Multi-classifier information fusion partial discharge diagnostic method

Abstract

A multi-classifier information fusion partial discharge diagnostic method comprises the steps of (1) signal acquisition, namely partial discharge signals of electrical equipment are acquired through a sensor, (2) signal preprocessing, (3) discharge feature extraction, namely extraction of pulse features and statistic features, (4) classifier recognition, namely extracted feature parameters are used as input vectors, and a neural network classifier, a fuzzy reasoning classifier and a distance discriminant classifier respectively give out confidence coefficient results of five discharge types of corona discharge, suspension electrode discharge, free particle discharge, air gap discharge and creeping discharge, (5) possibility judgment and (6) eventual confidence coefficient calculation. According to the multi-classifier information fusion partial discharge diagnostic method, the discharge types can be pointed out, the specific confidence coefficients can be given out, so that a result is more accurate and comprehensive. The multi-classifier information fusion partial discharge diagnostic method can be further popularized and applied to the fields of fault diagnosis, mode recognition and the like, and has broad market prospects and application values.

Description

technical field [0001] The invention relates to partial discharge detection technology in the field of high voltage and insulation technology, specifically a partial discharge diagnosis method based on information fusion of multiple classifiers, which belongs to a core technology in the partial discharge diagnosis process and is used in various military or It can be widely used in civilian detection systems. technical background [0002] Partial discharge detection is an important means to monitor the insulation state of large power equipment. Different insulation defects and discharge types have very different destructive effects on insulation. Therefore, effective identification of partial discharge signals is of great significance for timely detection of hidden dangers of insulation faults, judgment of fault types, prediction of equipment life, and ensuring reliable operation of equipment. . In this field, many scholars have done a lot of in-depth research in recent yea...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the deficiency of the above-mentioned single classifier for partial discharge diagnosis, and provide a method for partial discharge diagnosis of multi-classifier information fusion, based on multiple The classification result and its confidence degree of the classifier are integrated according to certain rules, and finally a credible diagnostic conclusion is given, which includes two aspects of partial discharge type and its confidence degree

Images