TY - GEN
T1 - An Ensemble Adaptive Deep Learning Method for High-Voltage Circuit Breaker Mechanical Fault Diagnosis
AU - Lu, Lei
AU - Yan, Jing
AU - Wang, Yanxin
AU - Ye, Xinyu
AU - Yang, Fan
N1 - Publisher Copyright:
© 2023, Beijing Paike Culture Commu. Co., Ltd.
PY - 2023
Y1 - 2023
N2 - In recent years, data-driven intelligent diagnosis methods have made rapid progress in the field of high-voltage circuit breaker mechanical fault diagnosis. However, most of the existing fault diagnosis methods are based on a single signal, which cannot make full use of the state information of high-voltage circuit breakers. To address this problem, this paper proposes a novel ensemble one-dimensional convolutional neural network (1DECNN) for the intelligent mechanical faults diagnosis of high-voltage circuit breakers. Firstly, multiple sensors are used to obtain the vibration signal, breaking coil current signal and moving contact travel signal form high-voltage circuit breaker. Then, a multi-resolution CNN is proposed to realize multi-sensor information fusion diagnosis. The proposed method extracts the fault characteristics of the characterized high-voltage circuit breaker with a 1D CNN, and uses ensemble learning to realize comprehensive mechanical fault diagnosis with multiple data. The experimental results show that the 1DECNN can achieve high-precision robust mechanical faults diagnosis of high-voltage circuit breakers and effectively fuse the different information compared with the traditional method.
AB - In recent years, data-driven intelligent diagnosis methods have made rapid progress in the field of high-voltage circuit breaker mechanical fault diagnosis. However, most of the existing fault diagnosis methods are based on a single signal, which cannot make full use of the state information of high-voltage circuit breakers. To address this problem, this paper proposes a novel ensemble one-dimensional convolutional neural network (1DECNN) for the intelligent mechanical faults diagnosis of high-voltage circuit breakers. Firstly, multiple sensors are used to obtain the vibration signal, breaking coil current signal and moving contact travel signal form high-voltage circuit breaker. Then, a multi-resolution CNN is proposed to realize multi-sensor information fusion diagnosis. The proposed method extracts the fault characteristics of the characterized high-voltage circuit breaker with a 1D CNN, and uses ensemble learning to realize comprehensive mechanical fault diagnosis with multiple data. The experimental results show that the 1DECNN can achieve high-precision robust mechanical faults diagnosis of high-voltage circuit breakers and effectively fuse the different information compared with the traditional method.
KW - Ensemble learning
KW - High-voltage circuit breakers
KW - Intelligent fault diagnostics
KW - One-dimensional convolutional neural network
UR - https://www.scopus.com/pages/publications/85152619277
U2 - 10.1007/978-981-99-0357-3_79
DO - 10.1007/978-981-99-0357-3_79
M3 - 会议稿件
AN - SCOPUS:85152619277
SN - 9789819903566
T3 - Lecture Notes in Electrical Engineering
SP - 772
EP - 779
BT - The Proceedings of the 17th Annual Conference of China Electrotechnical Society
A2 - Yang, Qingxin
A2 - Li, Jian
A2 - Xie, Kaigui
A2 - Hu, Jianlin
PB - Springer Science and Business Media Deutschland GmbH
T2 - 17th Annual Conference of China Electrotechnical Society, CES 2022
Y2 - 17 September 2022 through 18 September 2022
ER -