Efficient Near-Field Radiofrequency Imaging of Impact Damage on CFRP Materials with Learning-Based Compressed Sensing
Carbon fiber-reinforced polymer (CFRP) is a widely-used composite material that is vulnerable to impact damage. Light impact damages destroy the inner structure but barely show obvious change on the surface. As a non-contact and high-resolution method to detect subsurface and inner defect, near-fiel...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-08-01
|
| Series: | Materials |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1944/15/17/5874 |
| _version_ | 1797494580215545856 |
|---|---|
| author | Huadong Song Zijun Wang Yanli Zeng Xiaoting Guo Chaoqing Tang |
| author_facet | Huadong Song Zijun Wang Yanli Zeng Xiaoting Guo Chaoqing Tang |
| author_sort | Huadong Song |
| collection | DOAJ |
| description | Carbon fiber-reinforced polymer (CFRP) is a widely-used composite material that is vulnerable to impact damage. Light impact damages destroy the inner structure but barely show obvious change on the surface. As a non-contact and high-resolution method to detect subsurface and inner defect, near-field radiofrequency imaging (NRI) suffers from high imaging times. Although some existing works use compressed sensing (CS) for a faster measurement, the corresponding CS reconstruction time remains high. This paper proposes a deep learning-based CS method for fast NRI, this plugin method decreases the measurement time by one order of magnitude without hardware modification and achieves real-time imaging during CS reconstruction. A special 0/1-Bernoulli measurement matrix is designed for sensor scanning firstly, and an interpretable neural network-based CS reconstruction method is proposed. Besides real-time reconstruction, the proposed learning-based reconstruction method can further reduce the required data thus reducing measurement time more than existing CS methods. Under the same imaging quality, experimental results in an NRI system show the proposed method is 20 times faster than traditional raster scan and existing CS reconstruction methods, and the required data is reduced by more than 90% than existing CS reconstruction methods. |
| first_indexed | 2024-03-10T01:36:22Z |
| format | Article |
| id | doaj.art-4f791e6deab54a17915a9dc38c8f58bc |
| institution | Directory Open Access Journal |
| issn | 1996-1944 |
| language | English |
| last_indexed | 2024-03-10T01:36:22Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Materials |
| spelling | doaj.art-4f791e6deab54a17915a9dc38c8f58bc2023-11-23T13:31:41ZengMDPI AGMaterials1996-19442022-08-011517587410.3390/ma15175874Efficient Near-Field Radiofrequency Imaging of Impact Damage on CFRP Materials with Learning-Based Compressed SensingHuadong Song0Zijun Wang1Yanli Zeng2Xiaoting Guo3Chaoqing Tang4SINOMACH Sensing Technology Co., Ltd., Shenyang 110043, ChinaSINOMACH Sensing Technology Co., Ltd., Shenyang 110043, ChinaSINOMACH Sensing Technology Co., Ltd., Shenyang 110043, ChinaSINOMACH Sensing Technology Co., Ltd., Shenyang 110043, ChinaSchool of Artificial Intelligence and Automation, Huazhong University of Science and Technology (HUST), Wuhan 430074, ChinaCarbon fiber-reinforced polymer (CFRP) is a widely-used composite material that is vulnerable to impact damage. Light impact damages destroy the inner structure but barely show obvious change on the surface. As a non-contact and high-resolution method to detect subsurface and inner defect, near-field radiofrequency imaging (NRI) suffers from high imaging times. Although some existing works use compressed sensing (CS) for a faster measurement, the corresponding CS reconstruction time remains high. This paper proposes a deep learning-based CS method for fast NRI, this plugin method decreases the measurement time by one order of magnitude without hardware modification and achieves real-time imaging during CS reconstruction. A special 0/1-Bernoulli measurement matrix is designed for sensor scanning firstly, and an interpretable neural network-based CS reconstruction method is proposed. Besides real-time reconstruction, the proposed learning-based reconstruction method can further reduce the required data thus reducing measurement time more than existing CS methods. Under the same imaging quality, experimental results in an NRI system show the proposed method is 20 times faster than traditional raster scan and existing CS reconstruction methods, and the required data is reduced by more than 90% than existing CS reconstruction methods.https://www.mdpi.com/1996-1944/15/17/5874non-destructive testingnear-field radiofrequency imagingcompressed sensingdeep learning |
| spellingShingle | Huadong Song Zijun Wang Yanli Zeng Xiaoting Guo Chaoqing Tang Efficient Near-Field Radiofrequency Imaging of Impact Damage on CFRP Materials with Learning-Based Compressed Sensing Materials non-destructive testing near-field radiofrequency imaging compressed sensing deep learning |
| title | Efficient Near-Field Radiofrequency Imaging of Impact Damage on CFRP Materials with Learning-Based Compressed Sensing |
| title_full | Efficient Near-Field Radiofrequency Imaging of Impact Damage on CFRP Materials with Learning-Based Compressed Sensing |
| title_fullStr | Efficient Near-Field Radiofrequency Imaging of Impact Damage on CFRP Materials with Learning-Based Compressed Sensing |
| title_full_unstemmed | Efficient Near-Field Radiofrequency Imaging of Impact Damage on CFRP Materials with Learning-Based Compressed Sensing |
| title_short | Efficient Near-Field Radiofrequency Imaging of Impact Damage on CFRP Materials with Learning-Based Compressed Sensing |
| title_sort | efficient near field radiofrequency imaging of impact damage on cfrp materials with learning based compressed sensing |
| topic | non-destructive testing near-field radiofrequency imaging compressed sensing deep learning |
| url | https://www.mdpi.com/1996-1944/15/17/5874 |
| work_keys_str_mv | AT huadongsong efficientnearfieldradiofrequencyimagingofimpactdamageoncfrpmaterialswithlearningbasedcompressedsensing AT zijunwang efficientnearfieldradiofrequencyimagingofimpactdamageoncfrpmaterialswithlearningbasedcompressedsensing AT yanlizeng efficientnearfieldradiofrequencyimagingofimpactdamageoncfrpmaterialswithlearningbasedcompressedsensing AT xiaotingguo efficientnearfieldradiofrequencyimagingofimpactdamageoncfrpmaterialswithlearningbasedcompressedsensing AT chaoqingtang efficientnearfieldradiofrequencyimagingofimpactdamageoncfrpmaterialswithlearningbasedcompressedsensing |