TY - GEN
T1 - High-speed train state monitoring method with Broad Learning System
AU - Chong, Wang
AU - Jie, Liu
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/10/16
Y1 - 2020/10/16
N2 - In this paper, based on Broad Learning System (BLS) that is proposed recently, a real-time monitoring method is designed for the high-speed train (HST) braking system. Due to the high efficiency of the BLS, it is possible to update the state monitoring model in time to adapt to the changes during the HST operation. Moreover, the actual data is highly imbalanced, thus boosting ensemble learning framework is applied to optimize the model to obtain a higher generalization accuracy. In the monitoring system based on BLS integrated with boosting algorithm (noted as B-BLS), the data collected by sensors are added to the model training process in real-time, which makes the anomaly detection more suitable for the current state of the HST braking system. Compared with off-line training models, i.e. artificial neural networks and convolutional neural networks, experimental results demonstrate that the B-BLS has relatively higher adaptivity and efficiency, showing that the proposed monitoring method is feasible.
AB - In this paper, based on Broad Learning System (BLS) that is proposed recently, a real-time monitoring method is designed for the high-speed train (HST) braking system. Due to the high efficiency of the BLS, it is possible to update the state monitoring model in time to adapt to the changes during the HST operation. Moreover, the actual data is highly imbalanced, thus boosting ensemble learning framework is applied to optimize the model to obtain a higher generalization accuracy. In the monitoring system based on BLS integrated with boosting algorithm (noted as B-BLS), the data collected by sensors are added to the model training process in real-time, which makes the anomaly detection more suitable for the current state of the HST braking system. Compared with off-line training models, i.e. artificial neural networks and convolutional neural networks, experimental results demonstrate that the B-BLS has relatively higher adaptivity and efficiency, showing that the proposed monitoring method is feasible.
KW - Braking system
KW - Broad Learning System
KW - Ensemble learning
KW - High-speed train
KW - Highly imbalanced data
KW - State monitoring
UR - https://www.scopus.com/pages/publications/85099708230
U2 - 10.1109/PHM-Shanghai49105.2020.9280973
DO - 10.1109/PHM-Shanghai49105.2020.9280973
M3 - 会议稿件
AN - SCOPUS:85099708230
T3 - 2020 Global Reliability and Prognostics and Health Management, PHM-Shanghai 2020
BT - 2020 Global Reliability and Prognostics and Health Management, PHM-Shanghai 2020
A2 - Guo, Wei
A2 - Li, Steven
A2 - Miao, Qiang
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2020 Global Reliability and Prognostics and Health Management, PHM-Shanghai 2020
Y2 - 16 October 2020 through 18 October 2020
ER -