Scholarlink

<p>This study proposes a real-time transmission line sag monitoring and risk assessment framework based on the Beidou Navigation Satellite System (BDS) integrated with machine learning–driven analytics. The system synergistically combines high-precision satellite positioning with physics-based sag modelling to enable continuous and automated monitoring of conductor behaviour under dynamic environmental and operational conditions. By systematically incorporating thermal expansion, mechanical deformation, and meteorological influences into a unified analytical framework, the proposed methodology facilitates accurate sag estimation alongside robust short-term predictive capability. Experimental validation demonstrates stable long-term operation and enhanced sag detection accuracy compared with conventional monitoring approaches. The findings confirm the technical feasibility of deploying BDS-enabled intelligent monitoring systems as a scalable and reliable solution for improving grid safety, operational reliability, and proactive maintenance in smart power networks.</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

Real-time transmission line sag monitoring and risk assessment using Beidou navigation satellite system: a machine learning-enhanced approach for smart grid applications

  • 期刊论文

  • 发表日期：

    2026年4月28日

查看全文
  • Shizhong Lin,
  • Kai Zhang,
  • Siming Ding,
  • Xiaoma Fang,
  • Maorong Wei,
  • Yongchao Hu,
  • Jun Zhang,
  • Zhan Shao

摘要

This study proposes a real-time transmission line sag monitoring and risk assessment framework based on the Beidou Navigation Satellite System (BDS) integrated with machine learning–driven analytics. The system synergistically combines high-precision satellite positioning with physics-based sag modelling to enable continuous and automated monitoring of conductor behaviour under dynamic environmental and operational conditions. By systematically incorporating thermal expansion, mechanical deformation, and meteorological influences into a unified analytical framework, the proposed methodology facilitates accurate sag estimation alongside robust short-term predictive capability. Experimental validation demonstrates stable long-term operation and enhanced sag detection accuracy compared with conventional monitoring approaches. The findings confirm the technical feasibility of deploying BDS-enabled intelligent monitoring systems as a scalable and reliable solution for improving grid safety, operational reliability, and proactive maintenance in smart power networks.