Partial discharge defect type recognition method and system based on convolutional neural network

Abstract

The invention provides a partial discharge defect type recognition method and a system based on a convolutional neural network. The recognition method comprises steps: A, partial discharge signals with a known partial discharge defect type are acquired; B, a partial discharge information library is built, wherein the partial discharge information library comprises partial discharge waveform signals with a plurality of defect types and corresponding defect types; C, a convolutional neural network for mode recognition is built; D, a waveform and a corresponding defect type in the partial discharge information library are used as input to train the convolutional neural network; E, multiple times of partial discharge signals with to-be-decided defect types are acquired; and F, the partial discharge waveform data with the to-be-decided defect types are inputted to the well-trained convolutional neural network, and a defect type with the largest ratio in the output is used as the final defect type. A complex feature extraction and data reconstruction process in the traditional recognition algorithm is avoided, the defect type can be recognized more accurately, and realization is easy.

Description

technical field [0001] The invention relates to the field of transformers, in particular to a method and system for identifying partial discharge defect types of transformers based on a convolutional neural network. Background technique [0002] With the increasing miniaturization of high-voltage transformers, the internal insulation space is becoming more and more compact, and the insulating materials are often subjected to high working field strength. However, unexpected problems may occur in transformers from raw material selection, production and assembly, to transportation and installation, which may cause some hidden defects inside the transformer, such as burr tips, damage along the insulation surface, looseness of internal components or even drop. In addition, during the operation of the transformer, its oil-paper insulation and solid insulation will gradually age and deteriorate under the combined effects of electricity, heat, machinery and other environments, maki...

AI Technical Summary

Problems solved by technology

This method has problems such as high uncertainty, great influence of interference, and unclear physical meaning of the extracted mathematical features.

Although relevant scholars have done a lot of work on the identification of partial discharge defect types, and have avoided many faults in practical applications, due to the complexity of partial discharge, accurate identification of partial discharge is still an urgent problem for power equipment. big challenge puzzle

Images