Power equipment fault tracing method and system based on knowledge graph

Abstract

The invention discloses a power equipment fault traceability method and system based on a knowledge graph, which is applied to the field of power equipment fault traceability, and comprises the following steps: constructing a power equipment fault knowledge graph ontology by adopting a top-down and bottom-up combined mode based on power equipment fault related original data, defining ontology concepts and relationships, and establishing a power equipment fault knowledge graph ontology; defining a unique attribute for each ontology concept; the method comprises the following steps of: converting semi-structured data and non-structured data in power equipment fault related original data into triple structure data by adopting a method of manually defining a template rule, extracting a triple form of a relationship between entities based on an ontology concept and a relationship, and constructing a power equipment fault knowledge graph; and based on the power equipment fault knowledge graph, training a power equipment fault traceability model based on the graph convolutional network, and inputting the to-be-detected set to obtain a power equipment fault traceability result. According to the invention, more efficient and accurate power equipment fault traceability is realized, and a more reliable traceability result is provided.

Images