Structural damage detection of wind turbine based on YOLO11
Bibliographic record
Abstract
Conventional methods for visually examining wind turbines have numerous constraints and frequently fall short of guaranteeing optimal outcomes. Flaws or impairments on wind turbine blades diminish the lifespan and energy production efficiency of the turbine, while also escalating monitoring inaccuracies, safety hazards, and maintenance expenses. The automated assessment of wind turbines via deep learning has become a powerful and efficient method for tackling quality control challenges in the industrial sector, particularly through object detection methods using the YOLO versions that improves the detection of minor objects. Consequently, this research suggests identifying wind turbine faults through the latest version of YOLO (YOLO11) lightweight model that was released in 2024, which includes enhancements in YOLO’s series network effectiveness, precision, and real-time object detection features. YOLO11 incorporates an improved backbone and neck architecture, introducing components like the C3k2 (Cross Stage Partial with kernel size 2) block, SPPF (Spatial Pyramid Pooling - Fast), and C2PSA (Convolutional block with Parallel Spatial Attention), which enhance feature extraction and lead to higher precision, allowing the model to achieve better computational efficiency without compromising accuracy. Defect detection on wind turbines is challenging because there is a high similarity between the defects and the structure itself, but also the very small size of the defects on the structure may not be detected. Through the results obtained but also by comparing our findings with the studies already done, in this article we have demonstrated that YOLO11 is capable of detecting several defects at the same time with precision. In consequence our model can assist in improving wind turbines inspection.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".