Field-Validated UAV-Based Deep Learning Framework for Automated Inspection of Power Transmission and Distribution Infrastructure
Sensors · 14.07.2026 · 26 (14) · 4478
DOI: 10.3390/s26144478 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 14.07.2026. Verfasst von Gabriel Miguel Castro Martins und 5 weiteren Autor:innen. Beteiligte Einrichtung: Master Degree Program in Automation and Systems (PPGAS), Federal Center of Technological Education of Minas Gerais (CEFET-MG), Leopoldina 36700-001, …. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Elera Renewable Energies.
Abstract (Originalsprache)
The reliable inspection of power transmission and distribution infrastructure is essential for ensuring energy security, operational continuity, and asset reliability. Conventional inspection procedures are labor-intensive, costly, and often expose maintenance teams to hazardous environments. In this context, Unmanned Aerial Vehicles (UAVs) combined with artificial intelligence have emerged as an effective solution for large-scale infrastructure monitoring. This paper presents a field-validated framework for automated inspection of power transmission and distribution assets using autonomous UAV image acquisition and deep learning analysis. The proposed approach enables multiclass detection of electrical components and anomalies in high-resolution aerial imagery, without requiring computationally intensive 3D reconstruction. The framework integrates autonomous data collection, object detection, and dedicated condition assessment models into a scalable inspection workflow. The system was validated across six transmission and distribution lines located in five Brazilian states, covering 2925 support structures and a wide range of environmental and operational conditions. Experimental results achieved an overall mAP50 of 0.9572 across seven target classes, with individual scores ranging from 0.8945 for corrosion detection to 0.9935 for ceramic disc insulators. Complementary classification models achieved accuracies of 0.97 for insulator contamination assessment, 0.92 for pin attachment configuration, and 0.98 for ceramic pin integrity evaluation. The results demonstrate the feasibility of deploying Artificial Intelligence (AI)-assisted UAV inspections in real utility scenarios, providing a scalable alternative for preventive maintenance, asset management, and condition-based monitoring of electrical infrastructure.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Master Degree Program in Automation and Systems (PPGAS), Federal Center of Technological Education of Minas Gerais (CEFET-MG), Leopoldina 36700-001, Brazil.
- Robotictech Technology Services, Juiz de Fora 36036-330, Brazil.
- Elera Renewable Energies, Rio de Janeiro 22775-028, Brazil.
ORCID-Profile: Murillo Ferreira Dos Santos, Mathaus Ferreira da Silva, Juliano Emir Nunes Masson
Förderung
- Elera Renewable Energies
Zitieren
APA
Martins, G. M. C., Dos Santos, M. F., da Silva, M. F., Masson, J. E. N., Alves, P. M. R., & Chain, G. R. C. (2026). Field-Validated UAV-Based Deep Learning Framework for Automated Inspection of Power Transmission and Distribution Infrastructure. Sensors, 26(14), 4478. https://doi.org/10.3390/s26144478
Vancouver
Martins GMC, Dos Santos MF, da Silva MF, Masson JEN, Alves PMR, Chain GRC. Field-Validated UAV-Based Deep Learning Framework for Automated Inspection of Power Transmission and Distribution Infrastructure. Sensors. 2026;26(14):4478. doi:10.3390/s26144478
BibTeX
@article{Martins2026,
author = {Martins, Gabriel Miguel Castro and Dos Santos, Murillo Ferreira and da Silva, Mathaus Ferreira and Masson, Juliano Emir Nunes and Alves, Pedro Mendes Rocha and Chain, Gabriela Ribeiro Cabral},
title = {Field-Validated UAV-Based Deep Learning Framework for Automated Inspection of Power Transmission and Distribution Infrastructure},
journal = {Sensors},
year = {2026},
volume = {26},
number = {14},
pages = {4478},
doi = {10.3390/s26144478}
}
EUVIMED