Artificial neural network based fault diagnostics of rolling element bearings using continuous wavelet transform

Any industry needs an efficient predictive plan in order to optimize the management of resources and improve the economy of the plant by reducing unnecessary costs and increasing the level of safety. A great percentage of breakdowns in productive processes are caused by bearings. This paper presents a methodology for fault diagnosis of ball bearings based on continuous wavelet transform (CWT) and artificial neural network (ANN). Three wavelet selection criteria Maximum Energy, Minimum Shannon Entropy, and Maximum Energy to Shannon Entropy ratio are used and compared to select an appropriate wavelet to extract statistical features. Total 15 feature set and 87 mother wavelet candidates were studied, and results show that complex morlet 1-1 has a best diagnosis performance based on minimum shannon entropy than the other mother wavelets and criteria. Also results show the potential application of proposed methodology with ANN for the development of on-line fault diagnosis systems for machine condition.