432 / 2022-03-15 22:00:13
Research on fault characteristics and online diagnosis method of superconducting DC current limiter
Superconducting DC current limiter;,failure characteristic;,fault diagnosis
摘要录用
Yaxiong Tan / 重庆大学
Jianfa Wu / 重庆大学电气工程学院
The complex structure and operating conditions of superconducting DC current limiters(SDCCL) have caused long-term operational failures to become a concern. The fault characteristics of SDCCL are non-linear and dynamically coupled, making fault identification and location extremely difficult. In this paper, the fault characteristics of SDCCL are analyzed and a fault diagnosis method for SDCCL based on LM-BP neural networks is proposed.The article analyzes the function and working principle of SDCCL components, its weak parts leading to defects and potential failures are researched. A SDCCL fault tree model and typical failure modes are developed. Neural network algorithms are optimally designed for real-time monitoring and diagnosis of current limiter fault conditions.In this paper, typical fault correlation coupled systems are investigated. The electrical parameters (voltage, current) and non-electrical parameters (level, temperature, pressure) of SDCCL are identified as important monitoring parameters to achieve fault diagnosis. The problem of high similarity of partial fault characteristics of superconducting DC current limiters and the existence of slow convergence of BP neural networks are solved by the designed LM-BP optimisation algorithm. This paper implements the design of a fault diagnosis algorithm for superconducting DC current limiters with high accuracy and stability.

 
重要日期
  • 会议日期

    09月25日

    2022

    09月29日

    2022

  • 08月15日 2022

    提前注册日期

  • 09月10日 2022

    报告提交截止日期

  • 11月10日 2022

    注册截止日期

  • 11月30日 2022

    初稿截稿日期

  • 11月30日 2022

    终稿截稿日期

主办单位
IEEE DEIS
承办单位
Chongqing University
移动端
在手机上打开
小程序
打开微信小程序
客服
扫码或点此咨询