Angle-Domain Feature Mode Decomposition for Fault Diagnosis Under Speed-Varying Condition

It is significant for the machinery fault diagnosis to extract the fault information from the multicomponent vibration signal. Feature mode decomposition (FMD), which can accurately separate the fault feature, has been widely verified and accepted in this field; however, it greatly limited its application that FMD cannot be directly applied under the speed-varying condition (SVC) since its decomposition objective, correlated kurtosis (CK), is only defined in the stationary condition. Motivated by this, a new angle-domain feature mode decomposition (AFMD) is tailored under the SVC. In this article, average kurtosis (AK), which inherently highlights the periodic impulses from the angle domain is first used as the decomposition objective. Subsequently, a finite impulse response (FIR) filter bank initialized by the Hanning window is designed to provide a-direction for the decomposition. Then, the adaptive filtering decomposition is iteratively performed constrained by the objective AK. Finally, the redundant and mixing modes are removed by the mode dropout strategy with correlation coefficient (CC) as its criterion. The simulations and experiments validate the effectiveness of the proposed method AFMD under SVC and its success in extending FMD to the SVC.