Transformer substation secondary circuit fault positioning method and system based on graph neural network

Abstract

The invention discloses a transformer substation secondary circuit fault positioning method and system based on a graph neural network, wherein the method comprises the steps: analyzing a configuration description file of an intelligent transformer substation, storing an analysis result into a graph database, and building a corresponding relation between a physical circuit and a virtual circuit of secondary equipment; making a training set by using a historical database or a fault emergence method, and training a graph neural network model offline; finding out all associated fault equipment by using an alarm signal, preprocessing the alarm signal, judging whether the associated fault equipment forms a connected graph or not, and if the connected graph is not formed, dividing the the associated fault equipment into independent connected graphs, representing topological information and alarm signals of the independent connected graphs, and inputting the topological information and alarm signals into a trained graph neural network model; and predicting the fault type of the associated fault equipment by using the graph neural network model. According to the method, the graph neural network is used for building the fault positioning model, so that the accuracy of the model is improved under the condition that the networking mode is changed.

Description

technical field [0001] The invention relates to the technical field of intelligent substation fault location, in particular to a method and system for fault location of a secondary circuit of a substation based on a graph neural network. Background technique [0002] With the rapid development of smart substation information technology, the secondary system network of smart substations is becoming more and more complex. As the core of intelligent operation and maintenance of smart substations, fault location technology has always been a research hotspot. Due to the interconnection of secondary equipment, there is a certain correlation between the faults of the secondary circuit, and the fault location of the secondary circuit needs to locate the fault source from multiple fault events based on the relationship between the alarm signals. In the secondary system of smart substation, if a node in the network topology fails, it will often cause abnormalities in other nodes conne...

AI Technical Summary

Problems solved by technology

In the secondary system of smart substation, if a node in the network topology fails, it will often cause abnormalities in other nodes connected to it, and then generate a large number of alarms, making it difficult to judge the source of the fault

[0003] There have been studies on the fault location methods of the secondary system of smart substations. Traditional methods mainly use Petri nets and proof tables, which are difficult to deal with large-scale networks. Although traditional machine learning and deep learning methods can increase the positioning accuracy, when the secondary When the alarm signal changes or even the network structure changes in the system network, the model needs to be retrained, which is difficult to apply in actual scenarios

Images