Wavelet packet feature extraction for vibration monitoring and fault diagnosis of turbo-generator

Condition monitoring of turbo-generator 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 global basis. The wavelet packet transform (WPT) is introduced as an alternative means of extracting time-frequency information from vibration signature. 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. The extracted reduced dimensional feature vector is then used for fault diagnosis. In this paper, we put forward a new method based on WPT for vibration monitoring and fault diagnosis of turbo-generator. The method is mainly based on WPT power spectrum density (PSD) analysis. Extensive experiments on rotor laboratorial platform show that the implementation meets the requirement of vibration signals analysis. It is feasible and effective.