• HOME
  • About Journal
    • Historical evolution
    • Journal Honors
  • Editorial Board
    • Members of Committee
    • Director of the Committee
    • President and Editor in chief
  • Submission Guide
    • Instructions for Authors
    • Manuscript Processing Flow
    • Model Text
    • Procedures for Submission
  • Academic Influence
  • Open Access
  • Ethics&Policies
    • Publication Ethics Statement
    • Peer Review Process
    • Academic Misconduct Identification and Treatment
    • Advertising and Marketing
    • Correction and Retraction
    • Conflict of Interest
    • Authorship & Copyright
  • Contact Us
  • Chinese
Site search        
文章摘要
LLC串联谐振式开关电源MOSFET故障诊断研究
Research on fault diagnosis of LLC series resonant switching power supply MOSFET
Received:September 04, 2018  Revised:September 04, 2018
DOI:10.19753/j.issn1001-1390.2020.02.023
中文关键词: 串联谐振  开关电源  MOSFET  故障诊断  支持向量机
英文关键词: series resonant, switching power supply, MOSFET, fault diagnosis, support vector machine
基金项目:湖北省自然科学基金资助项目
Author NameAffiliationE-mail
Liu Ting* Wuhan Second Institute of ship design and research nataly2010@163.com 
Wen Xinyi Wuhan Second Institute of ship design and research 624365465@qq.com 
Chen Gang Wuhan Second Institute of ship design and research 1012121880@qq.com 
Wang Suyong Wuhan Second Institute of ship design and research djkwsy@163.com 
Liu Yuxi Wuhan Second Institute of ship design and research 3438097950@qq.com 
Zhang Xiantao Wuhan Second Institute of ship design and research 158491788@qq.com 
Hits: 2142
Download times: 906
中文摘要:
      针对在LLC串联谐振式开关电源中起关键作用但故障率高的MOSFET,本文基于Cadence/OrCAD PSpice软件环境,分析MOSFET的故障失效模式及其在电路中造成的影响,以电路功能模块之间的关键输入/输出为故障特征提取点,建立故障特征集,并分别采用基于K-CV优化的支持向量机算法和基于GA优化的BP神经网络算法。诊断结果表明,所选择的测点数据基本保留电路中MOSFET的故障特征,两种算法均具备较高的诊断准确率。本文提出的诊断策略具有实际可操作性强、运算简洁的特点。
英文摘要:
      According to MOSFET in the LLC series resonant switching power supply which plays a key role but has a high failure rate, the failure modes of MOSFET and their influences on the circuit is analyzed based on the Cadence/OrCAD PSpice environment in this paper, and the important input and output between the functional module of the circuit is selected as a fault feature extraction point, after which, the fault feature set is established, a support vector machine algorithm based on K-CV optimization and a neutral network algorithm based on GA optimization is applied to fault identification. The diagnostic results indicate that data of the selected point is basically retain fault characteristics of MOSFET in the circuit, both algorithms have high accuracy of fault diagnosis. The diagnostic strategy proposed in this paper has the characteristics of practical operability and simple operation.
View Full Text   View/Add Comment  Download reader
Close
  • Home
  • About Journal
    • Historical evolution
    • Journal Honors
  • Editorial Board
    • Members of Committee
    • Director of the Committee
    • President and Editor in chief
  • Submission Guide
    • Instructions for Authors
    • Manuscript Processing Flow
    • Model Text
    • Procedures for Submission
  • Academic Influence
  • Open Access
  • Ethics&Policies
    • Publication Ethics Statement
    • Peer Review Process
    • Academic Misconduct Identification and Treatment
    • Advertising and Marketing
    • Correction and Retraction
    • Conflict of Interest
    • Authorship & Copyright
  • Contact Us
  • 中文页面
Address: No.2000, Chuangxin Road, Songbei District, Harbin, China    Zip code: 150028
E-mail: dcyb@vip.163.com    Telephone: 0451-86611021
© 2012 Electrical Measurement & Instrumentation
黑ICP备11006624号-1
Support:Beijing Qinyun Technology Development Co., Ltd