Deep learning-based detection method for analysis of high-pressure hydrogen induced damage in acrylonitrile butadiene rubber for hydrogen mobility
The increasing use of high-pressure hydrogen gas has heightened the need to understand material behavior in hydrogen-rich environments. Recent studies have shown that examining the pore-shaped damage in the cross-section of rubber materials exposed to high-pressure hydrogen can provide valuable insi...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-11-01
|
| Series: | Materials & Design |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S0264127523008857 |
| _version_ | 1797526276472307712 |
|---|---|
| author | Sang Min Lee Byeong-Lyul Choi Un Bong Baek Byoung-Ho Choi |
| author_facet | Sang Min Lee Byeong-Lyul Choi Un Bong Baek Byoung-Ho Choi |
| author_sort | Sang Min Lee |
| collection | DOAJ |
| description | The increasing use of high-pressure hydrogen gas has heightened the need to understand material behavior in hydrogen-rich environments. Recent studies have shown that examining the pore-shaped damage in the cross-section of rubber materials exposed to high-pressure hydrogen can provide valuable insights into their resistance to such environments. This paper introduces an approach for training a deep learning model to detect hydrogen-induced pore-shaped damage. The study proposes a semi-automated labeling method and employs a modified faster R-CNN, implementing ResNet50-D, aspectual anchor box optimization, and dataset augmentation. To conduct the testing to validate the proposed method, acrylonitrile butadiene rubber was exposed to hydrogen at 96.6 MPa for 24 h. The dataset was created by analyzing damaged cross-sections using a scanning electron microscope. The detection results demonstrate that the proposed method outperforms both traditional and data-based conventional methods. |
| first_indexed | 2024-03-10T09:26:57Z |
| format | Article |
| id | doaj.art-c2497faa97eb472b9033087430ea95ca |
| institution | Directory Open Access Journal |
| issn | 0264-1275 |
| language | English |
| last_indexed | 2024-03-10T09:26:57Z |
| publishDate | 2023-11-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Materials & Design |
| spelling | doaj.art-c2497faa97eb472b9033087430ea95ca2023-11-22T04:46:36ZengElsevierMaterials & Design0264-12752023-11-01235112470Deep learning-based detection method for analysis of high-pressure hydrogen induced damage in acrylonitrile butadiene rubber for hydrogen mobilitySang Min Lee0Byeong-Lyul Choi1Un Bong Baek2Byoung-Ho Choi3School of Mechanical Engineering, College of Engineering, Korea University, Seoul 02841, South KoreaSchool of Mechanical Engineering, College of Engineering, Korea University, Seoul 02841, South KoreaKorea Research Institute of Standards and Science, Daejeon 34113, South KoreaSchool of Mechanical Engineering, College of Engineering, Korea University, Seoul 02841, South Korea; Corresponding author.The increasing use of high-pressure hydrogen gas has heightened the need to understand material behavior in hydrogen-rich environments. Recent studies have shown that examining the pore-shaped damage in the cross-section of rubber materials exposed to high-pressure hydrogen can provide valuable insights into their resistance to such environments. This paper introduces an approach for training a deep learning model to detect hydrogen-induced pore-shaped damage. The study proposes a semi-automated labeling method and employs a modified faster R-CNN, implementing ResNet50-D, aspectual anchor box optimization, and dataset augmentation. To conduct the testing to validate the proposed method, acrylonitrile butadiene rubber was exposed to hydrogen at 96.6 MPa for 24 h. The dataset was created by analyzing damaged cross-sections using a scanning electron microscope. The detection results demonstrate that the proposed method outperforms both traditional and data-based conventional methods.http://www.sciencedirect.com/science/article/pii/S0264127523008857Nitrile butadiene rubberSilica fillerResistance to high pressure-hydrogenDeep learningObject detectionFaster R-CNN |
| spellingShingle | Sang Min Lee Byeong-Lyul Choi Un Bong Baek Byoung-Ho Choi Deep learning-based detection method for analysis of high-pressure hydrogen induced damage in acrylonitrile butadiene rubber for hydrogen mobility Materials & Design Nitrile butadiene rubber Silica filler Resistance to high pressure-hydrogen Deep learning Object detection Faster R-CNN |
| title | Deep learning-based detection method for analysis of high-pressure hydrogen induced damage in acrylonitrile butadiene rubber for hydrogen mobility |
| title_full | Deep learning-based detection method for analysis of high-pressure hydrogen induced damage in acrylonitrile butadiene rubber for hydrogen mobility |
| title_fullStr | Deep learning-based detection method for analysis of high-pressure hydrogen induced damage in acrylonitrile butadiene rubber for hydrogen mobility |
| title_full_unstemmed | Deep learning-based detection method for analysis of high-pressure hydrogen induced damage in acrylonitrile butadiene rubber for hydrogen mobility |
| title_short | Deep learning-based detection method for analysis of high-pressure hydrogen induced damage in acrylonitrile butadiene rubber for hydrogen mobility |
| title_sort | deep learning based detection method for analysis of high pressure hydrogen induced damage in acrylonitrile butadiene rubber for hydrogen mobility |
| topic | Nitrile butadiene rubber Silica filler Resistance to high pressure-hydrogen Deep learning Object detection Faster R-CNN |
| url | http://www.sciencedirect.com/science/article/pii/S0264127523008857 |
| work_keys_str_mv | AT sangminlee deeplearningbaseddetectionmethodforanalysisofhighpressurehydrogeninduceddamageinacrylonitrilebutadienerubberforhydrogenmobility AT byeonglyulchoi deeplearningbaseddetectionmethodforanalysisofhighpressurehydrogeninduceddamageinacrylonitrilebutadienerubberforhydrogenmobility AT unbongbaek deeplearningbaseddetectionmethodforanalysisofhighpressurehydrogeninduceddamageinacrylonitrilebutadienerubberforhydrogenmobility AT byounghochoi deeplearningbaseddetectionmethodforanalysisofhighpressurehydrogeninduceddamageinacrylonitrilebutadienerubberforhydrogenmobility |