Criticality Assessment of Wind Turbine Defects via Multispectral UAV Fusion and Fuzzy Logic
Energies, Vol. 18, No. 17, pp. 4523
Abstract
This paper presents a comprehensive framework for assessing the criticality of wind turbine defects using multispectral UAV imaging and fuzzy logic. An ensemble of YOLOv8n models trained on fused RGB-thermal data achieves a mean Average Precision (mAP@.5) of 92.8% for detecting cracks, erosion, and thermal anomalies. A 27-rule Fuzzy Inference System translates quantitative defect parameters into a five-level criticality score.
Citation
Serhii Svystun, Lukasz Scislo, Michal Pawlik, Oleksandr Melnychenko, Pavlo Radiuk, Oleg Savenko, Anatoliy Sachenko. "Criticality Assessment of Wind Turbine Defects via Multispectral UAV Fusion and Fuzzy Logic". Energies, Vol. 18, No. 17, pp. 4523, 2025.