Skip to content
Open access

A Comparison of Coating-Defect Detection Models for Wind Turbine Towers

Sep 2026 · Coatings · 0 citations · 29 references

Abstract

Wind energy is becoming increasingly important in meeting energy security, grid reliability, and the growing electricity demand. The rapid increase in the number and prevalence of wind turbines has triggered the need for fast, cost-effective, reliable, and easy-to-implement inspection systems. Automated detection of coating defects is important for the maintenance and corrosion prevention of the turbines. In this context, this study aimed to compare and evaluate the accuracy and efficiency of deep learning models for detection of coating defects from images. In this context, the study evaluates five object detection models, RT-DETR-L, YOLOv8-M, YOLOv9-C, YOLO11-L, and YOLO26-L, on an open coating-defect dataset, with inclusion, pinhole, and scratch classes. Each model was trained with 3 random seeds for images of 640 × 640 and 1088 × 1088-pixel resolutions. At 1088 × 1088, YOLO26-L achieved the highest mean mAP50–95 (0.1142), while RT-DETR-L achieved the highest recall (0.5591) and F1 score (0.2217) at the operating confidence threshold of 0.25; RT-DETR-L was also the slowest model (59.8 ms/image). YOLOv8-M achieved a mean mAP50–95 of 0.0976 together with the lowest latency (34.2 ms/image) and lowest true batch-size-1 peak GPU-memory allocation (278 MB). Reducing the resolution to 640 × 640 lowered mAP50–95 by 25.4% for YOLOv8-M and 33.6% for RT-DETR-L while reducing latency and memory use. The results revealed a pronounced accuracy-efficiency trade-off rather than universal superiority of one model for coating defect detection for wind turbine towers. The dataset was acquired during the wind-tower painting process under controlled industrial imaging conditions, so the results characterise in-process coating inspection rather than the inspection of weathered, in-service turbines. Because only three random seeds were used, paired comparisons between individual models were not statistically conclusive (8 of 100 pairwise tests reached p < 0.05) and the reported rankings are descriptive. Applying operating thresholds—determined on the validation set for each model—to the independent test set altered the architectural ranking. At 1088 × 1088 resolution, YOLO26-L surpassed RT-DETR-L to achieve the highest mean F1 score, whereas at 640 × 640 resolution, RT-DETR-L’s ranking dropped significantly. The fact that the selected thresholds range from 0.076 to 0.456 indicates that the differences observed at the common threshold of 0.25 are sensitive to the choice of threshold. While the mAP50–95 decreased by approximately half in the 640 × 640 evaluation—where data leakage was eliminated—the 1088 × 1088 results were considered optimistic, as they were obtained based on the previous segmentation.

Read PDF

Similar papers

Open access Sep 2026

Thermal-Aware Attention-Driven Deep Learning for Intelligent Solar Panel Defect Detection

As global awareness of climate change grows, renewable energy sources like solar power have become increasingly important. Photovoltaic (PV) systems, which convert sunlight into electricity using solar cells, are widely used due to their sustainability, low maintenance costs, and ease of installation. However, PV pa...

Iherorochi Nneji Richard · 0 citations
Open access Oct 2026

Deep Learning-Based Methods for Rolling Bearing Fault Diagnosis: Optimization and Comparison

Rolling bearings are the vital support elements of industrial rotating machinery. Operational conditions have a direct impact on the safety, dependability and economical operation and maintenance of the production system. An effective and accurate fault diagnosis technology is very important for predictive maintenance...

Ze-Xin Yin · 0 citations
Open access Sep 2026

BCDC-YOLO: A Lightweight Detection Network for Anti-Corrosion Coating Surface Defects on Bridge Prestressed Corrugated Ducts

During the long-term service and construction of bridges, various types of surface defects frequently occur in the anti-corrosion coating on the surface of prestressed metallic corrugated ducts, severely threatening the overall durability of the bridge structure. To address the challenges of uneven optical imaging, hig...

En-He Wu, Jun Peng, Qing-Shuang Xu et al. · 0 citations
Open access 2026

Photovoltaic Anomaly Detection in Electroluminescence Images Using a Transformer-Enhanced YOLO Algorithm

This study proposes a lightweight and enhanced You Only Look Once (YOLO)11-based architecture specifically designed for superior defect detection, which surpasses all competing methods by a substantial margin and is evaluated against a comprehensive suite of state-of-the-art object detection frameworks.

Mehmet Fatih Bekciogullari, H. Acikgoz, S. Ozbay · 0 citations
Open access Sep 2026

Deep Learning-Based Visual Detection Technology for Metal Gear Surface Defects

Due to complex background interference, a lack of real defect samples, and inconsistent evaluation of real-time deployment in metal gear surface defect detection, four representative studies were selected for comparison and four technical approaches were analyzed: lightweight detection, interference resistance, few-sam...

Jie Meng · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.