Fused partial discharge type identification method based on DS evidence theory

Abstract

The invention provides a fused partial discharge type identification method based on a DS evidence theory. The invention relates to the fields of power systems, deep learning technologies, image processing technologies and the like. According to the method, firstly, a convolutional neural network is utilized to input partial discharge PRPD map image features for recognition to obtain a recognition rate, then statistical features of PD signals are extracted and input into an SVM classifier to obtain classification probabilities, and finally, a DS evidence theory is utilized to perform fusion judgment of partial discharge types on the two probabilities. Compared with a traditional support vector machine (SVM) and a back propagation neural network (BPNN) algorithm, the method provided by the invention is advantaged in that the correct recognition rate is remarkably improved, the effect of improving the recognition rate of two defects with relatively high similarity is particularly obvious, and robustness is relatively good.

Description

technical field [0001] The invention relates to an SVM (Support Vector Machine, Support Vector Machine)-CNN (Convolutional Neural Networks, convolutional neural network) fusion partial discharge type identification method based on DS evidence theory, involving power systems, deep learning technology and image processing technology and other fields. Background technique [0002] Transformers are very important to the operation of power systems, and if they fail, it will cause immeasurable economic losses. Transformers are prone to insulation defects during production, manufacturing, installation, and operation, resulting in distortion of the electric field in the equipment, resulting in partial discharge (Partial Discharge, PD). There are various forms of insulation defects inside transformers. Different discharge types have certain differences in insulation degradation mechanism and manifestations, and the impact on the safe operation of equipment and the degree of damage t...

AI Technical Summary

Problems solved by technology

[0005] The present invention is aimed at the lack of prior knowledge in the existing feature extraction, the sensitivity of the initially selected partial discharge characteristic parameters is poor, and the partial discharge characteristics cannot be fully described. The existing partial discharge pattern recognition methods are limited to various shallow machine learning methods, which are difficult To overcome the limitations of the method itself, the present invention designs an SVM-CNN fusion partial discharge type identification method based on DS evidence theory

Images