Research on algorithm for improving imaging accuracy of CFRP low speed impact damage
Carbon fiber reinforced polymer（CFRP）composites has small and hidden damage after low-speed impact，and the existence of damage significantly reduces the bearing capacity and service life of CFRP materials. C-scan represents a conventional ultrasonic imaging method. To address the issue of low imagin...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Journal of Aeronautical Materials
2025-02-01
|
| Series: | Journal of Aeronautical Materials |
| Subjects: | |
| Online Access: | http://jam.biam.ac.cn/article/doi/10.11868/j.issn.1005-5053.2023.000189 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823856407479320576 |
|---|---|
| author | WU Xiangnan CHENG Xiaojin LI Qixin SHANG Jianhua |
| author_facet | WU Xiangnan CHENG Xiaojin LI Qixin SHANG Jianhua |
| author_sort | WU Xiangnan |
| collection | DOAJ |
| description | Carbon fiber reinforced polymer（CFRP）composites has small and hidden damage after low-speed impact，and the existence of damage significantly reduces the bearing capacity and service life of CFRP materials. C-scan represents a conventional ultrasonic imaging method. To address the issue of low imaging precision in C-scan detection of internal damage caused by low-velocity impact in CFRP，gradient operators were employed to process the original images，and transfer learning methodology was utilized to conduct damage classification training on ResNet18 and ResNet50 architectures. To enhance the classification model’s performance，an image reconstruction model（IRM）based on convolutional neural networks was proposed to improve imaging precision. Additionally，a performance metric σEOL，based on the structural similarity index（SSIM），was introduced to validate the level of image quality enhancement. The iterative training results demonstrate that when the iteration count reaches 200，the σEOL of different types of impact damage is greater than 1. To further improve imaging precision，the ResNet residual connection concept is incorporated，leading to the development of the ResIRM network. Compared to IRM，ResIRM exhibits enhanced detection precision for different types of impact damage，with an average σEOL improvement of 0.85% across all impact types. Furthermore，the gradient saliency heat maps of the classification model processed by ResIRM indicate that ResIRM effectively reinforces the features in damaged regions. |
| format | Article |
| id | doaj-art-24fa41970f974223ae3c6fe71f0d24b3 |
| institution | Kabale University |
| issn | 1005-5053 |
| language | zho |
| publishDate | 2025-02-01 |
| publisher | Journal of Aeronautical Materials |
| record_format | Article |
| series | Journal of Aeronautical Materials |
| spelling | doaj-art-24fa41970f974223ae3c6fe71f0d24b32025-02-12T09:22:41ZzhoJournal of Aeronautical MaterialsJournal of Aeronautical Materials1005-50532025-02-01451809010.11868/j.issn.1005-5053.2023.000189a2023-0189Research on algorithm for improving imaging accuracy of CFRP low speed impact damageWU Xiangnan0CHENG Xiaojin1LI Qixin2SHANG Jianhua3School of Mechanical and Automotive Engineering，Shanghai University of Engineering Science，Shanghai 201620，ChinaSchool of Mechanical and Automotive Engineering，Shanghai University of Engineering Science，Shanghai 201620，ChinaSchool of Mechanical and Automotive Engineering，Shanghai University of Engineering Science，Shanghai 201620，ChinaSchool of Information Science and Technology，Donghua University，Shanghai 201620，ChinaCarbon fiber reinforced polymer（CFRP）composites has small and hidden damage after low-speed impact，and the existence of damage significantly reduces the bearing capacity and service life of CFRP materials. C-scan represents a conventional ultrasonic imaging method. To address the issue of low imaging precision in C-scan detection of internal damage caused by low-velocity impact in CFRP，gradient operators were employed to process the original images，and transfer learning methodology was utilized to conduct damage classification training on ResNet18 and ResNet50 architectures. To enhance the classification model’s performance，an image reconstruction model（IRM）based on convolutional neural networks was proposed to improve imaging precision. Additionally，a performance metric σEOL，based on the structural similarity index（SSIM），was introduced to validate the level of image quality enhancement. The iterative training results demonstrate that when the iteration count reaches 200，the σEOL of different types of impact damage is greater than 1. To further improve imaging precision，the ResNet residual connection concept is incorporated，leading to the development of the ResIRM network. Compared to IRM，ResIRM exhibits enhanced detection precision for different types of impact damage，with an average σEOL improvement of 0.85% across all impact types. Furthermore，the gradient saliency heat maps of the classification model processed by ResIRM indicate that ResIRM effectively reinforces the features in damaged regions.http://jam.biam.ac.cn/article/doi/10.11868/j.issn.1005-5053.2023.000189convolutional neural network (cnn)non-destructive testing (ndt)damage reconstructionultrasonic testing |
| spellingShingle | WU Xiangnan CHENG Xiaojin LI Qixin SHANG Jianhua Research on algorithm for improving imaging accuracy of CFRP low speed impact damage Journal of Aeronautical Materials convolutional neural network (cnn) non-destructive testing (ndt) damage reconstruction ultrasonic testing |
| title | Research on algorithm for improving imaging accuracy of CFRP low speed impact damage |
| title_full | Research on algorithm for improving imaging accuracy of CFRP low speed impact damage |
| title_fullStr | Research on algorithm for improving imaging accuracy of CFRP low speed impact damage |
| title_full_unstemmed | Research on algorithm for improving imaging accuracy of CFRP low speed impact damage |
| title_short | Research on algorithm for improving imaging accuracy of CFRP low speed impact damage |
| title_sort | research on algorithm for improving imaging accuracy of cfrp low speed impact damage |
| topic | convolutional neural network (cnn) non-destructive testing (ndt) damage reconstruction ultrasonic testing |
| url | http://jam.biam.ac.cn/article/doi/10.11868/j.issn.1005-5053.2023.000189 |
| work_keys_str_mv | AT wuxiangnan researchonalgorithmforimprovingimagingaccuracyofcfrplowspeedimpactdamage AT chengxiaojin researchonalgorithmforimprovingimagingaccuracyofcfrplowspeedimpactdamage AT liqixin researchonalgorithmforimprovingimagingaccuracyofcfrplowspeedimpactdamage AT shangjianhua researchonalgorithmforimprovingimagingaccuracyofcfrplowspeedimpactdamage |