A New Gear Fault Recognition Method Using Muwd Sample Entropy and Grey Incidence

In this paper, we propose a new gear fault recognition method by using morphological undecimated wavelet decomposition (MUWD), sample entropy and grey incidence. MUWD possesses both the characteristic of morphological filter in morphology and multi-resolution in wavelet transform. Then we develop multi-scale MUWD based on the characteristic of impulse feature extraction in difference morphological filter. At first, we use multi-scale MUWD to process different gear fault signals in five levels, signal length is maintained invariable and information loss could be avoided in MUWD, simulation example tests the good effectiveness of its denoising capacity. Second, we calculate the sample entropy of each level. Different fault type corresponds with different sample entropy. In the end, we serve sample entropy as the feature vectors and calculate the grey incidence of different gear vibration signals to identify the fault pattern and condition. Practical example shows that the high efficiency of the proposed method. It is suitable for condition monitoring and fault diagnosis of gear.