A sliding window feature extraction method for rotating machinery based on the lifting scheme

In order to diagnose and predict incipient fault of rotating machinery, a new sliding window feature extraction method based on the lifting scheme is proposed for extracting transient impacts from original signals. Firstly, a wavelet with impact characteristics is constructed by using the lifting scheme to decompose signals. Then a sliding window designed according to the revolution cycle of given rotating machinery is applied to process detail signals. By extracting modulus maxima from these windows, fault features and their locations in the original signals are revealed. An incipient impact fault caused by axis misalignment, and mass imbalance and a bush broken fault have been successfully detected by using the proposed approach.