Power distribution network fault type identification method

Abstract

The invention discloses a power distribution network fault type identification method. The method comprises the following steps: constructing a fault waveform generator model and a fault waveform identifier model for providing a fault waveform fault type data set for classifier training; constructing an auxiliary classifier model, wherein the auxiliary classifier model is used for identifying whether the time sequence of the input fault waveform is a forward time sequence or an inverse time sequence; constructing a fault classifier model, wherein partial structures in the fault classifier model and the auxiliary classifier model are kept consistent; and training the fault classifier model by using the actual fault waveform-fault type data set or the artificial fault waveform fault type data set generated by the fault waveform generator so as to obtain a fault classifier.

Description

technical field [0001] The invention relates to the field of electric power technology, in particular to a method for identifying fault types of distribution networks. Background technique [0002] The distribution network is an important part of the power system. With the rapid development of the smart grid, a large number of uncertain connections of distributed power sources make the fault information of the distribution network more and more complicated, and the accurate and rapid analysis of the fault becomes more and more difficult. In order to ensure the highly intelligent operation of the distribution network, real-time monitoring of feeder operation data, timely warning of abnormal conditions, and rapid fault detection and processing are required. Among them, the identification of abnormal working conditions of the feeder is an important function of the intelligent distribution network. [0003] With the emergence of the distribution network line monitoring system, t...

AI Technical Summary

Problems solved by technology

This leads to a large number of transient recording waveforms without corresponding matching fault types. Such data cannot be used for neural network model training, resulting in insufficient training data for deep neural network models and poor training results.

Images