High-reliability transformer substation multi-interval information intelligent configuration method

Abstract

The invention provides a high-reliability intelligent configuration method for multi-interval information of a transformer substation. The method comprises the following steps: S1, preprocessing multi-interval configuration information data from a high-reliability transformer substation to obtain standardized structured data; s2, determining a corresponding knowledge extraction strategy based on the standardized multi-interval configuration information data type, and extracting knowledge representation information corresponding to the standardized multi-interval configuration information data according to the knowledge extraction strategy; s3, for knowledge representation information of the entities and the attributes extracted from the structured data, establishing association relationships between the entities and between the entities and the attributes, constructing a triple, obtaining a template knowledge graph, and adding the knowledge graph into a graph database; s4, based on the constructed knowledge graph, developing an intelligent configuration algorithm, and realizing reutilization and migration of typical interval configuration; according to the method, the multi-interval configuration workload can be effectively reduced, and the configuration efficiency and accuracy are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power system automation, and in particular to a high-reliability substation multi-bay information intelligent configuration method, namely a new generation high-reliability substation multi-bay information intelligent configuration technology for a new generation of high-reliability substations. Background Art

[0002] In the new generation of high-reliability substations, bay configuration usually refers to the configuration and management of bay-layer equipment to achieve real-time data transmission, intelligence and automation, optimize network communication and enhance remote monitoring capabilities. Through this configuration, the high reliability and safe operation of the system can be ensured, the reliability and efficiency of equipment operation can be improved, the intermediate links and communication bottlenecks can be reduced, and unmanned operation and remote real-time monitoring and data processing can be achieved, thereby promoting the modernization and intelligence of substations and ensuring the stability and efficiency of power grid operation.

[0003] In the secondary system specifications of the new generation of high-reliability substations, detailed provisions are made for the power grid model, plant model, voltage level model, bay model, primary equipment topology model, and IED naming rules in the SCD file. Compared with the model provisions of existing smart substations, there has been a substantial improvement, and in theory, the characteristic attribute extraction and application of the same bay configuration can be realized.

[0004] The bay configuration in the secondary system of the new generation of high-reliability substations is an important link to ensure the stable and reliable operation of the secondary system of the substation. The traditional bay configuration process is cumbersome and time-consuming, especially for multiple bays of the same type. The configuration workload is large, and the multi-bay information intelligent configuration method is the key to improving the level of configuration automation. Although the existing technology has achieved the automation of configuration to a certain extent, the specific configuration process is generally a copy of the typical bay, and then the keyword is replaced to form a new bay. The replacement method is relatively inflexible and requires the replacement position, replacement keyword and other contents to be specified in advance. After the typical bay template is replaced, the original program is no longer applicable. Summary of the invention

[0005] The present invention proposes a method for intelligent configuration of multi-compartment information of a high-reliability substation, which is used for the compartment configuration in the secondary system of the new generation of high-reliability substation described in the above background technology. It can effectively reduce the configuration workload of multiple compartments, improve configuration efficiency and accuracy, and promote the development of intelligent and automated substations.

[0006] The present invention adopts the following technical solutions.

[0007] A high-reliability substation multi-compartment information intelligent configuration method, the method comprising the following steps; Step S1, first preprocessing the multi-bay configuration information data from the high-reliability substation to obtain standardized structured data; Step S2: determining a corresponding knowledge extraction strategy based on the standardized multi-interval configuration information data type, so as to extract knowledge representation information corresponding to the standardized multi-interval configuration information data according to the knowledge extraction strategy; Step S3: for the knowledge representation information of entities and attributes extracted from the structured data, establish associations between entities and between entities and attributes, construct triples including subject, predicate, and object, obtain a template knowledge graph, and add the knowledge graph to the graph database; Step S4: Based on the constructed knowledge graph, develop an intelligent configuration algorithm to achieve reuse and migration of typical interval configurations.

[0008] In step S1, the configuration information data comes from configuration templates of different interval types. When obtaining the configuration information data, the configuration information of the interval configuration files is first obtained in batches through the API interface or data export function of the interval configuration platform; the configuration information includes structured data, semi-structured data and unstructured data.

[0009] In step S1, structured data refers to tabular data that can be directly queried through SQL statements, semi-structured data refers to JSON format or XML format files that need to be processed by a specific parser, and unstructured data refers to text data that requires natural language processing technology to extract information.

[0010] In step S1, if the interval configuration files are stored in different databases, file systems or cloud storage services, the obtained multi-interval configuration information data is integrated, summarized and classified to take into account the differences between different types of configuration file information and the different storage methods; in order to ensure the accuracy of the configuration template generated later, it is necessary to perform data cleaning on the obtained configuration information data, and process the missing values ​​of the configuration items in the configuration file and the non-compliant configuration item content.

[0011] When processing the content of configuration items, the correctness verification of the configuration item content relies on manual work, and then the data is segmented and processed according to the association relationships contained in different templates, and stored in JSON format to generate structured data.

[0012] In step S2, the knowledge representation information includes equipment, parameters, and status to ensure that various information in the substation system can be accurately reflected, so as to obtain the structured multi-interval configuration information data from step S1, and determine the knowledge extraction strategy of different types of configuration files for different data storage methods; In step S2, when determining the knowledge extraction strategy for different types of configuration files, the association relationship between the fields to be configured in the configuration file is determined for different interval types, and the configuration file is divided with the association relationship as the smallest unit for segmentation; the basic constituent unit of the knowledge graph storage is a triple, and the composition of the triple includes three parts: a head entity, a relationship, and a tail entity. The acquired structured data needs to be further divided. To facilitate subsequent template reorganization and configuration file generation, the hierarchical structure relationship of the content contained in the configuration file is selected as the basis for content division. The specific division method is to set the configuration item to the head entity in the knowledge representation information, the association relationship is the hierarchical structure relationship of the content contained in the configuration file, and the tail entity is the corresponding configuration attribute, so as to obtain the basic tuple constituting the knowledge graph.

[0013] In step S3, the knowledge representation information obtained in step S2 is organized and processed. Thus, the knowledge graph corresponding to the multi-interval configuration data is obtained, and the knowledge graph is added to the graph database for storage; the specific method is to first determine the basic attributes of each node based on the entity information contained in the knowledge representation information, and determine the basic attributes and relationships of each edge based on the relationship information; secondly, based on the determined basic attributes of the nodes and the basic attributes and relationships of the edges, construct the knowledge graph corresponding to the multi-source data; finally, synchronize the constructed knowledge graph to the graph database for storage.

[0014] In step S3, a semantic web framework is used to construct a knowledge graph, so that the expression of the device and its attributes is richer and more semantic, and the efficiency of subsequent reasoning and query is improved; specifically, the configuration template JSON data for different interval types is imported into the Neo4j graph database for storage through the Py2Neo library in Python, so as to construct a knowledge graph based on different configuration template types, and the knowledge graph is stored in a graph database to obtain a powerful graph query capability, which is used to efficiently process complex relationships and achieve fast retrieval; In step S3, the properties of the nodes and edges of the constructed knowledge graph are customized and expanded according to actual needs, so that the knowledge graph can adapt to various complex data scenarios and changing needs; In step S3, the knowledge graph is synchronized into the graph database to utilize the cascading security permission mechanism provided by the graph database to effectively ensure the security of the knowledge graph data.

[0015] In step S4, the specific method includes: first, the system obtains the type of interval configuration file to be modified according to user needs and system operation status, and retrieves the template knowledge graph corresponding to the type from the graph database; when the user modifies a configuration item, the system uses the Cypher query language to query the template knowledge graph generated in step S3 to quickly locate and obtain the nodes and attributes associated with the configuration item. In order to improve the flexibility of configuration processing, a regular expression keyword matching algorithm is used to support replacement operations in complex scenarios; During the configuration file migration phase, template engine technology is combined to achieve dynamic generation of configuration files. After the new configuration is generated, the engineering staff will manually confirm it to ensure the security and stability of the system operation by verifying the correctness and consistency of the configuration. The accuracy and reliability of the configuration operation are guaranteed by forming a human-machine combined verification mechanism. The template engine technology includes Freemarker or Thymeleaf.

[0016] The high-reliability substation multi-compartment information intelligent configuration method is operated using a high-reliability substation multi-compartment information intelligent configuration device, the device comprising: The preprocessing unit (301) preprocesses the multi-bay configuration information data from the new generation high-reliability substation to obtain structured data, wherein the configuration information data comes from configuration templates of different bay types.

[0017] The knowledge extraction unit (302) determines a corresponding knowledge extraction strategy based on the standardized multi-interval configuration information data type, so as to extract the knowledge representation information corresponding to the standardized multi-interval configuration information data according to the knowledge extraction strategy, including equipment, parameters, status, etc., to ensure that various information in the system can be accurately reflected.

[0018] The knowledge graph construction unit (303) represents the knowledge information such as entities and attributes extracted from the structured data, establishes the association relationship between entities and between entities and attributes, constructs triples (subject, predicate, object), obtains a template knowledge graph, and adds the knowledge graph to the graph database.

[0019] The intelligent configuration unit (304) realizes the reuse and migration of typical interval configurations based on the constructed knowledge graph through an intelligent configuration algorithm.

[0020] The configuration result display unit (305) finally presents the generated configuration information to the user in an interface manner, making it convenient for the user to view, adjust and confirm the configuration information, thereby improving user experience and operation efficiency.

[0021] Through the above technical solutions, the present invention can effectively reduce the workload of multi-bay configuration, improve configuration efficiency and accuracy, and promote the development of intelligent and automated substations.

[0022] The present invention provides a new generation of high-reliability substation multi-interval information intelligent configuration technology. The multi-interval information intelligent configuration technology based on the knowledge graph is studied. For the existing typical interval configuration, its reuse and migration technology are studied, and a knowledge graph of interval configuration-related data is established to effectively reduce the configuration workload of the secondary system model, graphic parameters, and on-site debugging and acceptance parameters. The innovation of the present invention is that the multi-interval information intelligent configuration technology based on the knowledge graph of the present invention is used to automatically configure the interval layer equipment in the new generation of high-reliability substations, thereby reducing the configuration workload of multiple intervals of the same type, and to a certain extent improves the query and identification efficiency of relevant equipment information, configuration parameters and other contents in the typical interval configuration, effectively improves the organization and utilization of existing configuration texts, and greatly simplifies the tasks of entity and attribute extraction. The method described in the present invention is the core of a new generation of highly reliable substation multi-interval information intelligent configuration technology based on knowledge graph, which can improve the automation and intelligence level of configuration; the present invention, through in-depth research on knowledge graph, explores the reuse and migration technology of typical interval configuration, which can effectively reduce the configuration workload of multiple intervals of the same type and improve the work efficiency and reliability of the overall system. Through the method described in the present invention, the multi-interval information intelligent configuration method based on knowledge graph can be mastered, and an intelligent migration plan for typical interval configuration can be formulated to ensure that manual intervention can be effectively reduced in practical applications and configuration accuracy can be improved.

[0023] Compared with the existing method, the beneficial effects of the present invention are: The multi-interval information intelligent configuration technology based on knowledge graph of the present invention is used to automatically configure the interval layer equipment in the new generation of high-reliability substations, thereby reducing the configuration workload of multiple intervals of the same type. On the one hand, by utilizing the graph structure characteristics of the knowledge graph itself, the text data containing semantic information and having clear logical relationships is organized and managed, and a knowledge graph is established for the relevant data of the existing typical interval configuration, which improves the query and identification efficiency of the relevant equipment information, configuration parameters and other contents in the typical interval configuration to a certain extent. On the other hand, based on the knowledge graph technology, the reuse and migration technology for typical interval configuration is studied, which effectively improves the organization and utilization of existing configuration texts and greatly simplifies the task of entity and attribute extraction. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The present invention is further described in detail below with reference to the accompanying drawings and specific embodiments: Attached Figure 1A schematic diagram of a new generation of highly reliable substation multi-bay information intelligent configuration method provided in the embodiments of this specification; Attached Figure 2 A schematic diagram of the system architecture corresponding to a new generation of highly reliable substation multi-bay information intelligent configuration method provided in the embodiments of this specification; Attached Figure 3 A schematic diagram of the structure of a new generation of highly reliable substation multi-bay information intelligent configuration device provided in an embodiment of this specification. DETAILED DESCRIPTION

[0025] As shown in the figure, a high-reliability substation multi-compartment information intelligent configuration method includes the following steps: Step S1, first preprocessing the multi-bay configuration information data from the high-reliability substation to obtain standardized structured data; Step S2: determining a corresponding knowledge extraction strategy based on the standardized multi-interval configuration information data type, so as to extract knowledge representation information corresponding to the standardized multi-interval configuration information data according to the knowledge extraction strategy; Step S3: for the knowledge representation information of entities and attributes extracted from the structured data, establish associations between entities and between entities and attributes, construct triples including subject, predicate, and object, obtain a template knowledge graph, and add the knowledge graph to the graph database; Step S4: Based on the constructed knowledge graph, develop an intelligent configuration algorithm to achieve reuse and migration of typical interval configurations.

[0026] In step S1, the configuration information data comes from configuration templates of different interval types. When obtaining the configuration information data, the configuration information of the interval configuration files is first obtained in batches through the API interface or data export function of the interval configuration platform; the configuration information includes structured data, semi-structured data and unstructured data.

[0027] In step S1, structured data refers to tabular data that can be directly queried through SQL statements, semi-structured data refers to JSON format or XML format files that need to be processed by a specific parser, and unstructured data refers to text data that requires natural language processing technology to extract information.

[0028] In step S1, if the interval configuration files are stored in different databases, file systems or cloud storage services, the obtained multi-interval configuration information data is integrated, summarized and classified to take into account the differences between different types of configuration file information and the different storage methods; in order to ensure the accuracy of the configuration template generated later, it is necessary to perform data cleaning on the obtained configuration information data, and process the missing values ​​of the configuration items in the configuration file and the non-compliant configuration item content.

[0029] When processing the content of configuration items, the correctness verification of the configuration item content relies on manual work, and then the data is segmented and processed according to the association relationships contained in different templates, and stored in JSON format to generate structured data.

[0030] In step S2, the knowledge representation information includes equipment, parameters, and status to ensure that various information in the substation system can be accurately reflected, so as to obtain the structured multi-interval configuration information data from step S1, and determine the knowledge extraction strategy of different types of configuration files for different data storage methods; In step S2, when determining the knowledge extraction strategy for different types of configuration files, the association relationship between the fields to be configured in the configuration file is determined for different interval types, and the configuration file is divided with the association relationship as the smallest unit for segmentation; the basic constituent unit of the knowledge graph storage is a triple, and the composition of the triple includes three parts: a head entity, a relationship, and a tail entity. The acquired structured data needs to be further divided. To facilitate subsequent template reorganization and configuration file generation, the hierarchical structure relationship of the content contained in the configuration file is selected as the basis for content division. The specific division method is to set the configuration item to the head entity in the knowledge representation information, the association relationship is the hierarchical structure relationship of the content contained in the configuration file, and the tail entity is the corresponding configuration attribute, so as to obtain the basic tuple constituting the knowledge graph.

[0031] In step S3, the knowledge representation information obtained in step S2 is organized and processed. Thus, the knowledge graph corresponding to the multi-interval configuration data is obtained, and the knowledge graph is added to the graph database for storage; the specific method is to first determine the basic attributes of each node based on the entity information contained in the knowledge representation information, and determine the basic attributes and relationships of each edge based on the relationship information; secondly, based on the determined basic attributes of the nodes and the basic attributes and relationships of the edges, construct the knowledge graph corresponding to the multi-source data; finally, synchronize the constructed knowledge graph to the graph database for storage.

[0032] In step S3, a semantic web framework is used to construct a knowledge graph, so that the expression of the device and its attributes is richer and more semantic, and the efficiency of subsequent reasoning and query is improved; specifically, the configuration template JSON data for different interval types is imported into the Neo4j graph database for storage through the Py2Neo library in Python, so as to construct a knowledge graph based on different configuration template types, and the knowledge graph is stored in a graph database to obtain a powerful graph query capability, which is used to efficiently process complex relationships and achieve fast retrieval; In step S3, the properties of the nodes and edges of the constructed knowledge graph are customized and expanded according to actual needs, so that the knowledge graph can adapt to various complex data scenarios and changing needs; In step S3, the knowledge graph is synchronized into the graph database to utilize the cascading security permission mechanism provided by the graph database to effectively ensure the security of the knowledge graph data.

[0033] In step S4, the specific method includes: first, the system obtains the type of interval configuration file to be modified according to user needs and system operation status, and retrieves the template knowledge graph corresponding to the type from the graph database; when the user modifies a configuration item, the system uses the Cypher query language to query the template knowledge graph generated in step S3 to quickly locate and obtain the nodes and attributes associated with the configuration item. In order to improve the flexibility of configuration processing, a regular expression keyword matching algorithm is used to support replacement operations in complex scenarios; During the configuration file migration phase, template engine technology is combined to achieve dynamic generation of configuration files. After the new configuration is generated, the engineering staff will manually confirm it to ensure the security and stability of the system operation by verifying the correctness and consistency of the configuration. The accuracy and reliability of the configuration operation are guaranteed by forming a human-machine combined verification mechanism. The template engine technology includes Freemarker or Thymeleaf.

[0034] The high-reliability substation multi-compartment information intelligent configuration method is operated using a high-reliability substation multi-compartment information intelligent configuration device, the device comprising: The preprocessing unit 301 preprocesses the multi-bay configuration information data from the new generation high-reliability substation to obtain structured data, wherein the configuration information data comes from configuration templates of different bay types.

[0035] The knowledge extraction unit 302 determines a corresponding knowledge extraction strategy based on the standardized multi-interval configuration information data type, so as to extract the knowledge representation information corresponding to the standardized multi-interval configuration information data according to the knowledge extraction strategy, including equipment, parameters, status, etc., to ensure that various information in the system can be accurately reflected.

[0036] The knowledge graph construction unit 303 represents the knowledge information such as entities and attributes extracted from the structured data, establishes the relationship between entities and between entities and attributes, constructs triples (subject, predicate, object), obtains a template knowledge graph, and adds the knowledge graph to the graph database.

[0037] The intelligent configuration unit 304 realizes the reuse and migration of typical interval configurations based on the constructed knowledge graph through an intelligent configuration algorithm.

[0038] The configuration result display unit 305 finally presents the generated configuration information to the user in an interface manner, so as to facilitate the user to view, adjust and confirm the configuration information, thereby improving the user experience and operation efficiency.

[0039] Embodiment 1: like Figure 1 As shown, this embodiment provides a flow chart of a new generation of highly reliable substation multi-bay information intelligent configuration method.

[0040] Depend on Figure 1 It can be seen that in one or more embodiments, a new generation of highly reliable substation multi-bay information intelligent configuration method includes: S101: Preprocessing multi-bay configuration information data from a new generation high-reliability substation to obtain structured data, wherein the configuration information data comes from configuration templates of different bay types.

[0041] In order to ensure the pertinence and accuracy of the template files generated later, the example in this manual first pre-processes the multi-interval configuration information data, that is, the configuration file data from different intervals is summarized, classified, cleaned and structured. This process can remove non-compliant content contained in the data, ensure the accuracy and completeness of the data, and lay a good foundation for subsequent processing procedures.

[0042] Specifically, in one or more embodiments of the present specification, preprocessing is performed on multi-bay configuration information data from a new generation high-reliability substation to obtain structured data, which specifically includes the following process: First, the interval configuration file information is obtained in batches through the interval configuration platform's API interface or data export function. These configuration information includes structured data (table data that can be directly queried through SQL statements), semi-structured data (JSON, XML and other format files that need to be processed by specific parsers) and unstructured data (text data that requires natural language processing technology to extract information). These configuration files may be stored in different databases, file systems or cloud storage services.

[0043] The acquired multi-interval configuration information data is integrated, summarized and classified, taking into account the differences between different types of configuration file information and the different storage methods. In order to ensure the accuracy of the configuration template generated later, the acquired configuration information data needs to be cleaned. This process mainly deals with the missing values ​​of the configuration items in the configuration file and the non-compliant configuration item content. Considering the professionalism of the data, there is currently no mature technical means to automatically verify and check it, so the correctness of the configuration item content will mainly rely on manual verification. Then, according to the association relationship contained in different templates, the data is segmented and stored in JSON format to generate structured data.

[0044] S102: Based on the standardized multi-interval configuration information data type, determine the corresponding knowledge extraction strategy to extract the knowledge representation information corresponding to the standardized multi-interval configuration information data according to the knowledge extraction strategy, including equipment, parameters, status, etc., to ensure that various information in the system can be accurately reflected.

[0045] After the structured multi-interval configuration information data is obtained based on step S101, since different types of interval configuration files often correspond to different data storage methods, it is necessary to determine the knowledge extraction strategies for different types of configuration files in a targeted manner, specifically including: For different interval types, determine the association relationship between the fields to be configured in the configuration file, and divide the configuration file with the association relationship as the smallest unit of segmentation. Since the basic building block of knowledge graph storage is a triple, and the composition of the triple includes a head entity, a relationship, and a tail entity, the acquired structured data needs to be further divided. Considering the subsequent template reorganization and configuration file generation, the hierarchical structure relationship of the content contained in the configuration file is selected as the basis for content division. The specific division idea is to set the configuration item as the head entity in the knowledge representation information, the association relationship is the hierarchical structure relationship of the content contained in the configuration file, and the tail entity is the corresponding configuration attribute. At this point, the basic tuples that constitute the knowledge graph have been acquired.

[0046] S103: For the knowledge representation information such as entities and attributes extracted from the structured data, establish the association relationship between entities and between entities and attributes, construct triples (subject, predicate, object), obtain the template knowledge graph, and add the knowledge graph to the graph database In order to construct an extensible knowledge graph structure and facilitate subsequent template query modification and template file generation based on the knowledge graph, the knowledge representation information obtained in the above step S102 is organized and processed. Thereby, the knowledge graph corresponding to the multi-interval configuration data is obtained, and the knowledge graph is added to the graph database for storage. Specifically, first, the basic attributes of each node are determined based on the entity information contained in the knowledge representation information, and the basic attributes and relationships of each edge are determined based on the relationship information; secondly, based on the determined basic attributes of the nodes and the basic attributes and relationships of the edges, the knowledge graph corresponding to the multi-source data is constructed; finally, the constructed knowledge graph is synchronized to the graph database for storage.

[0047] At the specific implementation level, the present invention uses the semantic web framework to construct a knowledge graph, which makes the expression of devices and their attributes richer and more semantic, effectively improving the efficiency of subsequent reasoning and query. In terms of technical implementation, through the Py2Neo library in Python, the configuration template JSON data for different interval types is imported into the Neo4j graph database for storage, thereby constructing a knowledge graph based on different configuration template types. The use of a graph database to store knowledge graphs fully utilizes its powerful graph query capabilities, which can efficiently process complex relationships and achieve fast retrieval.

[0048] The knowledge graph constructed in this way can have rich attributes on its nodes and edges, which can be flexibly customized and expanded according to actual needs, so that the knowledge graph can adapt to various complex data scenarios and changing needs. At the same time, by synchronizing the knowledge graph to the graph database, the cascading security permissions and other mechanisms provided by the graph database can be fully utilized to effectively ensure the security of the knowledge graph data.

[0049] S104: Based on the constructed knowledge graph, develop intelligent configuration algorithms to achieve reuse and migration of typical interval configurations. Specifically include: First, the system obtains the type of interval configuration file to be modified according to user needs and system operation status, and retrieves the template knowledge graph corresponding to this type from the graph database. When the user modifies a configuration item, the system uses the Cypher query language to query the template knowledge graph generated in step S103 to quickly locate and obtain the nodes and attributes associated with the configuration item. To improve the flexibility of configuration processing, this algorithm uses regular expressions for keyword matching and supports replacement operations in complex scenarios.

[0050] In the configuration file migration phase, this algorithm combines template engine technology (such as Freemarker or Thymeleaf) to achieve dynamic generation of configuration files. After the new configuration is generated, the system requires engineering personnel to manually confirm it to ensure the security and stability of system operation by verifying the correctness and consistency of the configuration. This human-machine combined verification mechanism effectively guarantees the accuracy and reliability of configuration operations.

[0051] This step achieves efficient reuse and migration of typical bay configurations through the implementation of intelligent configuration algorithms, significantly improves configuration management efficiency, and provides strong technical support for intelligent operation and maintenance of substations.

[0052] like Figure 3 As shown, the embodiment of this specification provides a new generation of highly reliable substation multi-bay information intelligent configuration device structure diagram. Figure 3 It can be seen that in one or more embodiments of this specification, a new generation of highly reliable substation multi-bay information intelligent configuration device includes: The preprocessing unit 301 preprocesses the multi-bay configuration information data from the new generation high-reliability substation to obtain structured data, wherein the configuration information data comes from configuration templates of different bay types.

[0053] The knowledge extraction unit 302 determines a corresponding knowledge extraction strategy based on the standardized multi-interval configuration information data type, so as to extract the knowledge representation information corresponding to the standardized multi-interval configuration information data according to the knowledge extraction strategy, including equipment, parameters, status, etc., to ensure that various information in the system can be accurately reflected.

[0054] The knowledge graph construction unit 303 represents the knowledge information such as entities and attributes extracted from the structured data, establishes the relationship between entities and between entities and attributes, constructs triples (subject, predicate, object), obtains a template knowledge graph, and adds the knowledge graph to the graph database.

[0055] The intelligent configuration unit 304 realizes the reuse and migration of typical interval configurations based on the constructed knowledge graph through an intelligent configuration algorithm.

[0056] The configuration result display unit 305 finally presents the generated configuration information to the user in an interface manner, so as to facilitate the user to view, adjust and confirm the configuration information, thereby improving the user experience and operation efficiency.

[0057] Embodiment 2: In this embodiment, based on the constructed knowledge graph, an intelligent configuration algorithm is developed to realize the reuse and migration of typical interval configurations, specifically including: using an intelligent configuration algorithm, utilizing a variety of methods and technologies in modern software engineering, effectively managing existing configuration data, supporting flexible keyword replacement and automatic configuration, and improving the intelligence level of the substation. The specific process is as follows: first, the type of interval configuration file to be modified is obtained, the selection of the configuration template is determined according to user needs and system status, and the template knowledge graph corresponding to the type is obtained from the graph database. When the user modifies a configuration item, the Cypher query language is used to quickly obtain the nodes and attributes associated with the configuration item, and the corresponding content is modified. In order to realize a flexible keyword replacement mechanism, regular expressions are used to match keywords to support more complex replacement scenarios. After the replacement is completed, in the configuration file migration stage, the configuration file is dynamically generated in combination with a template engine (such as Freemarker or Thymeleaf). After the new configuration is finally generated, the configuration operation is manually confirmed by the engineering staff to ensure the correctness and consistency of the new configuration and ensure the security and stability of the system.

Claims

1. A highly reliable substation multi-compartment information intelligent configuration method, characterized by: The method comprises the following steps: Step S1, first preprocessing the multi-bay configuration information data from the high-reliability substation to obtain standardized structured data; Step S2: determining a corresponding knowledge extraction strategy based on the standardized multi-interval configuration information data type, so as to extract knowledge representation information corresponding to the standardized multi-interval configuration information data according to the knowledge extraction strategy; Step S3: for the knowledge representation information of entities and attributes extracted from the structured data, establish associations between entities and between entities and attributes, construct triples including subject, predicate, and object, obtain a template knowledge graph, and add the knowledge graph to the graph database; Step S4: Based on the constructed knowledge graph, develop an intelligent configuration algorithm to achieve reuse and migration of typical interval configurations.

2. A highly reliable substation multi-compartment information intelligent configuration method according to claim 1, characterized in that: In step S1, the configuration information data comes from configuration templates of different interval types. When obtaining the configuration information data, the configuration information of the interval configuration files is first obtained in batches through the API interface or data export function of the interval configuration platform; the configuration information includes structured data, semi-structured data and unstructured data.

3. A highly reliable substation multi-compartment information intelligent configuration method according to claim 2, characterized in that: In step S1, structured data refers to tabular data that can be directly queried through SQL statements, semi-structured data refers to JSON format or XML format files that need to be processed by a specific parser, and unstructured data refers to text data that requires natural language processing technology to extract information.

4. A highly reliable substation multi-compartment information intelligent configuration method according to claim 3, characterized in that: In step S1, if the interval configuration files are stored in different databases, file systems or cloud storage services, the acquired multi-interval configuration information data is integrated, summarized and classified to take into account the differences between different types of configuration file information and different storage methods; In order to ensure the accuracy of the configuration template generated later, it is necessary to clean the acquired configuration information data and process the missing values ​​​​and non-compliant configuration item contents in the configuration file.

5. A highly reliable substation multi-compartment information intelligent configuration method according to claim 4, characterized in that: When processing the content of configuration items, the correctness verification of the configuration item content relies on manual work, and then the data is segmented and processed according to the association relationships contained in different templates, and stored in JSON format to generate structured data.

6. A highly reliable substation multi-compartment information intelligent configuration method according to claim 1, characterized in that: In step S2, the knowledge representation information includes equipment, parameters, and status to ensure that various information in the substation system can be accurately reflected, so as to obtain the structured multi-interval configuration information data from step S1, and determine the knowledge extraction strategy of different types of configuration files for different data storage methods; In step S2, when determining the knowledge extraction strategy for different types of configuration files, the association relationship between the fields to be configured in the configuration file is determined for different interval types, and the configuration file is divided with the association relationship as the smallest unit for segmentation; the basic constituent unit of the knowledge graph storage is a triple, and the composition of the triple includes three parts: a head entity, a relationship, and a tail entity. The acquired structured data needs to be further divided. To facilitate subsequent template reorganization and configuration file generation, the hierarchical structure relationship of the content contained in the configuration file is selected as the basis for content division. The specific division method is to set the configuration item to the head entity in the knowledge representation information, the association relationship is the hierarchical structure relationship of the content contained in the configuration file, and the tail entity is the corresponding configuration attribute, so as to obtain the basic tuple constituting the knowledge graph.

7. A highly reliable substation multi-compartment information intelligent configuration method according to claim 6, characterized in that: In step S3, the knowledge representation information obtained in step S2 is organized and processed; Thereby, the knowledge graph corresponding to the multi-interval configuration data is obtained, and the knowledge graph is added to the graph database for storage; the specific method is, first, the basic attributes of each node are determined according to the entity information contained in the knowledge representation information, and the basic attributes and relationships of each edge are determined based on the relationship information; secondly, based on the determined basic attributes of the nodes and the basic attributes and relationships of the edges, the knowledge graph corresponding to the multi-source data is constructed; finally, the constructed knowledge graph is synchronized to the graph database for storage.

8. A highly reliable substation multi-compartment information intelligent configuration method according to claim 7, characterized in that: In step S3, a semantic web framework is used to construct a knowledge graph, so that the expression of the device and its attributes is richer and more semantic, and the efficiency of subsequent reasoning and query is improved; specifically, the configuration template JSON data for different interval types is imported into the Neo4j graph database for storage through the Py2Neo library in Python, so as to construct a knowledge graph based on different configuration template types, and the knowledge graph is stored in a graph database to obtain a powerful graph query capability, which is used to efficiently process complex relationships and achieve fast retrieval; In step S3, the properties of the nodes and edges of the constructed knowledge graph are customized and expanded according to actual needs, so that the knowledge graph can adapt to various complex data scenarios and changing needs; In step S3, the knowledge graph is synchronized into the graph database to utilize the cascading security permission mechanism provided by the graph database to effectively ensure the security of the knowledge graph data.

9. A highly reliable substation multi-compartment information intelligent configuration method according to claim 7, characterized in that: In step S4, the specific method includes: first, the system obtains the type of interval configuration file to be modified according to user needs and system operation status, and retrieves the template knowledge graph corresponding to the type from the graph database; when the user modifies a configuration item, the system uses the Cypher query language to query the template knowledge graph generated in step S3 to quickly locate and obtain the nodes and attributes associated with the configuration item. In order to improve the flexibility of configuration processing, a regular expression keyword matching algorithm is used to support replacement operations in complex scenarios; During the configuration file migration phase, template engine technology is combined to achieve dynamic generation of configuration files. After the new configuration is generated, the engineering staff will manually confirm it to ensure the security and stability of the system operation by verifying the correctness and consistency of the configuration. The accuracy and reliability of the configuration operation are guaranteed by forming a human-machine combined verification mechanism. The template engine technology includes Freemarker or Thymeleaf.

10. A high-reliability substation multi-compartment information intelligent configuration method according to claim 9, characterized in that: The high-reliability substation multi-compartment information intelligent configuration method is operated using a high-reliability substation multi-compartment information intelligent configuration device, the device comprising: A preprocessing unit (301) preprocesses multi-bay configuration information data from a new generation high-reliability substation to obtain structured data; Wherein, the configuration information data are respectively from configuration templates of different interval types; The knowledge extraction unit (302) determines a corresponding knowledge extraction strategy based on the standardized multi-interval configuration information data type, so as to extract the knowledge representation information corresponding to the standardized multi-interval configuration information data according to the knowledge extraction strategy, including equipment, parameters, status, etc., to ensure that various information in the system can be accurately reflected; The knowledge graph construction unit (303) extracts knowledge representation information such as entities and attributes from the structured data, establishes associations between entities and between entities and attributes, constructs triples (subject, predicate, object), obtains a template knowledge graph, and adds the knowledge graph to the graph database; An intelligent configuration unit (304), based on the constructed knowledge graph, realizes the reuse and migration of typical interval configurations through an intelligent configuration algorithm; The configuration result display unit (305) finally presents the generated configuration information to the user in an interface manner, making it convenient for the user to view, adjust and confirm the configuration information, thereby improving user experience and operation efficiency.

Images