Machine fault diagnosis using a cluster-based wavelet feature extraction and probabilistic neural networks

In this paper, a cluster-based feature extraction from the coefficients of a discrete wavelet transform and probabilistic neural networks are proposed for machine fault diagnosis. The proposed approach first divides the matrix of wavelet coefficients into clusters, which are centered around the discriminative coefficient positions identified by an unsupervised procedure, based on the entropy value of coefficients from a set of representative signals. The features that contain the informative attributes of the signals are computed from the energy content of the obtained clusters. Then, machine faults are diagnosed based on these feature vectors using a probabilistic neural network. The experimental results from the application on bearing fault diagnosis have shown that the proposed approach is able to effectively extract important intrinsic information content of the test signals and increase the overall fault diagnostic accuracy, as compared to conventional methods.