Electric reactor fault diagnosis method

Abstract

The invention discloses an electric reactor fault diagnosis method. The method comprises the following steps: decomposing a vibration signal of an electric reactor, and obtaining M IMF components; selecting several IMF components as data source for fault feature extraction; constructing fault feature quantity through the selected IMF components; and diagnosing an electric reactor fault state in combination with a kernel clustering algorithm. The method provided by the invention can improve accuracy of fault diagnosis.

Description

technical field [0001] The invention relates to a reactor fault diagnosis method, which belongs to the field of electric equipment state detection and fault diagnosis. [0002] Background technique: [0003] Reactor is one of the key substation equipment for the normal operation of the power transmission and transformation system. Its operational reliability affects the safety and service life of the entire system. Therefore, the monitoring and fault diagnosis of reactors play a very important role in the field of mechanical fault diagnosis. [0004] In recent years, the Hilbert-Huang transform based on Empirical Mode Decomposition (EMD) proposed by Huang et al. has been widely used in the time-frequency localization analysis of mechanical vibration signals, and achieved good results. EMD is fully self-adaptive, but it lacks a mathematical theoretical basis, and has problems such as endpoint effects, over-envelope, under-envelope, and false modes, which cannot guarantee the a...

AI Technical Summary

Problems solved by technology

EMD is fully adaptive, but it lacks a mathematical theoretical basis, and has problems such as endpoint effects, over-envelope, under-envelope, and false modes, which cannot guarantee the accuracy of signal decomposition

When using FCMC to classify samples, if the difference between the samples is not large, it will lead to a decline in recognition accuracy.

Images