Rolling element bearings fault classification based on feature extraction from acceleration data and artificial neural networks

Abstract

This paper presents the development of an artificial neural network (ANN) model for rolling element bearings fault classification that uses features extracted from acceleration data collected during run-to-failure experiments. The presented approach initially employs a wavelet decomposition method for signal denoising and subsequently relies on a Fourier transform to analyse the acceleration signal in the frequency domain. Several features that correspond to the entire signal range as well as to specific frequency bands are then extracted and used as inputs in the ANN model, which is trained to identify three different operational states, namely, no fault, inner race fault and outer race fault. The developed ANN model is validated using experimental data from the publicly available dataset provided by the Center of Intelligent Maintenance Systems (IMS) of the University of Cincinnati. The results show that the trained ANN model has a classification accuracy of 90.2% in the training data and 100% in the test data.