Scholarlink

<p>The increasing need for efficient monitoring of electrical infrastructure has led to the development of innovative solutions that combine hardware and software for automated inspection and cataloging of assets. This paper presents a comprehensive system designed to improve the accuracy and efficiency of monitoring electrical distribution networks. The proposed solution utilizes advanced computer vision and artificial intelligence algorithms integrated into a versatile hardware setup capable of capturing high-definition images and 3D models of the environment from vehicles in motion. Key features include automatic classification of components such as transformers, poles, and vegetation, focusing on identifying potential risks to the network, such as vegetation encroachment. The system’s performance has been validated through field tests, demonstrating high accuracy in component detection and classification and reliable distance measurements between vegetation and electrical lines. The solution also offers a web interface for data visualization and report generation, enabling seamless integration into existing workflows. This work contributes to the field by providing a scalable and efficient approach to asset management in the energy sector.</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

AI-Powered Automated Inspection for Optimized Asset Management in Electrical Distribution Networks

  • 期刊论文

  • 发表日期：

    2025年8月16日

查看全文
  • Mathaus F. da Silva,
  • Murillo F. dos Santos,
  • Juliano E. N. Masson,
  • Pedro M. R. Alves,
  • William R. Silva,
  • Gabriel M. C. Martins,
  • Vitor Hugo G. da Costa,
  • Vinícius B. Schettino,
  • Maurício E. Stivanello

摘要

The increasing need for efficient monitoring of electrical infrastructure has led to the development of innovative solutions that combine hardware and software for automated inspection and cataloging of assets. This paper presents a comprehensive system designed to improve the accuracy and efficiency of monitoring electrical distribution networks. The proposed solution utilizes advanced computer vision and artificial intelligence algorithms integrated into a versatile hardware setup capable of capturing high-definition images and 3D models of the environment from vehicles in motion. Key features include automatic classification of components such as transformers, poles, and vegetation, focusing on identifying potential risks to the network, such as vegetation encroachment. The system’s performance has been validated through field tests, demonstrating high accuracy in component detection and classification and reliable distance measurements between vegetation and electrical lines. The solution also offers a web interface for data visualization and report generation, enabling seamless integration into existing workflows. This work contributes to the field by providing a scalable and efficient approach to asset management in the energy sector.