Scholarlink

<p>Lightning strikes pose a significant threat to the structural integrity and operational performance of wind turbine blades. Due to the high probability of lightning strikes but the difficulty in capturing their dynamic data, obtaining comprehensive data on blades subjected to lightning strikes is challenging. This study presents a rare multimodal dataset for wind turbine blade monitoring during lightning strikes (MDWTBM-LS). It includes vibration, load, and strain measurements from fiber optic load sensors and fiber optic accelerometer sensors. It provides real-time records of blade operational status and damage assessments after strikes. The dataset is intended to promote the development of predictive models for lightning strike detection and blade damage assessment, ultimately enhancing the monitoring, maintenance, and operational optimization of wind energy facilities. The dataset is publicly available for researchers to conduct in-depth studies in fields such as machine learning, condition monitoring, and fault prediction, contributing to the resilience and reliability of wind turbine operations.</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

Multimodal dataset for wind turbine blade monitoring during lightning strikes

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年9月1日

查看全文
  • Tao Li,
  • Chenxi Li,
  • Yuxin Qin,
  • Long Tan,
  • Bang Jiang,
  • Hang Deng

摘要

Lightning strikes pose a significant threat to the structural integrity and operational performance of wind turbine blades. Due to the high probability of lightning strikes but the difficulty in capturing their dynamic data, obtaining comprehensive data on blades subjected to lightning strikes is challenging. This study presents a rare multimodal dataset for wind turbine blade monitoring during lightning strikes (MDWTBM-LS). It includes vibration, load, and strain measurements from fiber optic load sensors and fiber optic accelerometer sensors. It provides real-time records of blade operational status and damage assessments after strikes. The dataset is intended to promote the development of predictive models for lightning strike detection and blade damage assessment, ultimately enhancing the monitoring, maintenance, and operational optimization of wind energy facilities. The dataset is publicly available for researchers to conduct in-depth studies in fields such as machine learning, condition monitoring, and fault prediction, contributing to the resilience and reliability of wind turbine operations.