Application of the Laplace-Wavelet Combined With ANN for Rolling Bearing Fault Diagnosis

摘要

A new technique fur automated detection and diagnosis of rolling bearing conditions is proposed. The time-domain vibration siguals of rolling bearing with different fault conditions are processed using Laplace wavelet trnnsform for features extraction. The extracted features in time and frequency domain of the wavelet transform coefficients are applied as input vectors to artificial neural networks (ANN) for rolling bearing fault classification. The Laplace-Wavelet shape and the ANN classifier parameters are optimized using a genetic algorithm. To speed up the computation and increase the accuracy of classification process the predominate wavelet transform scales are used for features extraction. The results show the effectiveness of the proposed technique for bearing conditions identification with very high success rate using minimum input features.