Power grid tripping event intelligent identification method based on knowledge graph

Abstract

The invention discloses a power grid tripping event intelligent identification method based on a knowledge graph, and belongs to the technical field of intelligent identification methods, the method comprises the steps of data collection and preprocessing, knowledge extraction, knowledge graph construction, disambiguation and knowledge reasoning, and intelligent identification and auxiliary decision making, and the accuracy and efficiency of power grid fault diagnosis are improved. The fault location and reason can be rapidly positioned, the possibility of misjudgment and missed judgment is reduced, the accuracy and efficiency of power grid fault diagnosis are improved, the intelligent identification method can automatically complete part of fault analysis and disposal work, the service pressure of monitoring personnel is relieved, decision support is assisted, and the fault attribution analysis and statistical function based on a knowledge graph is achieved. Comprehensive fault processing key information can be provided for dispatchers, the dispatchers are assisted to make decisions, and the emergency disposal capability of the power grid is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent identification methods, and in particular to an intelligent identification method for power grid tripping events based on a knowledge graph. Background Art

[0002] As the scale of power grids continues to expand and the complexity increases, the handling of power grid tripping events has put forward higher requirements on the professional capabilities and response speed of monitoring personnel. The traditional dispatching decision-making mechanism that relies on manual experience is unable to cope with the rapid fault analysis and disposal of complex large power grids. Therefore, developing a method that can intelligently identify power grid tripping events is of great significance to improving the accuracy and efficiency of power grid fault diagnosis. Summary of the invention

[0003] The purpose of the present invention is to solve the shortcomings existing in the prior art and to propose a method for intelligent identification of power grid tripping events based on knowledge graph.

[0004] In order to achieve the above-mentioned purpose, the present invention adopts the following technical solution: a method for intelligently identifying power grid tripping events based on knowledge graph, comprising:

[0005] (1) Data collection and preprocessing: Collect historical sample data of power grid tripping events, and clean, standardize, and format these data to ensure data quality and consistency for subsequent knowledge extraction and knowledge graph construction.

[0006] (2) Knowledge extraction: Using natural language processing technology and the knowledge characteristics of the power system, entities, attributes, and relationships related to the power grid tripping event are extracted from the preprocessed data to form knowledge triples. These entities include but are not limited to equipment, fault type, fault cause, and disposal measures.

[0007] (3) Knowledge graph construction: The extracted knowledge triples are integrated to construct a knowledge graph of power grid tripping events. This knowledge graph takes the power grid tripping event as the core and associates related entities to form a complete knowledge system of power grid tripping events.

[0008] (4) Disambiguation and knowledge reasoning: Disambiguate information with uncertainty to reduce differences in understanding caused by improper maintenance or professional barriers. At the same time, knowledge reasoning is performed based on the knowledge graph, combined with relevant power grid status perception to complete cross-confirmation and more information collection.

[0009] (5) Intelligent identification and decision support: Using the constructed knowledge graph of power grid tripping events, the intelligent identification of power grid tripping events can be realized. When a fault occurs, the fault location and cause can be quickly located, assisting the dispatcher in fault analysis and handling decisions.

[0010] The data collection and preprocessing steps also include the collection of basic data on power grid dispatching and the construction of a power grid operation knowledge graph based on the collected data.

[0011] The knowledge extraction step also includes learning the historical sample data of power grid tripping events. Through knowledge extraction and fusion, a knowledge triple model of power grid tripping events is constructed to form the association relationship between entities.

[0012] The power grid tripping event knowledge graph also includes the equipment entity knowledge graph, the accident plan knowledge graph and the disposal process knowledge graph to support the intelligent disposal of power grid faults.

[0013] The disambiguation and knowledge reasoning steps also include disambiguating the uncertain information in the power grid tripping event, reducing the differences in understanding caused by professional barriers, and performing knowledge reasoning based on the knowledge graph, combining with power grid status perception to complete cross-confirmation and more information collection.

[0014] The intelligent identification and decision-making assistance steps also include fault attribution analysis and statistical functions based on the knowledge graph of power grid tripping events, providing dispatchers with comprehensive key information on fault handling and assisting them in making decisions.

[0015] The present invention has the following beneficial effects:

[0016] Improve the accuracy and efficiency of power grid fault diagnosis: Through intelligent identification methods, the fault location and cause can be quickly located, reducing the possibility of misjudgment and missed judgment, and improving the accuracy and efficiency of power grid fault diagnosis.

[0017] Reduce the work pressure of monitoring personnel: Intelligent identification methods can automatically complete part of the fault analysis and disposal work, reduce the work pressure of monitoring personnel and improve work efficiency.

[0018] Auxiliary decision support: Fault attribution analysis and statistical functions based on knowledge graphs can provide dispatchers with comprehensive key information on fault handling, assist them in making decisions, and improve the emergency response capabilities of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A schematic block diagram of the composition of a knowledge graph-based intelligent identification method for power grid tripping events proposed in the present invention. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] Reference Figure 1 , an embodiment provided by the present invention: a method for intelligently identifying power grid tripping events based on a knowledge graph, comprising:

[0022] (1) Data collection and preprocessing: Collect historical sample data of power grid tripping events, and clean, standardize, and format these data to ensure data quality and consistency for subsequent knowledge extraction and knowledge graph construction.

[0023] (2) Knowledge extraction: Using natural language processing technology and the knowledge characteristics of the power system, entities, attributes, and relationships related to the power grid tripping event are extracted from the preprocessed data to form knowledge triples. These entities include but are not limited to equipment, fault type, fault cause, and disposal measures.

[0024] (3) Knowledge graph construction: The extracted knowledge triples are integrated to construct a knowledge graph of power grid tripping events. This knowledge graph takes the power grid tripping event as the core and associates related entities to form a complete knowledge system of power grid tripping events.

[0025] (4) Disambiguation and knowledge reasoning: Disambiguate information with uncertainty to reduce differences in understanding caused by improper maintenance or professional barriers. At the same time, knowledge reasoning is performed based on the knowledge graph, combined with relevant power grid status perception to complete cross-confirmation and more information collection.

[0026] (5) Intelligent identification and decision support: Using the constructed knowledge graph of power grid tripping events, the intelligent identification of power grid tripping events can be realized. When a fault occurs, the fault location and cause can be quickly located, assisting the dispatcher in fault analysis and handling decisions.

[0027] The data collection and preprocessing steps also include the collection of basic data on power grid dispatching and the construction of a power grid operation knowledge graph based on the collected data.

[0028] The knowledge extraction step also includes learning the historical sample data of power grid tripping events. Through knowledge extraction and fusion, a knowledge triple model of power grid tripping events is constructed to form the association relationship between entities.

[0029] The power grid tripping event knowledge graph also includes the equipment entity knowledge graph, the accident plan knowledge graph and the disposal process knowledge graph to support the intelligent disposal of power grid faults.

[0030] The disambiguation and knowledge reasoning steps also include disambiguating the uncertain information in the power grid tripping event, reducing the differences in understanding caused by professional barriers, and performing knowledge reasoning based on the knowledge graph, combining with power grid status perception to complete cross-confirmation and more information collection.

[0031] The intelligent identification and decision-making assistance steps also include fault attribution analysis and statistical functions based on the knowledge graph of power grid tripping events, providing dispatchers with comprehensive key information on fault handling and assisting them in making decisions.

[0032] Working principle: Data collection: First, collect historical sample data of power grid tripping events. These data may come from records of power grid monitoring systems, fault reports, etc. Data preprocessing: clean, standardize and format the collected data to eliminate noise, inconsistency and redundant information in the data to ensure data quality and consistency. Knowledge extraction: use natural language processing technology and power system knowledge characteristics to extract entities, attributes and relationships related to power grid tripping events from preprocessed data. These entities may include equipment, fault type, fault cause, etc., while attributes and relationships describe the association between these entities. Through the study of historical sample data, knowledge extraction and fusion are performed to construct a knowledge triple model of power grid tripping events. These triple models represent the association between entities and are the basis for building knowledge graphs. The knowledge graph construction fuses the extracted knowledge triples to form a knowledge graph of power grid tripping events. This knowledge graph takes the power grid tripping event as the core, associates related entities such as equipment, fault type, and fault cause, and forms a complete knowledge system of power grid tripping events. In the process of constructing the knowledge graph, visualization technology can be used to display the knowledge graph in a graphical way to facilitate user understanding and analysis. Disambiguation: Since the data may be uncertain and ambiguous, it is necessary to disambiguate the information with uncertainty. This helps to reduce the understanding differences caused by improper maintenance or professional barriers. Knowledge reasoning: Based on the constructed knowledge graph, knowledge reasoning can be performed. Combined with relevant power grid state perception information, cross-confirmation and more information collection can be completed to further improve the accuracy and efficiency of power grid tripping event identification. Intelligent identification: Using the constructed power grid tripping event knowledge graph, the system can realize intelligent identification of power grid tripping events. When a new power grid tripping event occurs, the system can quickly locate the fault location and cause. Decision support: Based on the results of intelligent identification, the system can provide dispatchers with comprehensive key information for fault handling. This information can help dispatchers analyze fault conditions more accurately and formulate more effective disposal measures.

[0033] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for intelligent identification of power grid tripping events based on knowledge graph, characterized in that: include: (1) Data collection and preprocessing: Collect historical sample data of power grid tripping events, and clean, standardize, and format these data to ensure data quality and consistency for subsequent knowledge extraction and knowledge graph construction; (2) Knowledge extraction: Using natural language processing technology and the knowledge characteristics of the power system, entities, attributes, and relationships related to the power grid tripping event are extracted from the preprocessed data to form knowledge triples; these entities include but are not limited to equipment, fault type, fault cause, and disposal measures; (3) Knowledge graph construction: The extracted knowledge triples are integrated to construct a knowledge graph of power grid tripping events. This knowledge graph takes the power grid tripping event as the core and associates related entities to form a complete knowledge system of power grid tripping events. (4) Disambiguation and knowledge reasoning: Disambiguate information with uncertainty to reduce differences in understanding caused by improper maintenance or professional barriers. At the same time, perform knowledge reasoning based on the knowledge graph and combine it with relevant power grid status perception to complete cross-confirmation and more information collection. (5) Intelligent identification and decision support: The constructed knowledge graph of power grid tripping events is used to realize intelligent identification of power grid tripping events. When a fault occurs, the fault location and cause can be quickly located, assisting the dispatcher in fault analysis and handling decisions.

2. According to claim 1, a method for intelligently identifying power grid tripping events based on knowledge graph, characterized in that: The data collection and preprocessing steps also include the collection of basic grid dispatch data and the construction of a grid operation knowledge graph based on the collected data.

3. The method for intelligently identifying power grid tripping events based on knowledge graph according to claim 1 is characterized in that: The knowledge extraction step also includes learning the historical sample data of power grid tripping events, constructing a knowledge triple model of power grid tripping events through knowledge extraction and fusion, and forming associations between entities.

4. The method for intelligently identifying power grid tripping events based on knowledge graph according to claim 1 is characterized in that: The power grid tripping event knowledge graph also includes an equipment entity knowledge graph, an accident plan knowledge graph, and a handling process knowledge graph to support intelligent handling of power grid faults.

5. The method for intelligently identifying power grid tripping events based on knowledge graph according to claim 1 is characterized in that: The disambiguation and knowledge reasoning steps also include disambiguating the uncertainty information in the power grid tripping event, reducing the understanding differences caused by professional barriers, and performing knowledge reasoning based on the knowledge graph, combining with power grid status perception to complete cross-confirmation and more information collection.

6. The method for intelligently identifying power grid tripping events based on knowledge graph according to claim 1 is characterized in that: The intelligent identification and decision-making assistance steps also include fault attribution analysis and statistical functions based on the knowledge graph of power grid tripping events, providing dispatchers with comprehensive key information on fault handling to assist them in making decisions.

Images