Dual residual attention network for remaining useful life prediction of bearings

• Published in: Measurement : journal of the International Measurement Confederation 2022-08, Vol.199, p.111424, Article 111424
• Main Authors: Jiang, Guoqian, Zhou, Wenda, Chen, Qi, He, Qun, Xie, Ping
• Format: Article
• Language: English
• Subjects: Bearing degradation; Deep learning; Dual residual attention; Hybrid dilated convolution; Remaining useful life prediction
• ISSN: 0263-2241; 1873-412X
• DOI: 10.1016/j.measurement.2022.111424

Rolling bearing is a critical component of rotating machines and it is indispensable to accurately predict the remaining useful life (RUL) of bearings to realize predictive maintenance. To extract degradation-sensitive features from complex vibration signals, this paper proposes a new dual residual attention network (DRAN) to improve prediction performance. A frequency band residual attention (FBRA) block is first designed to automatically discover important frequency bands related to bearing degradation. Then, a spatio-temporal residual attention (STRA) block is proposed to sequentially learn high-level representations from frequency and temporal dimensions with a hybrid dilated convolution neural network (HDCNN) and then adaptively identify important features contributing to bearing RUL prediction via a residual attention mechanism. Finally, a weighted RUL estimation block is used to smooth the predicted RUL and provide a more reliable prediction. Experimental results on a public bearing dataset demonstrate the superiority of our DRAN against several state-of-the-art methods. •A new DRAN model is proposed to predict RUL of bearings.•The proposed RA can integrate the original information and the weighted information.•FBRA is designed to identify important frequency features.•HDCNN is used to learn feature information across frequency bands with different dilation rates.•STRA block can lean sensitive features related to bearing degradation.