Detection Transformer with Multi-Scale Fusion Attention Mechanism for Aero-Engine Turbine Blade Cast Defect Detection Considering Comprehensive Features
Casting defects in turbine blades can significantly reduce an aero-engine’s service life and cause secondary damage to the blades when exposed to harsh environments. Therefore, casting defect detection plays a crucial role in enhancing aircraft performance. Existing defect detection methods face cha...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/24/5/1663 |
| _version_ | 1827319305908256768 |
|---|---|
| author | Han-Bing Zhang Chun-Yan Zhang De-Jun Cheng Kai-Li Zhou Zhi-Ying Sun |
| author_facet | Han-Bing Zhang Chun-Yan Zhang De-Jun Cheng Kai-Li Zhou Zhi-Ying Sun |
| author_sort | Han-Bing Zhang |
| collection | DOAJ |
| description | Casting defects in turbine blades can significantly reduce an aero-engine’s service life and cause secondary damage to the blades when exposed to harsh environments. Therefore, casting defect detection plays a crucial role in enhancing aircraft performance. Existing defect detection methods face challenges in effectively detecting multi-scale defects and handling imbalanced datasets, leading to unsatisfactory defect detection results. In this work, a novel blade defect detection method is proposed. This method is based on a detection transformer with a multi-scale fusion attention mechanism, considering comprehensive features. Firstly, a novel joint data augmentation (JDA) method is constructed to alleviate the imbalanced dataset issue by effectively increasing the number of sample data. Then, an attention-based channel-adaptive weighting (ACAW) feature enhancement module is established to fully apply complementary information among different feature channels, and further refine feature representations. Consequently, a multi-scale feature fusion (MFF) module is proposed to integrate high-dimensional semantic information and low-level representation features, enhancing multi-scale defect detection precision. Moreover, R-Focal loss is developed in an MFF attention-based DEtection TRansformer (DETR) to further solve the issue of imbalanced datasets and accelerate model convergence using the random hyper-parameters search strategy. An aero-engine turbine blade defect X-ray (ATBDX) image dataset is applied to validate the proposed method. The comparative results demonstrate that this proposed method can effectively integrate multi-scale image features and enhance multi-scale defect detection precision. |
| first_indexed | 2024-04-25T00:18:48Z |
| format | Article |
| id | doaj.art-5883ff1782854e138a6c79cc150b7805 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-25T00:18:48Z |
| publishDate | 2024-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-5883ff1782854e138a6c79cc150b78052024-03-12T16:55:34ZengMDPI AGSensors1424-82202024-03-01245166310.3390/s24051663Detection Transformer with Multi-Scale Fusion Attention Mechanism for Aero-Engine Turbine Blade Cast Defect Detection Considering Comprehensive FeaturesHan-Bing Zhang0Chun-Yan Zhang1De-Jun Cheng2Kai-Li Zhou3Zhi-Ying Sun4School of Mechanical Engineering, Jiangsu University of Science and Technology, Zhenjiang 212003, ChinaSchool of Mechanical Engineering, Jiangsu University of Science and Technology, Zhenjiang 212003, ChinaSchool of Mechanical Engineering, Jiangsu University of Science and Technology, Zhenjiang 212003, ChinaSchool of Mechanical Engineering, Jiangsu University of Science and Technology, Zhenjiang 212003, ChinaSchool of Mechanical Engineering, Jiangsu University of Science and Technology, Zhenjiang 212003, ChinaCasting defects in turbine blades can significantly reduce an aero-engine’s service life and cause secondary damage to the blades when exposed to harsh environments. Therefore, casting defect detection plays a crucial role in enhancing aircraft performance. Existing defect detection methods face challenges in effectively detecting multi-scale defects and handling imbalanced datasets, leading to unsatisfactory defect detection results. In this work, a novel blade defect detection method is proposed. This method is based on a detection transformer with a multi-scale fusion attention mechanism, considering comprehensive features. Firstly, a novel joint data augmentation (JDA) method is constructed to alleviate the imbalanced dataset issue by effectively increasing the number of sample data. Then, an attention-based channel-adaptive weighting (ACAW) feature enhancement module is established to fully apply complementary information among different feature channels, and further refine feature representations. Consequently, a multi-scale feature fusion (MFF) module is proposed to integrate high-dimensional semantic information and low-level representation features, enhancing multi-scale defect detection precision. Moreover, R-Focal loss is developed in an MFF attention-based DEtection TRansformer (DETR) to further solve the issue of imbalanced datasets and accelerate model convergence using the random hyper-parameters search strategy. An aero-engine turbine blade defect X-ray (ATBDX) image dataset is applied to validate the proposed method. The comparative results demonstrate that this proposed method can effectively integrate multi-scale image features and enhance multi-scale defect detection precision.https://www.mdpi.com/1424-8220/24/5/1663aero-engine turbine blademulti-scale defect detectionattention-based channel-adaptive weightingmulti-scale feature fusionR-focal loss |
| spellingShingle | Han-Bing Zhang Chun-Yan Zhang De-Jun Cheng Kai-Li Zhou Zhi-Ying Sun Detection Transformer with Multi-Scale Fusion Attention Mechanism for Aero-Engine Turbine Blade Cast Defect Detection Considering Comprehensive Features Sensors aero-engine turbine blade multi-scale defect detection attention-based channel-adaptive weighting multi-scale feature fusion R-focal loss |
| title | Detection Transformer with Multi-Scale Fusion Attention Mechanism for Aero-Engine Turbine Blade Cast Defect Detection Considering Comprehensive Features |
| title_full | Detection Transformer with Multi-Scale Fusion Attention Mechanism for Aero-Engine Turbine Blade Cast Defect Detection Considering Comprehensive Features |
| title_fullStr | Detection Transformer with Multi-Scale Fusion Attention Mechanism for Aero-Engine Turbine Blade Cast Defect Detection Considering Comprehensive Features |
| title_full_unstemmed | Detection Transformer with Multi-Scale Fusion Attention Mechanism for Aero-Engine Turbine Blade Cast Defect Detection Considering Comprehensive Features |
| title_short | Detection Transformer with Multi-Scale Fusion Attention Mechanism for Aero-Engine Turbine Blade Cast Defect Detection Considering Comprehensive Features |
| title_sort | detection transformer with multi scale fusion attention mechanism for aero engine turbine blade cast defect detection considering comprehensive features |
| topic | aero-engine turbine blade multi-scale defect detection attention-based channel-adaptive weighting multi-scale feature fusion R-focal loss |
| url | https://www.mdpi.com/1424-8220/24/5/1663 |
| work_keys_str_mv | AT hanbingzhang detectiontransformerwithmultiscalefusionattentionmechanismforaeroengineturbinebladecastdefectdetectionconsideringcomprehensivefeatures AT chunyanzhang detectiontransformerwithmultiscalefusionattentionmechanismforaeroengineturbinebladecastdefectdetectionconsideringcomprehensivefeatures AT dejuncheng detectiontransformerwithmultiscalefusionattentionmechanismforaeroengineturbinebladecastdefectdetectionconsideringcomprehensivefeatures AT kailizhou detectiontransformerwithmultiscalefusionattentionmechanismforaeroengineturbinebladecastdefectdetectionconsideringcomprehensivefeatures AT zhiyingsun detectiontransformerwithmultiscalefusionattentionmechanismforaeroengineturbinebladecastdefectdetectionconsideringcomprehensivefeatures |