Gear fault diagnosis based on Gaussian correlation of vibrations signals and wavelet coefficients

TL;DR

This paper introduces a novel feature extraction method for non-stationary vibration signals using Gaussian correlation of wavelet coefficients, enhancing gearbox fault diagnosis accuracy.

Contribution

The paper proposes a new feature extraction technique combining wavelet analysis, Gaussian correlation, and EMD, improving fault classification without extra feature selection.

Findings

Features effectively classify faults with high accuracy.

EMD can improve or degrade feature quality.

Method outperforms traditional feature extraction approaches.

Abstract

The features of non-stationary multi-component signals are often difficult to be extracted for expert systems. In this paper, a new method for feature extraction that is based on maximization of local Gaussian correlation function of wavelet coefficients and signal is presented. The effect of empirical mode decomposition (EMD) to decompose multi-component signals to intrinsic mode functions (IMFs), before using of local Gaussian correlation is discussed. The experimental vibration signals from two gearbox systems are used to show the efficiency of the presented method. Linear support vector machine (SVM) is utilized to classify feature sets extracted with the presented method. The obtained results show that the features extracted in this method have excellent ability to classify faults without any additional feature selection; it is also shown that EMD can improve or degrade features according to the utilized feature reduction method.