Scholarlink

<p>Failures such as transmission line damage and increased sag pose significant challenges to the safe operation of power grids worldwide. Real-time detection of these issues is critical for preventing power interruptions, which can have severe economic and social consequences across different regions. A joint sensing method for transmission line damage and sag based on a triboelectric nanogenerator (TENG) is proposed in this study. A sensing model, termed Grid Breakage-Cracking-Sag Detection based on Triboelectric Nanogenerator (GBCS-TENG), is developed, and a prototype is fabricated and experimentally validated. Within the specified range, the GBCS-TENG demonstrated precise measurements of both damage and sag. By utilizing a damage classification model based on a deep convolutional neural network (DCNN), accurate identification of damage types was achieved, with a recognition accuracy of 93.7%. This device integrates self-powering, damage detection, and sag measurement, enhancing monitoring efficiency and accuracy for transmission line faults. The proposed method represents a novel online sensing approach that addresses critical challenges in transmission line monitoring, with potential applications across diverse international contexts.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A joint sensing method for transmission line damage and sag based on triboelectric nanogenerator and deep learning

  • 期刊论文

  • 发表日期：

    2025年4月25日

查看全文
  • Zhijie Hao,
  • Zhenyao Ma,
  • Changxin Liu,
  • Yi Wang,
  • Kailin Lei,
  • Jiaming Zhang,
  • Shengquan Wang,
  • Yunchi Xie,
  • Mingyu Lu

摘要

Failures such as transmission line damage and increased sag pose significant challenges to the safe operation of power grids worldwide. Real-time detection of these issues is critical for preventing power interruptions, which can have severe economic and social consequences across different regions. A joint sensing method for transmission line damage and sag based on a triboelectric nanogenerator (TENG) is proposed in this study. A sensing model, termed Grid Breakage-Cracking-Sag Detection based on Triboelectric Nanogenerator (GBCS-TENG), is developed, and a prototype is fabricated and experimentally validated. Within the specified range, the GBCS-TENG demonstrated precise measurements of both damage and sag. By utilizing a damage classification model based on a deep convolutional neural network (DCNN), accurate identification of damage types was achieved, with a recognition accuracy of 93.7%. This device integrates self-powering, damage detection, and sag measurement, enhancing monitoring efficiency and accuracy for transmission line faults. The proposed method represents a novel online sensing approach that addresses critical challenges in transmission line monitoring, with potential applications across diverse international contexts.