Remaining Useful Life Prediction of Rolling Bearings Based on Multi-Scale Attention Residual Network

Abstract

The remaining useful life (RUL) prediction of rolling bearings based on vibration signals has attracted widespread attention. It is not satisfactory to adopt information theory (such as information entropy) to realize RUL prediction for complex vibration signals. Recent research has used more deep learning methods based on the automatic extraction of feature information to replace traditional methods (such as information theory or signal processing) to obtain higher prediction accuracy. Convolutional neural networks (CNNs) based on multi-scale information extraction have demonstrated promising effectiveness. However, the existing multi-scale methods significantly increase the number of model parameters and lack efficient learning mechanisms to distinguish the importance of different scale information. To deal with the issue, the authors of this paper developed a novel feature reuse multi-scale attention residual network (FRMARNet) for the RUL prediction of rolling bearings. Firstly, a cross-channel maximum pooling layer was designed to automatically select the more important information. Secondly, a lightweight feature reuse multi-scale attention unit was developed to extract the multi-scale degradation information in the vibration signals and recalibrate the multi-scale information. Then, end-to-end mapping between the vibration signal and the RUL was established. Finally, extensive experiments were used to demonstrate that the proposed FRMARNet model can improve prediction accuracy while reducing the number of model parameters, and it outperformed other state-of-the-art methods.

The Prediction of the Remaining Useful Life of Rotating Machinery Based on an Adaptive Maximum Second-Order Cyclostationarity Blind Deconvolution and a Convolutional LSTM Autoencoder

“…A convolutional neural network (CNN) utilizes neural networks to improve the prognostic recognition and can automatically learn the remaining useful life (RUL) estimation of rotating machinery. However, a CNN has the disadvantages of overfitting and exploding gradients that decrease the prediction performance [ 10 , 11 , 12 , 13 , 14 ]. For better prognostics and the prognostics and health management (PHM) of the bearing degradation, an LSTM can use the advantages of its architecture for a long memory of bearing degradation and can address the limits and problems for the prediction of the RUL to achieve superior forecasting.…”

Rolling Bearing Residual Useful Life Prediction Model Based on the Particle Swarm Optimization-Optimized Fusion of Convolutional Neural Network and Bidirectional Long–Short-Term Memory–Multihead Self-Attention

“…This method adopts manual feature extraction, which is complicated in modeling, and, consequently, a few of the features that are manually extracted can be easily ignored. Song et al [17] proposed the use of a multi-scale a ention residual network for predicting rolling bearings' RUL. Qi et al [18] researched anomaly detection-and multistep estimation-based techniques for the prediction of the RUL of rolling bearings, which increased the accuracy of RUL prediction to some extent.…”