TY - GEN
T1 - Remaining Useful Life Prediction Based on Multi-channel Attention Bidirectional Long Short-term Memory Network
AU - Wang, Wenting
AU - Wang, Biao
AU - Li, Naipeng
AU - Lei, Yaguo
AU - Yan, Tao
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - Recently, a large number of deep learning-based prognostics methods for machinery remaining useful life (RUL) have been proposed. And massive monitoring data is the basis of deep learning-based RUL prediction methods. However, most existing methods usually assume that the monitoring data acquired from different sensors contain similar degradation information, and they lack consideration on effectively identifying the multi-sensor degradation information, which affects the prediction performance of deep networks. To overcome the weakness, this paper proposes a multi-channel attention bidirectional long short-term memory network (MCA-BiLSTM) for RUL prediction of machinery. In MCA-BiLSTM, sensitive features are firstly extracted and selected from the monitoring data of each sensor individually. Then, multi-channel bidirectional long and short-term memory (LSTM) network is constructed with the sensitive features as the inputs. Simultaneously, time attention and channel attention are utilized to realize the adaptive information fusion. Finally, the fusion representations are input into fully connected layers to predict RUL. The effectiveness of MCA-BiLSTM is verified by multi-sensor monitoring data from life testing of milling cutters.
AB - Recently, a large number of deep learning-based prognostics methods for machinery remaining useful life (RUL) have been proposed. And massive monitoring data is the basis of deep learning-based RUL prediction methods. However, most existing methods usually assume that the monitoring data acquired from different sensors contain similar degradation information, and they lack consideration on effectively identifying the multi-sensor degradation information, which affects the prediction performance of deep networks. To overcome the weakness, this paper proposes a multi-channel attention bidirectional long short-term memory network (MCA-BiLSTM) for RUL prediction of machinery. In MCA-BiLSTM, sensitive features are firstly extracted and selected from the monitoring data of each sensor individually. Then, multi-channel bidirectional long and short-term memory (LSTM) network is constructed with the sensitive features as the inputs. Simultaneously, time attention and channel attention are utilized to realize the adaptive information fusion. Finally, the fusion representations are input into fully connected layers to predict RUL. The effectiveness of MCA-BiLSTM is verified by multi-sensor monitoring data from life testing of milling cutters.
KW - Channel attention
KW - Mechanical RUL prediction
KW - Multi-channel bidirectional LSTM
KW - Multi-sensor fusion
KW - Time attention
UR - https://www.scopus.com/pages/publications/85126187587
U2 - 10.1109/SDPC52933.2021.9563596
DO - 10.1109/SDPC52933.2021.9563596
M3 - 会议稿件
AN - SCOPUS:85126187587
T3 - Proceedings of 2021 IEEE International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2021
SP - 7
EP - 12
BT - Proceedings of 2021 IEEE International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2021
A2 - Fu, Xuyun
A2 - Deng, Shengcai
A2 - Cabrera, Diego
A2 - Zhang, Yongjian
A2 - Pu, Zhiqiang
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2021 IEEE International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2021
Y2 - 13 August 2021 through 15 August 2021
ER -