Time–frequency manifold correlation matching for periodic fault identification in rotating machines

For rotating machines, the localized faults of key components generally represent as periodic transient impulses in vibration signals. The existence of background noise will corrupt transient impulses in practice, and will thus increase the difficulty to identify specific faults. This paper combines the concepts of time–frequency manifold (TFM) and image template matching, and proposes a novel TFM correlation matching method to enhance identification of the periodic faults. This method is to conduct correlation matching of a vibration signal in the time–frequency domain by using the TFM with a short duration as a template. By this method, the time–frequency distribution (TFD) of a vibration signal is firstly achieved by the Smoothed Pseudo-Wigner–Ville distribution (SPWVD) method. Then the TFM template is learned to do correlation matching with the TFD of the analyzed signal. Finally, the ridge is extracted from the correlation matching image and the ridge coefficients are analyzed for periodic fault identification. The proposed method takes advantages of the TFM in noise suppression and template matching in object enhancement, and can enhance the fault impulses of interest in a unified scale. The novel method is verified to be superior to traditional enveloping method with providing smoother and clearer fault impulse component via applications to gearbox fault detection and bearing defect identification.