Ultrasonic partial discharge signal feature extraction method and related equipment

Abstract

The invention discloses an ultrasonic partial discharge signal feature extraction method, an ultrasonic partial discharge signal feature extraction device, electronic equipment and a computer-readablestorage medium. The feature extraction method comprises the steps of: determining variational mode decomposed penalty parameters and the mode component number by calling a pre-set optimization algorithm; according to the penalty parameters and the mode component number, performing variational mode decomposition on ultrasonic partial discharge signals; performing hilbert transform on various modecomponents generated by variational mode decomposition, so that instantaneous frequencies are generated; and forming feature components of the ultrasonic partial discharge signals by the various instantaneous frequencies. According to the ultrasonic partial discharge signal feature extraction method and the related equipment in the invention, variational mode decomposition on the ultrasonic partial discharge signals is carried out; the ultrasonic partial discharge signals are decomposed into several mode components having a certain centre frequency, so that feature extraction is carried out; influence of residual noise and redundant modes is effectively reduced; the mode aliasing problem is overcome; and furthermore, parameter optimizing is carried out in advance, so that the signal analysis precision can be further increased effectively.

Description

technical field [0001] The present application relates to the technical field of ultrasonic detection, in particular to a feature extraction method, device, electronic equipment and computer-readable storage medium of ultrasonic partial discharge signals. Background technique [0002] In recent years, the development of ultrasonic detection technology has become more and more mature, and has been widely used in partial discharge (ie partial discharge) signal detection of electrical equipment such as transformers and high-voltage switchgear. [0003] Usually, partial discharge signals are mainly generated by phenomena such as corona discharge, creeping discharge or arc discharge of electrical equipment. Ultrasonic partial discharge signal detection first needs to collect the ultrasonic signal on site, and then perform feature extraction through signal analysis and other processes, which is used to judge the type of partial discharge and even locate the source of partial disch...

AI Technical Summary

Problems solved by technology

However, the feature extraction methods for ultrasonic partial discharge signals in the prior art have certain limitations, resulting in low accuracy of signal analysis results

Images