WindDefNet: A Multi-Scale Attention-Enhanced ViT-Inception-ResNet Model for Real-Time Wind Turbine Blade Defect Detection
Real-time non-intrusive monitoring of wind turbines, blades, and defect surfaces poses a set of complex challenges related to accuracy, safety, cost, and computational efficiency. This work introduces an enhanced deep learning-based framework for real-time detection of wind turbine blade defects. Th...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Machines |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-1702/13/6/453 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849432936480243712 |
|---|---|
| author | Majad Mansoor Xiyue Tan Adeel Feroz Mirza Tao Gong Zhendong Song Muhammad Irfan |
| author_facet | Majad Mansoor Xiyue Tan Adeel Feroz Mirza Tao Gong Zhendong Song Muhammad Irfan |
| author_sort | Majad Mansoor |
| collection | DOAJ |
| description | Real-time non-intrusive monitoring of wind turbines, blades, and defect surfaces poses a set of complex challenges related to accuracy, safety, cost, and computational efficiency. This work introduces an enhanced deep learning-based framework for real-time detection of wind turbine blade defects. The WindDefNet is introduced, which features the Inception-ResNet modules, Visual Transformer (ViT), and multi-scale attention mechanisms. WindDefNet utilizes modified cross-convolutional blocks, including the powerful Inception-ResNet hybrid, to capture both fine-grained and high-level features from input images. A multi-scale attention module is added to focus on important regions in the image, improving detection accuracy, especially in challenging areas of the wind turbine blades. We employ pertaining to Inception-ResNet and ViT patch embedding architectures to achieve superior performance in defect classification. WindDefNet’s capability to capture and integrate multi-scale feature representations enhances its effectiveness for robust wind turbine condition monitoring, thereby reducing operational downtime and minimizing maintenance costs. Our model WindDefNet integrates a novel advanced attention mechanism, with custom-pretrained Inception-ResNet combining self-attention with a Visual Transformer encoder, to enhance feature extraction and improve model accuracy. The proposed method demonstrates significant improvements in classification performance, as evidenced by the evaluation metrics attain precision, recall, and F1-scores of 0.88, 1.00, and 0.93 for the damage, 1.00, 0.71, and 0.83 for the edge, and 1.00, 1.00, and 1.00 for both the erosion and normal surfaces. The macro-average and weighted-average F1 scores stand at 0.94, highlighting the robustness of our approach. These results underscore the potential of the proposed model for defect detection in industrial applications. |
| format | Article |
| id | doaj-art-3bad1127aa7d40dc877bd037d4af2b86 |
| institution | Kabale University |
| issn | 2075-1702 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Machines |
| spelling | doaj-art-3bad1127aa7d40dc877bd037d4af2b862025-08-20T03:27:14ZengMDPI AGMachines2075-17022025-05-0113645310.3390/machines13060453WindDefNet: A Multi-Scale Attention-Enhanced ViT-Inception-ResNet Model for Real-Time Wind Turbine Blade Defect DetectionMajad Mansoor0Xiyue Tan1Adeel Feroz Mirza2Tao Gong3Zhendong Song4Muhammad Irfan5Institute of Intelligent Manufacturing Technology, Shenzhen Polytechnic University, Shenzhen 518000, ChinaFaculty of Education, University of Hong Kong, Hong Kong 999077, ChinaSchool of Automation and Intelligent Manufacturing, Southern University of Science and Technology, Shenzhen 518055, ChinaInstitute of Intelligent Manufacturing Technology, Shenzhen Polytechnic University, Shenzhen 518000, ChinaSchool of Mechanical and Electrical Engineering, Shenzhen Polytechnic University, Shenzhen 518000, ChinaSchool of Computing and Data Science, Wentworth Institute of Technology, Boston, MA 02115, USAReal-time non-intrusive monitoring of wind turbines, blades, and defect surfaces poses a set of complex challenges related to accuracy, safety, cost, and computational efficiency. This work introduces an enhanced deep learning-based framework for real-time detection of wind turbine blade defects. The WindDefNet is introduced, which features the Inception-ResNet modules, Visual Transformer (ViT), and multi-scale attention mechanisms. WindDefNet utilizes modified cross-convolutional blocks, including the powerful Inception-ResNet hybrid, to capture both fine-grained and high-level features from input images. A multi-scale attention module is added to focus on important regions in the image, improving detection accuracy, especially in challenging areas of the wind turbine blades. We employ pertaining to Inception-ResNet and ViT patch embedding architectures to achieve superior performance in defect classification. WindDefNet’s capability to capture and integrate multi-scale feature representations enhances its effectiveness for robust wind turbine condition monitoring, thereby reducing operational downtime and minimizing maintenance costs. Our model WindDefNet integrates a novel advanced attention mechanism, with custom-pretrained Inception-ResNet combining self-attention with a Visual Transformer encoder, to enhance feature extraction and improve model accuracy. The proposed method demonstrates significant improvements in classification performance, as evidenced by the evaluation metrics attain precision, recall, and F1-scores of 0.88, 1.00, and 0.93 for the damage, 1.00, 0.71, and 0.83 for the edge, and 1.00, 1.00, and 1.00 for both the erosion and normal surfaces. The macro-average and weighted-average F1 scores stand at 0.94, highlighting the robustness of our approach. These results underscore the potential of the proposed model for defect detection in industrial applications.https://www.mdpi.com/2075-1702/13/6/453wind turbine blade defectinception-ResNetViTfault detectionwind energy |
| spellingShingle | Majad Mansoor Xiyue Tan Adeel Feroz Mirza Tao Gong Zhendong Song Muhammad Irfan WindDefNet: A Multi-Scale Attention-Enhanced ViT-Inception-ResNet Model for Real-Time Wind Turbine Blade Defect Detection Machines wind turbine blade defect inception-ResNet ViT fault detection wind energy |
| title | WindDefNet: A Multi-Scale Attention-Enhanced ViT-Inception-ResNet Model for Real-Time Wind Turbine Blade Defect Detection |
| title_full | WindDefNet: A Multi-Scale Attention-Enhanced ViT-Inception-ResNet Model for Real-Time Wind Turbine Blade Defect Detection |
| title_fullStr | WindDefNet: A Multi-Scale Attention-Enhanced ViT-Inception-ResNet Model for Real-Time Wind Turbine Blade Defect Detection |
| title_full_unstemmed | WindDefNet: A Multi-Scale Attention-Enhanced ViT-Inception-ResNet Model for Real-Time Wind Turbine Blade Defect Detection |
| title_short | WindDefNet: A Multi-Scale Attention-Enhanced ViT-Inception-ResNet Model for Real-Time Wind Turbine Blade Defect Detection |
| title_sort | winddefnet a multi scale attention enhanced vit inception resnet model for real time wind turbine blade defect detection |
| topic | wind turbine blade defect inception-ResNet ViT fault detection wind energy |
| url | https://www.mdpi.com/2075-1702/13/6/453 |
| work_keys_str_mv | AT majadmansoor winddefnetamultiscaleattentionenhancedvitinceptionresnetmodelforrealtimewindturbinebladedefectdetection AT xiyuetan winddefnetamultiscaleattentionenhancedvitinceptionresnetmodelforrealtimewindturbinebladedefectdetection AT adeelferozmirza winddefnetamultiscaleattentionenhancedvitinceptionresnetmodelforrealtimewindturbinebladedefectdetection AT taogong winddefnetamultiscaleattentionenhancedvitinceptionresnetmodelforrealtimewindturbinebladedefectdetection AT zhendongsong winddefnetamultiscaleattentionenhancedvitinceptionresnetmodelforrealtimewindturbinebladedefectdetection AT muhammadirfan winddefnetamultiscaleattentionenhancedvitinceptionresnetmodelforrealtimewindturbinebladedefectdetection |