Estimation of Bearing Remaining Useful Life Based on Multiscale Convolutional Neural Network

TLDR

Bearing remaining useful life prediction is essential for safe machinery operation and minimizing maintenance costs. This study introduces a deep feature learning approach for RUL estimation that combines time‑frequency representation and a multiscale convolutional neural network. Time‑series degradation signals are transformed into wavelet‑based time‑frequency representations, reduced in dimensionality by bilinear interpolation, and fed into an MSCNN that simultaneously captures global and local features to automatically learn salient RUL indicators. Experimental results demonstrate that the proposed method outperforms traditional data‑driven and CNN‑based feature extraction techniques, achieving higher prediction accuracy.

Abstract

Bearing remaining useful life (RUL) prediction plays a crucial role in guaranteeing safe operation of machinery and reducing maintenance loss. In this paper, we present a new deep feature learning method for RUL estimation approach through time frequency representation (TFR) and multiscale convolutional neural network (MSCNN). TFR can reveal nonstationary property of a bearing degradation signal effectively. After acquiring time-series degradation signals, we get TFRs, which contain plenty of useful information using wavelet transform. Owing to high dimensionality, the size of these TFRs is reduced by bilinear interpolation, which are further regarded as inputs for deep learning models. Here, we introduce an MSCNN model structure, which keeps the global and local information synchronously compared to a traditional convolutional neural network (CNN). The salient features, which contribute for RUL estimation, can be learned automatically by MSCNN. The effectiveness of the presented method is validated by the experiment data. Compared to traditional data-driven and different CNN-based feature extraction methods, the proposed method shows enhanced performance in the prediction accuracy.