Weak fault feature extraction for polycrystalline diamond compact bit based on ensemble empirical mode decomposition and adaptive stochastic resonance

Abstract

Aiming at the problem of weak early fault signals of rotating machinery, a feature extraction method combining ensemble empirical mode decomposition (EEMD) and adaptive stochastic resonance (ASR) is proposed. First, the original vibration signal is decomposed into a series of intrinsic mode functions (IMF) through EEMD, and the main IMF components are selected using the correlation coefficient and the root mean square principle. Next, the selected components are reconstructed and used as the input of the ASR system based on the gray wolf algorithm. Finally, to evaluate the performance of ASR, a new evaluation index-weighted power spectrum kurtosis (WPSK) is defined. The results of experimental analysis on the simulation signals and vibration signals are used to verify the feasibility and superiority of the proposed method. Compared with the GA-SR, the proposed method increases the WPSK value by 34.5% when detecting weak signals of worn polycrystalline diamond compact bits.