Skip to main content

ORIGINAL RESEARCH article

Front. Phys.
Sec. Interdisciplinary Physics
Volume 12 - 2024 | doi: 10.3389/fphy.2024.1432783
This article is part of the Research Topic Wave Propagation in Complex Environments View all 13 articles

Research on the Identification Method of Cable Insulation Defects Based on Markov Transition Fields and Transformer Networks

Provisionally accepted
Ning Zhao Ning Zhao 1,2*Yongyi Fang Yongyi Fang 2Siying Wang Siying Wang 2Qian Li Qian Li 2Xiaonan Wang Xiaonan Wang 2Chi Feng Chi Feng 2
  • 1 Other, China, China
  • 2 State Grid Shijiazhuang Electric Power Supply Company, Shijiazhuang, Hebei Province, China

The final, formatted version of the article will be published soon.

    To enhance the accuracy of cable insulation defect identification and the robustness of the algorithm against noise, this paper proposes a method for identifying cable insulation defects based on the Markov transition field (MTF) and the Transformer network. Firstly, the algorithm performs modal transformation on the time series data acquired by the ultrasonic probe through MTF, generating corresponding images. Secondly, these image data are fed into a pre-trained Transformer network to achieve automated feature extraction. Then, a multi-head attention mechanism is introduced, which can assign weights to the features extracted by the Transformer network, thereby emphasizing the most critical information for the identification task Ultimately, more accurate defect identification is achieved based on the weighted features. Compared with traditional image processing and recognition methods, the method proposed in this paper demonstrates higher accuracy and stronger noise resistance in the task of cable insulation defect identification.

    Keywords: Cable, Insulation defect, Markov transition field, Transformer networks, Multi-head attention mechanism

    Received: 14 May 2024; Accepted: 19 Jul 2024.

    Copyright: © 2024 Zhao, Fang, Wang, Li, Wang and Feng. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence: Ning Zhao, Other, China, China

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.