Feature extraction techniques for ultrasonic shaft signal classification

Abstract

Discrete Wavelet Transform (DWT) coefficients of ultrasonic test signals are considered useful features for input into classifiers due to their effective time-frequency representation of non-stationary signals. However, DWT exhibits a time-variance problem that has resulted in reservations for, its wide acceptance. In this paper, a new technique to derive a preprocessing method for time-domain A-scans signal is presented. This techniques offer consistent extraction of a segment of the signal from long signals that occur in the Non Destructive Testing of shafts. We performed a comparison using artificial neural networks and evaluated classification performance of the classifier supplied with features generated by our method. We compared with other alternatives and report the results here. We established experimentally that DWT coefficients can be used as a feature extraction scheme more reliably by using our new preprocessing technique.