An efficient approach to machine health diagnosis based on harmonic wavelet packet transform

This paper presents an efficient approach to machine condition monitoring and health diagnosis, based on the Discrete Harmonic Wavelet Packet Transform (DHWPT). Specifically, vibration signals measured from a bearing test bed were decomposed into a number of frequency sub-bands, and key features associated with each sub-band were selected, based on the Fisher linear discriminant criterion. The key features were then used as inputs to a neural network classifiers for assessing the system's health status. Comparing to the conventional approach where statistical parameters from raw vibration signals are used, the presented approach enables higher signal-to-noise ratios and consequently, more effective and intelligent use of the available sensor information, leading to more accurate system health evaluation.