Grounding protection method and system based on risk platform supervision
By acquiring and processing substation operation plan data through a risk platform, and constructing an association structure diagram and rule knowledge base, the problem of traditional grounding protection relying on manual experience is solved, achieving fast, convenient verification efficiency and safety.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-31
- Publication Date
- 2026-04-14
AI Technical Summary
Traditional grounding protection measures rely on manual experience, resulting in low verification efficiency. Existing systems cannot be linked to real-time power grid status, leading to low verification efficiency of substation operation plan data.
The system obtains substation work plan data through a risk platform, performs preprocessing and data cleaning, constructs an association structure diagram and a rule knowledge base, and uses the rule knowledge base to perform risk analysis to determine whether there are any risks in the substation work plan data.
It enables rapid and convenient verification of substation work plan data, improves verification efficiency, and ensures work safety.
Smart Images
Figure CN121860411A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of power safety monitoring technology, specifically to a grounding protection method and system based on risk platform monitoring. Background Technology
[0002] Traditional grounding protection measures rely heavily on manual experience from preparation to execution. Work permit issuers and safety supervisors must meticulously verify the location, quantity, and operational sequence of grounding wires against the power grid wiring diagram and safety regulations. While existing systems and semantic large-scale models can retrieve equipment data, their static analysis mode fails to correlate with real-time power grid conditions, resulting in low verification efficiency. Therefore, a grounding protection method and system based on risk platform supervision is needed to quickly and conveniently verify substation work plan data. Summary of the Invention
[0003] The purpose of this invention is to provide a grounding protection method and system based on risk platform supervision, which can quickly and conveniently verify substation operation plan data.
[0004] To achieve the above objectives, embodiments of the present invention provide a grounding protection method based on risk platform supervision, the grounding protection method comprising: The risk platform obtains substation work plans containing key information such as work content, location, power outage range, planned personnel, and a preliminary description of safety measures. The substation operation plan is preprocessed to obtain operation data that meets the requirements; Extract the equipment information from the operation data and retrieve the corresponding primary wiring diagram from the power grid resource business platform; Establish the correspondence between the equipment information in the operation data and the primary wiring diagram to construct an associated structure diagram; The operation data is parsed and classified to obtain the corresponding classification data; The classified data is combined with the association structure graph to obtain a rule knowledge base; The risk platform acquires data on substation operation plans that require supervision regarding grounding work, and performs risk analysis using a rule knowledge base to determine whether the data on substation operation plans requiring supervision contains risks.
[0005] Optionally, the substation work plan is preprocessed to obtain work data that meets the requirements, including: Obtain the substation operation plan and remove duplicate or invalid operation plans; After the elimination is completed, the missing values in the substation operation plan will be supplemented; After the supplementation is completed, redundant words and symbols in the substation operation plan are removed to obtain operation data that meets the requirements.
[0006] Optionally, a correspondence is established between the equipment information in the operation data and the primary wiring diagram to construct an associated structure diagram, including: Obtain equipment information from the operation data and perform data cleaning and feature extraction; The extracted task data is initially grouped to group multiple entities that are suspected of describing the same physical device into the same initial set; Perform secondary matching on multiple entities in the initial set to obtain multiple mapping names for the same physical device; Multiple entities are matched a second time for manual verification and authoritative authentication to obtain multiple accurate mapping names for the same physical device; Based on the multiple mapping names obtained for the same physical device, the physical device is associated with the primary wiring diagram to obtain an association structure diagram of multiple mapping names and primary wiring diagrams.
[0007] Optionally, the extracted job data is preliminarily grouped to group multiple entities suspected of describing the same physical device into the same initial set, including: Multiple attributes of entities in the job data are obtained, and the same attributes with the highest weight are matched with the physical devices to achieve preliminary matching between entities; After the initial matching is completed, the similarity between multiple attributes and attributes that are suspected to describe the same physical device is determined, and weights are assigned to different attributes. Based on the obtained similarity and assigned weights, the relevance between the multiple entities and the physical device is calculated; Entities with a relevance greater than a preset threshold are selected as entities mapped to the physical device and grouped into the same initial set.
[0008] Optionally, a secondary matching is performed on multiple entities in the initial set to obtain multiple mapping names for the same physical device, including: Obtain the initial set, the corresponding context, and information about the physical devices; Feature extraction is performed on the context of the initial set and the information of the physical devices; The initial set after feature extraction, along with the corresponding context and physical device information, is fed into a Hidden Markov Model to further match the entities in the initial set, thereby obtaining multiple mapping names for the same physical device.
[0009] Optionally, the job data is obtained, parsed, and classified to obtain corresponding classification data, including: The task data is acquired, and features are extracted from the task data to obtain the corresponding entities; Filter the device entities with equipment descriptions and the personnel entities with personnel descriptions from the given entities; Obtain environmental feature words describing the work environment from the job data; Obtain safety feature words describing safety measures from the work data, as well as special descriptive words for special working conditions; The equipment entities, personnel entities, environmental feature words, safety feature words, and special descriptive words are respectively subjected to TF-IDF transformation to convert each segment of the description in the operation data into a multi-dimensional score vector; Cluster analysis is performed on the obtained multidimensional score vectors to obtain the corresponding classifications, and then the corresponding classification data is obtained.
[0010] Optionally, the risk platform acquires substation work plan data requiring supervision regarding grounding operations and performs risk analysis using a rule knowledge base to determine whether the substation work plan data requiring supervision contains risks, including: Acquire the substation operation plan data that needs to be monitored and perform feature analysis to obtain multiple plan features; The matching degree between the substation operation plan data to be monitored and the classification data in the rule knowledge base or the association structure diagram is determined according to formula (1): Formula (1), in, This indicates several characteristics of the substation work plan data that require monitoring. The attributes of the classification data to be matched or the association structure graph The degree of matching, This indicates the number of features in the substation operation plan data whose similarity to the features of the classification data to be matched or the features of the association structure diagram is greater than a preset threshold. This indicates the number of features in the substation work plan data. This indicates the number of features in the classification data to be matched or the association structure graph. The classification data and association structure diagram with the highest matching degree are selected as the matching data for the substation operation plan data that needs to be monitored.
[0011] Optionally, the risk platform acquires substation work plan data requiring supervision regarding grounding operations and performs risk analysis using a rule knowledge base to determine whether the substation work plan data requiring supervision contains risks, including: Obtain matching data for the substation operation plan data that needs to be monitored, and determine the differences, defects, and conflicts between the substation operation plan data and the matching data, thereby obtaining risk factors; The risk factors are compared pairwise using the 1-9 scale method to obtain the judgment matrix; Divide each column element in the judgment matrix by the sum of that column to normalize the column; After column normalization, the sum of each row of the judgment matrix is obtained. Divide the values of each row of the judgment matrix by the sum to obtain the weight of each row, thereby obtaining the weight of each risk factor; The risk factors of the substation operation plan data are scored and standardized. The standardized risk factor scores are multiplied by their corresponding weights to obtain a comprehensive risk score, and the risk level of the substation operation plan data requiring supervision is determined based on the comprehensive risk score.
[0012] On the other hand, the present invention can also provide a grounding protection system based on risk platform supervision, the grounding protection system including an execution module for executing a grounding protection method based on risk platform supervision as described above.
[0013] Through the above technical solution, the present invention provides a grounding protection method and system based on risk platform supervision. This method acquires substation operation plans containing key information such as work content, location, outage range, planning personnel, and a preliminary description of safety measures through a risk platform. After acquiring the substation operation plan, it can be preprocessed to obtain compliant operation data. After acquiring the operation data, equipment information can be extracted, and the corresponding primary wiring diagram can be retrieved from the power grid resource business platform. After obtaining the primary wiring diagram, the correspondence between the equipment information in the operation data and the primary wiring diagram can be constructed, thereby building an association structure diagram. The operation data can be parsed and classified to obtain corresponding classification data. After obtaining the corresponding classification data, it can be combined with the association structure diagram to obtain a rule knowledge base. The risk platform can acquire substation operation plan data requiring supervision related to grounding operations, and then perform risk analysis through the rule knowledge base to determine whether the substation operation plan data requiring supervision has any risks. This grounding protection method can quickly and conveniently verify substation operation plan data.
[0014] Other features and advantages of the embodiments of the present invention will be described in detail in the following detailed description section. Attached Figure Description
[0015] The accompanying drawings are provided to further illustrate embodiments of the present invention and form part of the specification. They are used together with the following detailed description to explain the embodiments of the present invention, but do not constitute a limitation thereof. In the drawings: Figure 1 This is a flowchart of a grounding protection method based on risk platform supervision according to an embodiment of the present invention; Figure 2 This is a primary wiring diagram of a grounding protection method based on risk platform supervision according to an embodiment of the present invention. Detailed Implementation
[0016] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit the scope of the present invention.
[0017] In the embodiments of this application, certain software, components, models and other existing solutions in the industry may be mentioned. These should be regarded as exemplary and are only intended to illustrate the feasibility of implementing the technical solution of this application. However, they do not mean that the applicant has used or necessarily used the solution.
[0018] Figure 1 This is a flowchart of a grounding protection method based on risk platform supervision according to an embodiment of the present invention. In this invention, the grounding protection method may include the following steps: In step S1, the risk platform obtains a substation operation plan containing key information such as work content, location, power outage range, planning personnel, and a preliminary description of safety measures.
[0019] In step S2, the substation work plan is preprocessed to obtain work data that meets the requirements.
[0020] In step S3, the equipment information is extracted from the operation data, and the corresponding primary wiring diagram is retrieved from the power grid resource business platform.
[0021] In step S4, the correspondence between the equipment information in the work data and the primary wiring diagram is established to construct the associated structure diagram.
[0022] In step S5, the job data is parsed and classified to obtain the corresponding classification data.
[0023] In step S6, the categorized data is combined with the association structure graph to obtain the rule knowledge base.
[0024] In step S7, the risk platform obtains substation operation plan data that requires supervision regarding grounding operations, and performs risk analysis through a rule knowledge base to determine whether there are any risks in the substation operation plan data that requires supervision.
[0025] In this invention, the risk platform can acquire a substation work plan containing key information such as work content, location, power outage area, planning personnel, and a preliminary description of safety measures. After acquiring the substation work plan, it can be preprocessed to obtain work data that meets the requirements. After acquiring the work data, equipment information can be extracted, and the corresponding primary wiring diagram can be retrieved from the power grid resource business platform. After obtaining the primary wiring diagram, the correspondence between the equipment information in the work data and the primary wiring diagram can be established, such as... Figure 2 The diagram shown is a primary wiring diagram, from which an association structure diagram can be constructed. This operational data can be parsed and categorized to obtain corresponding categorized data. After obtaining the categorized data, it can be combined with the association structure diagram to obtain a rule knowledge base. This risk platform can obtain substation operation plan data requiring supervision related to grounding operations, and then perform risk analysis using the rule knowledge base to determine whether the monitored substation operation plan data contains risks. This grounding protection method can quickly and conveniently verify substation operation plan data.
[0026] In one embodiment of the present invention, the preprocessing procedure may include: In step S8, the substation work plan is obtained and duplicate or invalid work plans are removed.
[0027] In step S9, after the elimination is completed, the missing values in the substation operation plan are supplemented.
[0028] In step S10, after the supplementation is completed, redundant words and symbols in the substation operation plan are removed to obtain operation data that meets the requirements.
[0029] In this invention, during preprocessing, substation work plans can be obtained, and duplicate or invalid work plans can be removed. After removal, missing values in the substation work plans can be added. After addition, redundant words and symbols in the substation work plans can be removed to obtain work data that meets the requirements.
[0030] In one embodiment of the present invention, the process of constructing an association structure graph may include: In step S11, the equipment information in the operation data is obtained and the data is cleaned and features are extracted.
[0031] In step S12, the job data after feature extraction is initially grouped to group multiple entities that are suspected of describing the same physical device into the same initial set.
[0032] In step S13, a secondary matching is performed on multiple entities in the initial set to obtain multiple mapping names for the same physical device.
[0033] In step S14, multiple entities are matched a second time for manual verification and authoritative authentication to obtain multiple accurate mapping names for the same physical device.
[0034] In step S15, based on the multiple mapping names obtained for the same physical device, the physical device is associated with a primary wiring diagram to obtain an association structure diagram of multiple mapping names associated with a primary wiring diagram.
[0035] In this invention, when constructing the association structure diagram, equipment information from the work data can be obtained and data cleaning and feature extraction can be performed. After cleaning and extraction, the feature-extracted work data can be initially grouped, thereby grouping multiple entities that may describe the same physical equipment into the same initial set. Secondary matching can be performed on the multiple entities in the initial set to obtain multiple mapping names for the same physical equipment. Then, secondary matching of the multiple entities can be performed for manual verification and authoritative authentication to obtain accurate multiple mapping names for the same physical equipment. Based on the obtained multiple mapping names for the same physical equipment, the physical equipment can be associated with a primary wiring diagram to obtain an association structure diagram relating multiple mapping names to the primary wiring diagram.
[0036] In one embodiment of the present invention, the preliminary grouping process may include: In step S16, multiple attributes of entities in the job data are obtained, and the same attributes with the greatest weight are matched with physical devices to achieve preliminary matching between entities.
[0037] In step S17, after the initial matching is completed, the similarity between multiple attributes and attributes that are suspected to describe the same physical device is determined, and weights are assigned to different attributes.
[0038] In step S18, the relevance between multiple entities and physical devices is calculated based on the obtained similarity and assigned weights.
[0039] In step S19, entities with a relevance greater than a preset threshold are selected as entities mapped to physical devices and grouped into the same initial set.
[0040] In this invention, during initial grouping, multiple attributes of entities in the job data can be obtained, and the same attributes with the highest weight can be matched with physical devices to achieve initial matching between entities. After initial matching, the similarity between multiple attributes and attributes that are suspected of describing the same physical device can be determined, and different attributes are assigned weights. Based on the obtained similarity and assigned weights, the relevance between multiple entities and physical devices is calculated. Entities with a relevance greater than a preset threshold can be selected as entities mapped to physical devices and grouped into the same initial set.
[0041] In one embodiment of the present invention, the secondary allocation process may include: In step S20, the initial set, the corresponding context, and the information of the physical device are obtained.
[0042] In step S21, the context of the initial set and the information of the physical device are used to extract features.
[0043] In step S22, the initial set after feature extraction, the corresponding context, and the information of the physical device are fed into the Hidden Markov Model to further match the entities in the initial set, thereby obtaining multiple mapping names for the same physical device.
[0044] In this invention, during secondary matching, an initial set, its corresponding context, and information about the physical device can be obtained. Then, features can be extracted from the context and physical device information of the initial set. The feature-extracted initial set, its corresponding context, and the physical device information can be fed into a Hidden Markov Model to further match entities in the initial set, thereby obtaining multiple mapping names for the same physical device.
[0045] In one embodiment of the present invention, the process of obtaining classification data may include: In step S23, the job data is acquired and features are extracted from the job data to obtain the corresponding entities.
[0046] In step S24, the device entities with device descriptions and the personnel entities with personnel descriptions are filtered out from the entities.
[0047] In step S25, environmental feature words describing the work environment are obtained from the job data.
[0048] In step S26, safety feature words describing safety measures and special descriptive words for special working conditions are obtained from the work data.
[0049] In step S27, the equipment entity, personnel entity, environmental feature words, safety feature words, and special descriptive words are converted into TF-IDF to convert each segment of description in the work data into a multidimensional score vector.
[0050] In step S28, cluster analysis is performed based on the obtained multidimensional score vectors to obtain the corresponding classifications, thereby obtaining the corresponding classification data.
[0051] In this invention, during data classification, operational data can be acquired and features extracted to obtain corresponding entities. After acquiring entities, equipment entities describing equipment and personnel entities describing personnel can be filtered. After filtering, environmental feature words describing the work environment can be obtained from the operational data. Safety feature words describing safety measures and special descriptive words for special working conditions can be obtained from the operational data. Then, TF-IDF transformation can be performed on equipment entities, personnel entities, environmental feature words, safety feature words, and special descriptive words to convert each segment of description in the operational data into a multidimensional score vector. Cluster analysis can be performed based on the obtained multidimensional score vectors to obtain the corresponding classifications, thereby acquiring the corresponding classification data.
[0052] In one embodiment of the present invention, the first process for determining risk may include: In step S29, the substation operation plan data that needs to be monitored is obtained and feature analysis is performed to obtain multiple plan features.
[0053] In step S30, the matching degree between the substation operation plan data to be monitored and the classification data or association structure diagram in the rule knowledge base is determined according to formula (1): Formula (1), in, This indicates several characteristics of the substation work plan data that require monitoring. Attributes of the categorical data or association graph to be matched The degree of matching, This indicates the number of features in the substation work plan data whose similarity to features in the classification data or association structure diagram to be matched is greater than a preset threshold. This indicates the number of features in the substation work plan data. This indicates the number of features in the classification data or association graph to be matched.
[0054] In step S31, the classification data and association structure diagram with the highest matching degree are selected as the matching data for the substation operation plan data that needs to be supervised.
[0055] In this invention, when determining risks, the substation operation plan data that needs to be monitored can be obtained and its features analyzed to obtain multiple plan features. Then, the matching degree between the substation operation plan data that needs to be monitored and the classification data or association structure diagram in the rule knowledge base can be determined according to formula (1). After obtaining the matching degree, the classification data and association structure diagram with the highest matching degree can be selected as the matching data for the substation operation plan data that needs to be monitored.
[0056] In one embodiment of the present invention, the second process for determining risk may include: In step S32, matching data of the substation operation plan data that needs to be monitored is obtained, and the differences, defects and conflicts between the substation operation plan data and the matching data are determined, thereby obtaining the risk factors; In step S33, risk factors are compared pairwise using the 1-9 scaling method to obtain a judgment matrix; In step S34, each column element in the judgment matrix is divided by the sum of that column to normalize the column; In step S35, after column normalization, the sum of each row of the judgment matrix is calculated, and the sum of the judgment matrix is obtained. In step S36, the values of each row of the judgment matrix are divided by the sum to obtain the weight of each row, thereby obtaining the weight of each risk factor; In step S37, the risk factors of the substation operation plan data are scored and standardized. In step S38, the scores of the standardized risk factors are multiplied by their corresponding weights to obtain a comprehensive risk score, and the risk level of the substation operation plan data that needs to be monitored is determined based on the comprehensive risk score.
[0057] In this invention, when determining risk, matching data of the substation operation plan data requiring monitoring can be obtained, and the differences, defects, and conflicts between the substation operation plan data and the matching data can be identified, thereby obtaining risk factors. After obtaining the risk factors, pairwise comparisons can be performed using the 1-9 scaling method to obtain a judgment matrix. After obtaining the judgment matrix, each column element can be divided by the sum of that column to normalize the columns. After column normalization, the sum of each row of the judgment matrix can be obtained to obtain the total sum of the judgment matrix. The values of each row of the judgment matrix can be divided by the total sum to obtain the weight of each row, thereby obtaining the weight of each risk factor. The risk factors of the substation operation plan data can be scored and standardized. Multiplying the standardized risk factor scores by their corresponding weights yields a comprehensive risk score, and the risk level of the substation operation plan data requiring monitoring can be determined based on the comprehensive risk score, allowing for timely warnings. This method of using the analytic hierarchy process (AHP) to determine the risk level of a substation work plan can increase the weight of important factors as needed, thereby improving the assessment of the risk level of the substation work plan.
[0058] On the other hand, the present invention can also provide a grounding protection system based on risk platform supervision, wherein the grounding protection system may include an execution module. This execution module can be used to perform a grounding protection method based on risk platform supervision as described above.
[0059] Through the above technical solution, the present invention provides a grounding protection method and system based on risk platform supervision. This method acquires substation operation plans containing key information such as work content, location, outage range, planning personnel, and a preliminary description of safety measures through a risk platform. After acquiring the substation operation plan, it can be preprocessed to obtain compliant operation data. After acquiring the operation data, equipment information can be extracted, and the corresponding primary wiring diagram can be retrieved from the power grid resource business platform. After obtaining the primary wiring diagram, the correspondence between the equipment information in the operation data and the primary wiring diagram can be constructed, thereby building an association structure diagram. The operation data can be parsed and classified to obtain corresponding classification data. After obtaining the corresponding classification data, it can be combined with the association structure diagram to obtain a rule knowledge base. The risk platform can acquire substation operation plan data requiring supervision related to grounding operations, and then perform risk analysis through the rule knowledge base to determine whether the substation operation plan data requiring supervision has any risks. This grounding protection method can quickly and conveniently verify substation operation plan data.
[0060] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application 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.
[0061] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. 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, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0062] 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.
[0063] 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.
[0064] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0065] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.
[0066] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.
[0067] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.
[0068] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.
Claims
1. A grounding protection method based on risk platform supervision, characterized in that, The grounding protection method includes: The risk platform obtains substation work plans containing key information such as work content, location, power outage range, planned personnel, and a preliminary description of safety measures. The substation operation plan is preprocessed to obtain operation data that meets the requirements; Extract the equipment information from the operation data and retrieve the corresponding primary wiring diagram from the power grid resource business platform; Establish the correspondence between the equipment information in the operation data and the primary wiring diagram to construct an associated structure diagram; The operation data is parsed and classified to obtain the corresponding classification data; The classified data is combined with the association structure graph to obtain a rule knowledge base; The risk platform acquires data on substation operation plans that require supervision related to grounding work, and performs risk analysis through a rule knowledge base to determine whether there are any risks in the data on substation operation plans that require supervision.
2. The grounding protection method according to claim 1, characterized in that, The substation work plan is preprocessed to obtain work data that meets the requirements, including: Obtain the substation operation plan and remove duplicate or invalid operation plans; After the elimination is completed, the missing values in the substation operation plan will be supplemented; After the supplementation is completed, redundant words and symbols in the substation operation plan are removed to obtain operation data that meets the requirements.
3. The grounding protection method according to claim 1, characterized in that, Constructing the correspondence between the equipment information in the operation data and the primary wiring diagram to build an associated structure diagram, including: Obtain equipment information from the operation data and perform data cleaning and feature extraction; The extracted job data is initially grouped to group multiple entities that are suspected of describing the same physical device into the same initial set; Perform secondary matching on multiple entities in the initial set to obtain multiple mapping names for the same physical device; Multiple entities are matched a second time for manual verification and authoritative authentication to obtain multiple accurate mapping names for the same physical device; Based on the multiple mapping names obtained for the same physical device, the physical device is associated with the primary wiring diagram to obtain an association structure diagram that associates multiple mapping names with the primary wiring diagram.
4. The grounding protection method according to claim 3, characterized in that, The extracted job data is initially grouped to group multiple entities that are suspected of describing the same physical device into the same initial set, including: Obtain multiple attributes of entities in the job data, and match the same attributes with the highest weight to the physical devices to achieve preliminary matching between entities; After the initial matching is completed, the similarity between multiple attributes and attributes that are suspected to describe the same physical device is determined, and weights are assigned to different attributes. Based on the obtained similarity and assigned weights, the relevance between multiple entities and the physical device is calculated; Entities with a relevance greater than a preset threshold are selected as entities mapped to the physical device and grouped into the same initial set.
5. The grounding protection method according to claim 3, characterized in that, Perform secondary matching on multiple entities in the initial set to obtain multiple mapping names for the same physical device, including: Obtain the initial set, the corresponding context, and information about the physical devices; Feature extraction is performed on the context of the initial set and the information of the physical devices; The initial set after feature extraction, along with the corresponding context and physical device information, is fed into a Hidden Markov Model to further match the entities in the initial set, thereby obtaining multiple mapping names for the same physical device.
6. The grounding protection method according to claim 1, characterized in that, The task data is acquired, parsed, and classified to obtain corresponding classification data, including: The task data is acquired, and features are extracted from the task data to obtain the corresponding entities; Filter the device entities with equipment descriptions and the personnel entities with personnel descriptions from the given entities; Obtain environmental feature words describing the work environment from the job data; Obtain safety feature words describing safety measures from the work data, as well as special descriptive words for special working conditions; The equipment entities, personnel entities, environmental feature words, safety feature words, and special descriptive words are respectively subjected to TF-IDF transformation to convert each segment of the description in the operation data into a multi-dimensional score vector; Cluster analysis is performed on the obtained multidimensional score vectors to obtain the corresponding classifications, and then the corresponding classification data is obtained.
7. The grounding protection method according to claim 1, characterized in that, The risk platform acquires substation work plan data requiring supervision related to grounding operations and performs risk analysis using a rule knowledge base to determine whether the monitored substation work plan data contains risks, including: Acquire the substation operation plan data that needs to be monitored and perform feature analysis to obtain multiple plan features; The matching degree between the substation operation plan data to be monitored and the classification data in the rule knowledge base or the association structure diagram is determined according to formula (1): Official (1), in, This indicates several characteristics of the substation work plan data that require monitoring. The attributes of the classification data to be matched or the association structure graph The degree of matching, This indicates the number of features in the substation operation plan data whose similarity to the features of the classification data to be matched or the features of the association structure diagram is greater than a preset threshold. This indicates the number of features in the substation work plan data. This indicates the number of features in the classification data to be matched or the association structure graph. The classification data and association structure diagram with the highest matching degree are selected as the matching data for the substation operation plan data that needs to be monitored.
8. The grounding protection method according to claim 7, characterized in that, The risk platform acquires substation work plan data requiring supervision related to grounding operations and performs risk analysis using a rule knowledge base to determine whether the monitored substation work plan data contains risks, including: Obtain matching data for the substation operation plan data that needs to be monitored, and determine the differences, defects, and conflicts between the substation operation plan data and the matching data, thereby obtaining risk factors; The risk factors are compared pairwise using the 1-9 scale method to obtain the judgment matrix; Divide each column element in the judgment matrix by the sum of that column to normalize the column; After column normalization, the sum of each row of the judgment matrix is obtained. Divide the values of each row of the judgment matrix by the sum to obtain the weight of each row, thereby obtaining the weight of each risk factor; The risk factors of the substation operation plan data are scored and standardized. The scores of the standardized risk factors are multiplied by their corresponding weights to obtain a comprehensive risk score, and the risk level of the substation operation plan data that needs to be monitored is determined based on the comprehensive risk score.
9. A grounding protection system based on risk platform supervision, characterized in that, The grounding protection system includes an execution module for executing a grounding protection method based on risk platform supervision as described in any one of claims 1-8.