in Embodiment 2 of this disclosure. Detailed Implementation

[0020] The present disclosure will now be described in detail with reference to the accompanying drawings and embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in the present application can be combined with each other.

[0021] The following detailed descriptions are exemplary and intended to provide further detailed explanation of this disclosure. Unless otherwise specified, all technical terms used in this disclosure have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. The terminology used in this disclosure is for the purpose of describing particular embodiments only and is not intended to limit the exemplary embodiments according to this disclosure.

[0022] Example 1: like Figure 1 As shown, this disclosure provides a model-based fault solution generation method, the method including steps S100 to S500.

[0023] S100: In response to detecting a fault in the medium-wave relay equipment, collect fault-related data and determine the fault type based on the fault-related data.

[0024] Furthermore, in S100, the fault-related data includes the equipment operating parameters of the medium-wave broadcasting equipment at the time of the fault, the description of the fault phenomenon, the time of the fault occurrence, the system identifiers involved in the fault, and the assessment data of the scope of the fault impact.

[0025] Furthermore, in S100, determining the fault type based on the fault-related data specifically includes: inputting the fault-related data into a preset fault type identification model, wherein the fault type identification model is trained on historical fault data using a machine learning algorithm, and outputting the fault type with the highest matching degree to the fault-related data.

[0026] Furthermore, the collection of fault-related data and the determination of the fault type based on the fault-related data may specifically include: S101. Input the collected fault-related data into the pre-trained fault classification model to identify and output the preliminary fault type and confidence level. S102. If the confidence level is lower than the preset threshold, guide the user to supplement information and use the Large Language Model (LLM) combined with the domain knowledge graph to conduct multi-round question-and-answer reasoning to refine the fault description. S103. Based on the pre-constructed "system control relationship graph", the propagation path of the preliminary fault type and confidence level is simulated, the possible chain effects are analyzed, and the most likely root cause node set is located using a probabilistic reasoning algorithm. S104. Generate the fault type based on the root cause node set.

[0027] S200. The preset fault strategy model is invoked to match the fault type and obtain the fault handling strategy. The fault strategy model includes maintenance logs, equipment manuals and relevant information on handling medium wave transmission faults. The technical information in the fault strategy model is classified and stored according to the receiving system, transmission system, transmission system, power distribution system and automation system.

[0028] Furthermore, the fault strategy model is associated with a preset material center.

[0029] Furthermore, the material center is configured to support uploading, categorizing, searching, and previewing of images, videos, and files in the technical materials.

[0030] Furthermore, when matching the corresponding fault handling strategy, the corresponding material resources in the material center are called to supplement the fault handling strategy.

[0031] Furthermore, the material resources include troubleshooting operation videos, equipment structure diagrams, and parameter configuration files.

[0032] Furthermore, the processing targets are relevant personnel identified based on their working relationships, job responsibilities, and historical fault handling records in medium-wave broadcasting. The warning information is sent through preset communication channels, including work group chats, personal message notifications, and email reminders.

[0033] Furthermore, the step of invoking a preset fault strategy model to match the fault type and obtain a fault handling strategy may include: S201. Using the fault type as input data, perform graph retrieval in the preset structured operation and maintenance knowledge graph in the preset fault strategy model to associate historical cases, handling actions, technical documents, component information and expert experience related to the fault type. S202. Based on domain-fine-tuned LLM and context (fault data, map retrieval results), dynamically generate a draft of a structured preliminary handling strategy.

[0034] S203. Convert the preliminary handling strategy draft into an executable instruction sequence, and input the executable instruction sequence into a preset high-fidelity digital twin model; S204. In the virtual environment of the high-fidelity digital twin model, simulate the execution of disposal instructions, monitor the state changes of the twin in real time, predict the secondary risks (such as overload and oscillation) that may be caused by the operation, and obtain the simulation results. S205. Generate a strategy pre-evaluation report based on the simulation results. The strategy pre-evaluation report includes expected repair effects, security risk warnings, and estimated required resources (personnel, spare parts, time), etc. S206. Based on the strategy pre-evaluation report, optimize the strategy draft or generate alternative solutions to obtain the fault handling strategy.

[0035] S300. Based on the fault strategy model, the fault handling strategy obtained by matching the fault type is combined with the preset work collaboration relationship to determine the handling object.

[0036] Furthermore, the step of determining the processing object based on preset work collaboration relationships specifically includes: Match several processing objects from the preset work collaboration relationships; The root cause of the fault and the complexity of the handling strategy are analyzed from the fault handling strategy. Combined with the skill tags and geographical location of each handling object, the optimal handling object is determined by the optimization algorithm.

[0037] Furthermore, in step S300, the fault handling strategy obtained by matching the fault type based on the fault strategy model specifically includes: Based on the fault type, keywords are extracted, and relevant information is filtered from the classified and stored technical documents using keyword retrieval technology. Semantic analysis is performed on the filtered relevant data to generate a standardized fault handling strategy. The fault handling strategy includes fault investigation steps, fault solutions, handling precautions, and expected handling time.

[0038] S400: Generate early warning information containing the fault type and fault handling strategy, and send the early warning information to the processing object.

[0039] S500: Receive fault handling result data fed back by the processing object, and update the fault strategy model with the result data to optimize the fault strategy model; the result data includes whether the fault is resolved, cost, risk avoidance degree, actual processing time, problems encountered during the processing, etc.

[0040] Furthermore, the warning information also includes the location of the fault, links to trace fault-related data, and access to technical documentation. The access to technical documentation can directly redirect to the corresponding maintenance log or equipment manual page in the fault strategy model.

[0041] Furthermore, updating the fault strategy model with the result data to optimize the fault strategy model may specifically include: S501. Receive the fault handling result data fed back by the processing object; S502. The fault handling result data (status-action-reward) is stored as a sample in the experience pool. The reward value in the experience pool is calculated comprehensively based on the actual handling time, cost, risk aversion, etc. S503. The fault policy model is trained online or offline based on reinforcement learning algorithms (such as DQN, PPO) to update the policy value function, so that when encountering similar states, the policy with higher historical returns can be recommended first.

[0042] Example 2: like Figure 2 As shown in Embodiment 2 of this disclosure, a model-based fault solution generation device is provided, the system comprising: The fault type determination module 100 is configured to collect fault-related data and determine the fault type based on the fault-related data in response to detecting a fault in the medium wave relay equipment. The technical data retrieval module 200 is configured to call a preset fault strategy model to match the fault type and obtain a fault handling strategy. The fault strategy model includes maintenance logs, equipment manuals, and relevant information on handling medium wave relay faults. The technical data in the fault strategy model is classified and stored according to receiving system, relay system, transmitting system, power distribution system, and automation system, etc. The solution matching module 300 is configured to determine the processing object based on the fault handling strategy obtained by matching the fault type according to the fault strategy model and combined with the preset work collaboration relationship. The early warning information sending module 400 is configured to generate early warning information containing the fault type and fault handling strategy, and send the early warning information to the processing object; The strategy model optimization module 500 is configured to receive fault handling result data fed back by the processing object, update the fault strategy model with the result data, and optimize the fault strategy model; the result data includes whether the fault is resolved, cost, risk avoidance degree, actual processing time, problems encountered in the processing, etc.

[0043] Preferably, the fault type determination module 100 includes: The data acquisition unit is configured to collect equipment operating parameters and fault-related feedback data in real time. The type identification unit is configured to have a built-in machine learning model trained on historical fault data, and to determine the fault type through the machine learning model.

[0044] Preferably, the technical data retrieval module 200 is further configured to periodically update the technical data in the fault strategy model, and synchronously add new maintenance logs, revised versions of equipment manuals, and fault handling case data.

[0045] Preferably, the solution matching module 300 includes: The priority sorting unit is configured to prioritize the matched fault handling strategies based on the scope of the fault's impact and the urgency of the fault, and push the higher priority handling strategies to the handling objects first.

[0046] Preferably, the warning information sending module 400 is further configured to track the warning information status based on the warning information, provide real-time feedback on the read status of the warning information and the response status of the processing object, and trigger a secondary reminder if no response is received within a preset time.

[0047] Preferably, the device further includes: The access control module 600 is configured to perform hierarchical control over access permissions to the fault strategy model, allowing only authorized users to access technical data and handling strategies for the corresponding fault type.

[0048] It is worth noting that the system described in Embodiment 2 is only one system implementation of the model-based fault solution generation method, and does not limit the model-based fault solution generation method to depend on the system described in Embodiment 2.

[0049] Example 3: Embodiment 3 of this disclosure provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the model-based fault solution generation method as described in Embodiment 1.

[0050] The computer-readable storage medium includes volatile or non-volatile, removable or non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, computer program modules, or other data). Computer-readable storage media include, but are not limited to, RAM (Random Access Memory), ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), flash memory or other memory technologies, CD-ROM (Compact Disc Read-Only Memory), DVD or other optical disc storage, cartridges, magnetic tapes, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer.

[0051] Example 4: Embodiment 4 of this disclosure provides an electronic device including a processor and a memory, wherein the processor is used to execute a computer program stored in the memory to implement the model-based fault solution generation method described in Embodiment 1.

[0052] Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, and read-only memory (ROM).

[0053] Those skilled in the art will understand that embodiments of this disclosure can be provided as methods, systems, or computer program products. Therefore, this disclosure can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this disclosure can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0054] This disclosure is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0055] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0056] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0057] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this disclosure. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0058] In summary, the model-based fault solution generation method and apparatus provided in embodiments 1-4 of this disclosure, by integrating relevant technical data of medium-wave transmission and establishing a classified and stored fault strategy model, combined with the visualization resources of the material center, solves the problems of scattered data and low search efficiency in traditional fault handling, making the fault handling strategy more intuitive and easy to understand. This disclosure utilizes a fault type identification model to achieve intelligent identification of fault types, avoiding the subjectivity and misjudgment risk of manual judgment, and improving the accuracy of fault type identification. This disclosure ensures the rapid and effective transmission of fault handling instructions by accurately locating the handling object and sending early warning information through multi-channel communication, coupled with status tracking and secondary reminder mechanisms. This disclosure also constructs a closed-loop feedback mechanism for fault handling effect, continuously optimizing the model and algorithm based on historical processing data, and realizing dynamic iterative upgrades of the fault strategy model and fault handling strategy, thereby avoiding the existing technical problem that the lack of a closed-loop feedback mechanism for fault handling effect makes it impossible to optimize subsequent solutions based on historical processing data, resulting in the need to re-explore the handling path when the same type of fault recurs.

[0059] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this disclosure and not to limit them. Although this disclosure has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of this disclosure. Any modifications or equivalent substitutions that do not depart from the spirit and scope of this disclosure should be covered within the protection scope of the claims of this disclosure.

Claims

1. A model-based fault solution generation method, characterized in that, The method includes: S100: In response to detecting a fault in the medium-wave relay equipment, collect fault-related data and determine the fault type based on the fault-related data; S200: The preset fault strategy model is invoked to match the fault type and obtain the fault handling strategy; the fault strategy model includes maintenance logs, equipment manuals and relevant information on handling medium wave transmission faults, and the technical information in the fault strategy model is classified and stored according to the receiving system, transmission system, transmission system, power distribution system and automation system. S300. Based on the fault strategy model, the fault handling strategy obtained by matching the fault type is combined with the preset work collaboration relationship to determine the handling object. S400: Generate early warning information containing the fault type and fault handling strategy, and send the early warning information to the processing object.

2. The method according to claim 1, characterized in that, In S100, the fault-related data includes the equipment operating parameters of the medium-wave broadcasting equipment when the fault occurs, the description of the fault phenomenon, the time of the fault occurrence, the system identifiers involved in the fault, and the assessment data of the scope of the fault impact.

3. The method according to claim 1, characterized in that, In step S100, determining the fault type based on the fault-related data specifically includes: inputting the fault-related data into a preset fault type identification model, wherein the fault type identification model is trained on historical fault data using a machine learning algorithm, and outputting the fault type that matches the fault-related data most closely.

4. The method according to claim 1, characterized in that, The fault strategy model is associated with a preset material center; The material center is configured to support uploading, categorizing, searching, and previewing of images, videos, and files in the technical materials. Specifically, when matching the corresponding fault handling strategy, the corresponding material resources in the material center are called to supplement the fault handling strategy; The material resources include troubleshooting operation videos, equipment structure diagrams, and parameter configuration files.

5. The method according to claim 1, characterized in that, The targets of the processing are the relevant personnel identified based on their work collaboration relationships, job responsibilities, and historical fault handling records in medium-wave relay. The warning information is sent through preset communication channels, including work group chats, personal message notifications, and email reminders.

6. The method according to claim 1, characterized in that, In step S300, the fault handling strategy obtained by matching the fault type based on the fault strategy model specifically includes: Based on the fault type, keywords are extracted, and relevant information is filtered from the classified and stored technical documents using keyword retrieval technology. Semantic analysis is performed on the filtered relevant data to generate a standardized fault handling strategy. The fault handling strategy includes fault investigation steps, fault solutions, handling precautions, and expected handling time.

7. The method according to claim 1, characterized in that, The method further includes: S500: Receive fault handling result data fed back by the processing object, and update the fault strategy model with the result data to optimize the fault strategy model; the result data includes whether the fault is resolved, cost, risk avoidance degree, actual processing time, and problems encountered during the processing.

8. A model-based fault solution generation device, characterized in that, The device includes: The fault type determination module is configured to collect fault-related data and determine the fault type based on the fault-related data in response to detecting a fault in the medium wave relay equipment. The technical data retrieval module is configured to call a preset fault strategy model to match the fault type and obtain a fault handling strategy. The fault strategy model includes maintenance logs, equipment manuals, and relevant information on handling medium wave relay faults. The technical data in the fault strategy model is stored in categories according to the receiving system, relay system, transmitting system, power distribution system, and automation system. The solution matching module is configured to determine the processing object based on the fault handling strategy obtained by matching the fault type according to the fault strategy model and combined with the preset work collaboration relationship. The early warning information sending module is configured to generate early warning information containing the fault type and fault handling strategy, and send the early warning information to the processing object; The strategy model optimization module is configured to receive fault handling result data fed back by the processing object, update the fault strategy model with the result data, and optimize the fault strategy model; the result data includes whether the fault is resolved, cost, risk avoidance degree, actual processing time, and problems encountered during the processing.

9. The apparatus according to claim 8, characterized in that, The fault type determination module includes: The data acquisition unit is configured to collect equipment operating parameters and fault-related feedback data in real time. The type identification unit is configured to have a built-in machine learning model trained on historical fault data, and to determine the fault type through the machine learning model.

10. The apparatus according to claim 9, characterized in that, The technical data retrieval module is also configured to periodically update the technical data in the fault strategy model, and synchronously add new maintenance logs, revised versions of equipment manuals, and fault handling case data.

Images