A signal-filtering and feature-enhancement method based on ensemble local mean decomposition and adaptive morphological filtering

The bearing fault signals from the spindle motors of computer numerical control machines are complex and non-linear due to being coupled to multiple subsystems. The complexity of industrial signals, with increased industrial noise, and the difference in fault features in different life cycles and different individual signals bring great challenges for fault feature extraction. In this paper, a signal-filtering and feature-enhancement method based on an ensemble local mean decomposition and adaptive morphological filtering (ELMD-AMF) method is proposed. First, the original vibration signal of the bearing is reconstructed by ELMD to reducing interference from background noise. Next, an improved feature-enhancement process based on AMF is constructed, a particle swarm optimization with maximum-weighted spectral kurtosis as an optimization objective is used to adaptively construct the size of the structural element, and a morphology hat product operator one is adapted to extract the periodic impulse features. Finally, the effectiveness of the method is proved by using an actual three-phase induction motor matched with an NTN ceramic bearing and a FAG metal bearing, respectively. Further, compared with minimum entropy deconvolution and fast kurtogram methods, the result proves that the proposed method has better performance for both early-failure and late-failure scenarios under real-world engineering conditions.