Study on Novel Surface Defect Detection Methods for Aeroengine Turbine Blades Based on the LFD-YOLO Framework
This study proposes a novel defect detection method to address the low accuracy and insufficient efficiency encountered during surface defect detection on aeroengine turbine blades (ATBs). The proposed approach employs the LDconv model to adjust the size and shape of convolutional kernels dynamicall...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-04-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/7/2219 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850212363308892160 |
|---|---|
| author | Wei Deng Guixiong Liu Jun Meng |
| author_facet | Wei Deng Guixiong Liu Jun Meng |
| author_sort | Wei Deng |
| collection | DOAJ |
| description | This study proposes a novel defect detection method to address the low accuracy and insufficient efficiency encountered during surface defect detection on aeroengine turbine blades (ATBs). The proposed approach employs the LDconv model to adjust the size and shape of convolutional kernels dynamically, integrates the deformable attention mechanism (DAT) to capture minute defect features effectively, and uses Focaler-CIoU to optimize the bounding box loss function of the detection network. Our approaches collectively provide precise detection of surface defects on ATBs. The results show that the proposed method achieves a mean average precision (<i>mAP</i><sub>0.5</sub>) of 96.2%, an F-measure of 96.7%, and an identification rate (<i>I<sub>r</sub></i>) of 98.8%, while maintaining a detection speed of over 25 images per second. The proposed method meets the stringent requirements for accuracy and real-time performance in ATB surface defect detection. |
| format | Article |
| id | doaj-art-8a2411e5c2134d07aa0a5fed4ac4f94f |
| institution | OA Journals |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-8a2411e5c2134d07aa0a5fed4ac4f94f2025-08-20T02:09:21ZengMDPI AGSensors1424-82202025-04-01257221910.3390/s25072219Study on Novel Surface Defect Detection Methods for Aeroengine Turbine Blades Based on the LFD-YOLO FrameworkWei Deng0Guixiong Liu1Jun Meng2School of Mechanical and Automotive Engineering, South China University of Technology, Guangzhou 510640, ChinaSchool of Mechanical and Automotive Engineering, South China University of Technology, Guangzhou 510640, ChinaJetech Technology Company, Shenzhen 518102, ChinaThis study proposes a novel defect detection method to address the low accuracy and insufficient efficiency encountered during surface defect detection on aeroengine turbine blades (ATBs). The proposed approach employs the LDconv model to adjust the size and shape of convolutional kernels dynamically, integrates the deformable attention mechanism (DAT) to capture minute defect features effectively, and uses Focaler-CIoU to optimize the bounding box loss function of the detection network. Our approaches collectively provide precise detection of surface defects on ATBs. The results show that the proposed method achieves a mean average precision (<i>mAP</i><sub>0.5</sub>) of 96.2%, an F-measure of 96.7%, and an identification rate (<i>I<sub>r</sub></i>) of 98.8%, while maintaining a detection speed of over 25 images per second. The proposed method meets the stringent requirements for accuracy and real-time performance in ATB surface defect detection.https://www.mdpi.com/1424-8220/25/7/2219ATBdefect detectionLDconvDATFocaler-CIoU |
| spellingShingle | Wei Deng Guixiong Liu Jun Meng Study on Novel Surface Defect Detection Methods for Aeroengine Turbine Blades Based on the LFD-YOLO Framework Sensors ATB defect detection LDconv DAT Focaler-CIoU |
| title | Study on Novel Surface Defect Detection Methods for Aeroengine Turbine Blades Based on the LFD-YOLO Framework |
| title_full | Study on Novel Surface Defect Detection Methods for Aeroengine Turbine Blades Based on the LFD-YOLO Framework |
| title_fullStr | Study on Novel Surface Defect Detection Methods for Aeroengine Turbine Blades Based on the LFD-YOLO Framework |
| title_full_unstemmed | Study on Novel Surface Defect Detection Methods for Aeroengine Turbine Blades Based on the LFD-YOLO Framework |
| title_short | Study on Novel Surface Defect Detection Methods for Aeroengine Turbine Blades Based on the LFD-YOLO Framework |
| title_sort | study on novel surface defect detection methods for aeroengine turbine blades based on the lfd yolo framework |
| topic | ATB defect detection LDconv DAT Focaler-CIoU |
| url | https://www.mdpi.com/1424-8220/25/7/2219 |
| work_keys_str_mv | AT weideng studyonnovelsurfacedefectdetectionmethodsforaeroengineturbinebladesbasedonthelfdyoloframework AT guixiongliu studyonnovelsurfacedefectdetectionmethodsforaeroengineturbinebladesbasedonthelfdyoloframework AT junmeng studyonnovelsurfacedefectdetectionmethodsforaeroengineturbinebladesbasedonthelfdyoloframework |