A Data-driven Deep Learning Approach for Remaining Useful Life of Rolling Bearings

Abstract

The bearing is a commonly used rotating element, and its condition significantly impacts the operation and maintenance of machinery. Therefore, accurately predicting the Remaining Useful Life (RUL) of bearings holds great importance. Deep learning has made significant progress in RUL prediction. This study presents a Deep Learning (DL) model incorporating a Convolution Neural Network (CNN), Long Short-Term Memory (LSTM), and attention mechanism to enhance RUL prediction accuracy for rolling bearings. Initially, time domain input data is processed by the CNN for feature extraction. Subsequently, two LSTM layers are utilized to capture intricate temporal relationships and create more abstract data representations, followed by the incorporation of an attention mechanism to align input and output sequences based on the content or semantics of the input sequence. Ultimately, the final predictions are made through a Fully Connected (FC) layer. The effectiveness of the proposed model is evaluated using the IEEE PHM 2012 Challenge dataset, and its performance is compared to various deep learning models to showcase its efficacy. Experimental results indicate that the suggested CNN-ALSTM model is a reliable choice for predicting the RUL of rolling bearings, outperforming all other models considered.