Abstract Details
  1. Home
  2. Abstract List
  3. Abstract Details
130 / 2021-10-27 11:03:08
Data-Driven IGBT Open-Circuit Fault Diagnosis Method for the Modular Multilevel Converter
MMC,data-driven,Fault Diagnosis
AI-driven technology > Intelligent Anomaly Detection, Fault Diagnosis and Prognostics
Draft Rejected
Yang An / Xi'an University of Technology School of Electrical Engineering
Xiangdong Sun / Xi'an University of Technology
Hui Li / Xi'an University of Technology
Mengnan Zhang / Xi'an University of Technology
With the wide application of the modular multilevel converter topology in different electric power transmission fields, the key technology is to ensure its normal operation. It is composed of a large number of IGBTs, and it is and it is difficult to detect the open-circuit fault of one or more IGBTs.  With regard to this problem, a data-driven IGBT open-circuit fault diagnosis method is proposed based on the Elman neural network. The principle of fault detection is to quickly detect the fault by comparing the distance between the predicted value of bridge arm current and actual value. The Elman neural network model is established by using Matlab and the modular multilevel converter circuit model  is built by using PSIM circuit model. The simulation results denote that the proposed method can detect IGBT open-circuit fault accurately, and it is proved that the data-driven method is suitable for fault diagnosis of the modular multilevel converter.

 
Important Date

  • Conference Date

    Jul 11

    2023

    to

    Aug 18

    2023

  • Nov 10 2021

    Draft paper submission deadline

  • Dec 10 2021

    Registration deadline

  • Dec 11 2021

    Contribution Submission Deadline

Sponsored By
IEEE IAS
Organized By
IEEE IAS Student Chapter of Southwest Jiaotong University (SWJTU)
IEEE IAS Student Chapter of Huazhong University of Science and Technology (HUST)
IEEE PELS (Power Electronics Society) Student Chapter of HUST
Contact Information
Login to view full contact details
Previous Conferences