Wavelet support vector machine and multi-layer perceptron neural network with continues wavelet transform for fault diagnosis of gearboxes

Abstract

In this paper, a method based on wavelet support vector machine (SVM) with OAOT algorithm, multi-layer perceptron (MLP) and Morlet wavelet transform were designed to diagnose different types of fault in a gearbox. A scale selection criterion based on the maximum relative energy to Shannon entropy ratio is proposed to determine optimal decomposition scale for wavelet analysis. Moreover, energy and entropy of the wavelet coefficients are used as two new features along with other statistical parameters as input of the classifier. The results showed that the WSVM identified the fault categories of gearbox more accurately as compared to the MLP network.