TY - GEN
T1 - Deep Degradation Feature Extraction and RUL Estimation for Switching Power Unit
AU - Guo, Qing
AU - Shi, Jian
AU - Wang, Shaoping
AU - Zhang, Chao
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/10
Y1 - 2019/10
N2 - Switch power unit is the power supply module for the control system of vehicles, ships and aircraft, etc. So, the safety of switching power supply determines the safety of control system. Usually, the failure of electronic devices is consider as a random event. However, the failure is caused by the degradation of internal components to the failure threshold. Therefore, it is found that the performance degradation of the main components in the switching power supply will eventually be manifested in the output ripple voltage by analyzing the output characteristics of the switching power supply. According to the performance degradation, we can divide the ripple into several stages, and get the time-frequency spectrum characteristics by the wavelet transform. Then the performance degradation model of switching power supply is obtained by using a ResNet convolution neural network with time-frequency spectrum characteristics. Finally, get the degradation state of switching power unit by ResNet model and get the remaining useful life.
AB - Switch power unit is the power supply module for the control system of vehicles, ships and aircraft, etc. So, the safety of switching power supply determines the safety of control system. Usually, the failure of electronic devices is consider as a random event. However, the failure is caused by the degradation of internal components to the failure threshold. Therefore, it is found that the performance degradation of the main components in the switching power supply will eventually be manifested in the output ripple voltage by analyzing the output characteristics of the switching power supply. According to the performance degradation, we can divide the ripple into several stages, and get the time-frequency spectrum characteristics by the wavelet transform. Then the performance degradation model of switching power supply is obtained by using a ResNet convolution neural network with time-frequency spectrum characteristics. Finally, get the degradation state of switching power unit by ResNet model and get the remaining useful life.
KW - ResNet
KW - Ripple Voltage
KW - Switching Power Unit
KW - Wavelet Transform
UR - https://www.scopus.com/pages/publications/85077987855
U2 - 10.1109/PHM-Qingdao46334.2019.8942852
DO - 10.1109/PHM-Qingdao46334.2019.8942852
M3 - 会议稿件
AN - SCOPUS:85077987855
T3 - 2019 Prognostics and System Health Management Conference, PHM-Qingdao 2019
BT - 2019 Prognostics and System Health Management Conference, PHAI-Qingdao 2019
A2 - Guo, Wei
A2 - Li, Steven
A2 - Miao, Qiang
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 10th Prognostics and System Health Management Conference, PHM-Qingdao 2019
Y2 - 25 October 2019 through 27 October 2019
ER -