Smart fault detection of HTS coils using artificial intelligence techniques for large-scale superconducting electric transport applications

Yazdani-Asrami, M. , Fang, L., Pei, X. and Song, W. (2023) Smart fault detection of HTS coils using artificial intelligence techniques for large-scale superconducting electric transport applications. Superconductor Science and Technology, 36(8), 085021. (doi: 10.1088/1361-6668/ace3fb)

Abstract

The superconducting coils in winding of large-scale devices work in kind of harsh environment from both temperature – considering liquid hydrogen or gashouse helium as coolant – (thermal stress) and electro-magneto-mechanical stress, point of views. Reliable operation of the coils in winding is of vital importance for reliability of superconducting device and safety of the application that the device is used in. If superconducting coil confronts with a fault or an abnormal operation in laboratory-level operation, it is straightforward to test the coil by measuring its critical current, AC loss, and etc, to find whether it is damaged or not. However, there would be an urgent need to have faster and more intelligent approaches with a possibility to become fully autonomous and real-time, in large-scale power applications especially in sensitive applications such as in future cryo-electric aircraft, or in fusion industry. To reach such intelligent fault-finding approaches, artificial intelligence-based techniques have been foreseen to be a promising solution. In this paper, we have developed an intelligent fault detection technique for finding a faulty superconducting coil, named the frequency-temporal classification method. This method has two main steps: first, this paper utilizes the Discrete Fourier Transform and Independent Component Analysis to convert measurement signals of the healthy and faulty coils from 1) the time-series domain to the frequency domain; and 2) into time-series source signals. Second, this paper trains the support-vector machine using the derived frequency-components. This trained model is then used for making fault detection for other superconducting coils with voltage signal data only. The developed technique can classify a fault with 99.2% accuracy. The results of proposed method in this paper has been compared with some other techniques to prove its effectiveness.

• Item Type: Articles
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Yazdani-Asrami, Dr Mohammad and Song, Dr Wenjuan
• Authors: Yazdani-Asrami, M., Fang, L., Pei, X., and Song, W.
• College/School: College of Science and Engineering > School of Engineering > Autonomous Systems and Connectivity
• Journal Name: Superconductor Science and Technology
• Publisher: IOP Publishing
• ISSN: 0953-2048
• ISSN (Online): 1361-6668
• Published Online: 04 July 2023
• Copyright Holders: Copyright © 2023 The Authors
• First Published: First published in Superconductor Science and Technology 36(8): 085021
• Publisher Policy: Reproduced under a Creative Commons License