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

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