Wavelet transform with spectral post-processing for enhanced feature extraction [machine condition monitoring]

摘要: The quality of machine condition monitoring techniques and their applicability in the industry are determined by effectiveness efficiency, with which characteristic signal features extracted identified. Because weak amplitude short duration structural defect signals at incipient stage, it is generally difficult to extract hidden from data measured using conventional spectral techniques. A new approach, based on a combined wavelet Fourier transformation, presented this paper. Experimental studies rolling bearing localized point 0.25 mm diameter have shown that technique provides significantly improved feature extraction capability over technique.