Remaining useful life prediction of rolling bearings based on refined composite multi-scale attention entropy and dispersion entropy

TL;DR

The paper tackles RUL prediction for rolling bearings using vibration signals by addressing the limitations of traditional features in capturing degradation. It introduces Fusion of Multi-Modal Multi-Scale Entropy (FMME), combining Refined Composite Multi-Scale Attention Entropy (RCMATE) and Refined Composite Multi-Scale Fluctuation Dispersion Entropy (RCMFDE) computed on EMD-derived modal components and fused with Laplacian Eigenmap to yield robust health indicators. A degradation feature evaluation metric MCR guides scale selection, enabling reliable fusion of multi-modal features into four degradation sequences from horizontal and vertical channels. Experimental results on IEEE PHM 2012 data under three operating conditions demonstrate superior RUL prediction performance and robustness over traditional features and baseline methods, highlighting the practical impact for condition-based maintenance of rotating machinery.

Abstract

Remaining useful life (RUL) prediction based on vibration signals is crucial for ensuring the safe operation and effective health management of rotating machinery. Existing studies often extract health indicators (HI) from time domain and frequency domain features to analyze complex vibration signals, but these features may not accurately capture the degradation process. In this study, we propose a degradation feature extraction method called Fusion of Multi-Modal Multi-Scale Entropy (FMME), which utilizes multi-modal Refined Composite Multi-scale Attention Entropy (RCMATE) and Fluctuation Dispersion Entropy (RCMFDE), to solve the problem that the existing degradation features cannot accurately reflect the degradation process. Firstly, the Empirical Mode Decomposition (EMD) is employed to decompose the dual-channel vibration signals of bearings into multiple modals. The main modals are then selected for further analysis. The subsequent step involves the extraction of RCMATE and RCMFDE from each modal, followed by wavelet denoising. Next, a novel metric is proposed to evaluate the quality of degradation features. The attention entropy and dispersion entropy of the optimal scales under different modals are fused using Laplacian Eigenmap (LE) to obtain the health indicators. Finally, RUL prediction is performed through the similarity of health indicators between fault samples and bearings to be predicted. Experimental results demonstrate that the proposed method yields favorable outcomes across diverse operating conditions.

Figures (9)

• Figure 1: Schematic of attention entropy.
• Figure 2: The illustration of our FMME method for extracting final degradation features.
• Figure 3: Comparison of good and poor features.
• Figure 4: Schematic of bearing failure points.
• Figure 5: IEEE PHM 2012 Challenge bearing accelerated degradation experimental platform.