Wavelet packet feature extraction for vibration monitoring

TLDR

Condition monitoring of dynamic systems typically relies on Fourier‑based analysis of vibration signals, but this approach poorly represents time‑localized signals, making pattern detection difficult. The study introduces the wavelet packet transform (WPT) as an alternative to extract time‑frequency information from vibration signatures. WPT coefficients provide arbitrary time‑frequency resolution, and after statistical feature selection discarding low‑discriminant components, the resulting reduced feature vector is input to a neural‑network classifier. This approach significantly shortens neural‑network training time and enhances its generalization capability.

Abstract

Condition monitoring of dynamic systems based on vibration signatures has generally relied upon Fourier-based analysis as a means of translating vibration signals in the time domain into the frequency domain. However, Fourier analysis provided a poor representation of signals well localized in time. In this case, it is difficult to detect and identify the signal pattern from the expansion coefficients because the information is diluted across the whole basis. The wavelet packet transform (WPT) is introduced as an alternative means of extracting time-frequency information from vibration signatures. The resulting WPT coefficients provide one with arbitrary time-frequency resolution of a signal. With the aid of statistical-based feature selection criteria, many of the feature components containing little discriminant information could be discarded, resulting in a feature subset having a reduced number of parameters without compromising the classification performance. The extracted reduced dimensional feature vector is then used as input to a neural network classifier. This significantly reduces the long training time that is often associated with the neural network classifier and improves its generalization capability.