Dual-Modal Fusion PRI-SWT Model for Eddy Current Detection of Cracks, Delamination, and Impact Damage in Carbon Fiber-Reinforced Plastic Materials
Carbon fiber-reinforced plastic (CFRP) composites are prone to damage during both manufacturing and operational phases, making the classification and identification of defects critical for maintaining structural integrity. This paper presents a novel dual-modal feature classification approach for th...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-11-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/14/22/10282 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846154541798522880 |
|---|---|
| author | Rongyan Wen Chongcong Tao Hongli Ji Jinhao Qiu |
| author_facet | Rongyan Wen Chongcong Tao Hongli Ji Jinhao Qiu |
| author_sort | Rongyan Wen |
| collection | DOAJ |
| description | Carbon fiber-reinforced plastic (CFRP) composites are prone to damage during both manufacturing and operational phases, making the classification and identification of defects critical for maintaining structural integrity. This paper presents a novel dual-modal feature classification approach for the eddy current detection of CFRP defects, utilizing a Parallel Real–Imaginary/Swin Transformer (PRI-SWT) model. Built using the Transformer architecture, the PRI-SWT model effectively integrates the real and imaginary components of sinusoidal voltage signals, demonstrating a significant performance improvement over traditional classification methods such as Support Vector Machine (SVM) and Vision Transformer (ViT). The proposed model achieved a classification accuracy exceeding 95%, highlighting its superior capability in terms of addressing the complexities of defect detection. Furthermore, the influence of key factors—including the real–imaginary fusion layer, the number of layers, the window shift size, and the model’s scale—on the classification performance of the PRI-SWT model was systematically evaluated. |
| format | Article |
| id | doaj-art-731984db1fde49198ce72de1bf088dcf |
| institution | Kabale University |
| issn | 2076-3417 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-731984db1fde49198ce72de1bf088dcf2024-11-26T17:48:09ZengMDPI AGApplied Sciences2076-34172024-11-0114221028210.3390/app142210282Dual-Modal Fusion PRI-SWT Model for Eddy Current Detection of Cracks, Delamination, and Impact Damage in Carbon Fiber-Reinforced Plastic MaterialsRongyan Wen0Chongcong Tao1Hongli Ji2Jinhao Qiu3College of Aerospace Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, ChinaCollege of Aerospace Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, ChinaCollege of Aerospace Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, ChinaCollege of Aerospace Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, ChinaCarbon fiber-reinforced plastic (CFRP) composites are prone to damage during both manufacturing and operational phases, making the classification and identification of defects critical for maintaining structural integrity. This paper presents a novel dual-modal feature classification approach for the eddy current detection of CFRP defects, utilizing a Parallel Real–Imaginary/Swin Transformer (PRI-SWT) model. Built using the Transformer architecture, the PRI-SWT model effectively integrates the real and imaginary components of sinusoidal voltage signals, demonstrating a significant performance improvement over traditional classification methods such as Support Vector Machine (SVM) and Vision Transformer (ViT). The proposed model achieved a classification accuracy exceeding 95%, highlighting its superior capability in terms of addressing the complexities of defect detection. Furthermore, the influence of key factors—including the real–imaginary fusion layer, the number of layers, the window shift size, and the model’s scale—on the classification performance of the PRI-SWT model was systematically evaluated.https://www.mdpi.com/2076-3417/14/22/10282CFRP defect detectioneddy current nondestructive testing systemVision Transformer modelParallel Real–Imaginary/Swin Transformer modelintelligent classification algorithm |
| spellingShingle | Rongyan Wen Chongcong Tao Hongli Ji Jinhao Qiu Dual-Modal Fusion PRI-SWT Model for Eddy Current Detection of Cracks, Delamination, and Impact Damage in Carbon Fiber-Reinforced Plastic Materials Applied Sciences CFRP defect detection eddy current nondestructive testing system Vision Transformer model Parallel Real–Imaginary/Swin Transformer model intelligent classification algorithm |
| title | Dual-Modal Fusion PRI-SWT Model for Eddy Current Detection of Cracks, Delamination, and Impact Damage in Carbon Fiber-Reinforced Plastic Materials |
| title_full | Dual-Modal Fusion PRI-SWT Model for Eddy Current Detection of Cracks, Delamination, and Impact Damage in Carbon Fiber-Reinforced Plastic Materials |
| title_fullStr | Dual-Modal Fusion PRI-SWT Model for Eddy Current Detection of Cracks, Delamination, and Impact Damage in Carbon Fiber-Reinforced Plastic Materials |
| title_full_unstemmed | Dual-Modal Fusion PRI-SWT Model for Eddy Current Detection of Cracks, Delamination, and Impact Damage in Carbon Fiber-Reinforced Plastic Materials |
| title_short | Dual-Modal Fusion PRI-SWT Model for Eddy Current Detection of Cracks, Delamination, and Impact Damage in Carbon Fiber-Reinforced Plastic Materials |
| title_sort | dual modal fusion pri swt model for eddy current detection of cracks delamination and impact damage in carbon fiber reinforced plastic materials |
| topic | CFRP defect detection eddy current nondestructive testing system Vision Transformer model Parallel Real–Imaginary/Swin Transformer model intelligent classification algorithm |
| url | https://www.mdpi.com/2076-3417/14/22/10282 |
| work_keys_str_mv | AT rongyanwen dualmodalfusionpriswtmodelforeddycurrentdetectionofcracksdelaminationandimpactdamageincarbonfiberreinforcedplasticmaterials AT chongcongtao dualmodalfusionpriswtmodelforeddycurrentdetectionofcracksdelaminationandimpactdamageincarbonfiberreinforcedplasticmaterials AT hongliji dualmodalfusionpriswtmodelforeddycurrentdetectionofcracksdelaminationandimpactdamageincarbonfiberreinforcedplasticmaterials AT jinhaoqiu dualmodalfusionpriswtmodelforeddycurrentdetectionofcracksdelaminationandimpactdamageincarbonfiberreinforcedplasticmaterials |