Energy weighting method and its application to fault diagnosis of rolling bearing

Feature extraction of vibration signal is the key factor of machine fault diagnosis. This paper proposes a novel method of capturing shock energy based on multi-scale weight evaluation of high definition time-frequency map. Specifically, the proposed method is conducted by the following steps. First, ensemble empirical mode decomposition (EEMD) preprocessor-based Hilbert-Huang Transform (HHT) is applied to the raw signal for high definition time-frequency map acquisition. Second, an original algorithm named multi-scale binary spectrum was applied to extract impulsive energy features with different frequency characteristics. Then weights of energy can be calculated by dimensionality reduction of each binary spectrum and merged by summation after blank processing. Finally, power spectrum of compound weight of energy can reveal characteristic frequency corresponding to specific fault. In this method, the key point is enhancement of frequency spectrum using higher dimension details. The process of multi-scale binarization and weight summation were aligned and the effectiveness is verified by simulated signal processing and actual case of train bearing experiment.