跳到主要导航 跳到搜索 跳到主要内容

Deep Degradation Feature Extraction and RUL Estimation for Switching Power Unit

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

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.

源语言英语
主期刊名2019 Prognostics and System Health Management Conference, PHAI-Qingdao 2019
编辑Wei Guo, Steven Li, Qiang Miao
出版商Institute of Electrical and Electronics Engineers Inc.
ISBN(电子版)9781728108612
DOI
出版状态已出版 - 10月 2019
活动10th Prognostics and System Health Management Conference, PHM-Qingdao 2019 - Qingdao, 中国
期限: 25 10月 201927 10月 2019

出版系列

姓名2019 Prognostics and System Health Management Conference, PHM-Qingdao 2019

会议

会议10th Prognostics and System Health Management Conference, PHM-Qingdao 2019
国家/地区中国
Qingdao
时期25/10/1927/10/19

指纹

探究 'Deep Degradation Feature Extraction and RUL Estimation for Switching Power Unit' 的科研主题。它们共同构成独一无二的指纹。

引用此