a new intelligent fault diagnosis scheme based on the extraction of statistical parameters from the paving of a wavelet packet transform(WPT), a distance evaluation technique (DET) and a support vector regression (SVR)-based generic multi-class solver is proposed.The collected signals are first pre-processed by the WPT at different decomposition depths. In this paper, the wavelet packet coefficients at different decomposition depths are referred to as WPT paving.Statistical parameters are then extracted from the signals obtained via the WPT at different decomposition depths. In selecting the sensitive fault features for fault pattern expression, a DET is employed toreduce the dimensionality of the feature space.
analysing the complex signals they produce to allow judgment concerning diagnosis requires considerable expertise.
the mapping of the original signals onto the statistical parameters concerned
Fault feature extraction is the most basic of these steps and involves the mapping of
the original signals onto the statistical parameters concerned to reflect the health of the machine.