Neural network autoregressive modeling of vibrations for condition monitoring of rotating shafts

Artificial neural networks provide a means of capturing stationary statistical information about machine vibrations in the form of nonlinear autoregressive models. These models can be used as one step ahead predictors allowing comparison of signals for the purposes of fault detection and diagnosis. From the prediction error, features can be extracted and used to determine the machine's condition. In this paper, the higher-order statistics of the error time series are extracted and used to compare vibration time series. Vibration data, from a rotating shaft placed under different fault conditions are used for training and testing models. A statistical approach which assesses the probability that a fault has occurred is used, and results indicate that this approach could be used to diagnose known conditions and even detect unknown faults.