Non-parametric Ensemble Empirical Mode Decomposition for extracting weak features to identify bearing defects

TL;DR

This paper introduces a non-parametric ensemble empirical mode decomposition method that effectively extracts weak features for bearing defect detection without needing to predefine noise levels or ensemble counts.

Contribution

The proposed NPCEEMD method reduces mode mixing and eliminates the need for parameter tuning in signal decomposition for bearing defect diagnosis.

Findings

NPCEEMD shows less mode mixing than existing methods.

The method successfully identifies bearing defects from experimental data.

It simplifies the decomposition process by removing parameter dependency.

Abstract

A non-parametric complementary ensemble empirical mode decomposition (NPCEEMD) is proposed for identifying bearing defects using weak features. NPCEEMD is non-parametric because, unlike existing decomposition methods such as ensemble empirical mode decomposition, it does not require defining the ideal SNR of noise and the number of ensembles, every time while processing the signals. The simulation results show that mode mixing in NPCEEMD is less than the existing decomposition methods. After conducting in-depth simulation analysis, the proposed method is applied to experimental data. The proposed NPCEEMD method works in following steps. First raw signal is obtained. Second, the obtained signal is decomposed. Then, the mutual information (MI) of the raw signal with NPCEEMD-generated IMFs is computed. Further IMFs with MI above 0.1 are selected and combined to form a resulting signal. Finally, envelope spectrum of resulting signal is computed to confirm the presence of defect.