Artificial intelligence-assisted fatigue fracture recognition based on morphing and fully convolutional networks | |
Lyu, Yetao1; Yang, Zi1; Liang, Hao2; Zhang, Beini3; Ge, Ming4; Liu, Rui5; Zhang, Zhefeng5; Yang, Haokun2 | |
Corresponding Author | Lyu, Yetao(aaronlyu@hkpc.org) ; Yang, Haokun(hkyang@hkpc.org) |
2022-04-06 | |
Source Publication | FATIGUE & FRACTURE OF ENGINEERING MATERIALS & STRUCTURES
![]() |
ISSN | 8756-758X |
Pages | 13 |
Abstract | Fatigue fracture is one of the most common metallic component failure cases in manufacturing industries. The observation on fractography can provide direct evidence for failure analysis. In this study, an image semantic segmentation method based on fully convolutional networks (FCNs) was proposed to figure out the boundary between fatigue crack propagation and fast fracture regions from optical microscope (OM) fractography images. Furthermore, a novel morphing-based data augmentation method was adopted to enable few-shot learning of sample images. The proposed framework can successfully segment two categories, namely, the crack propagation and fast fracture regions, thus differentiating the boundary of two regions in one image. This artificial intelligence (AI)-assisted fatigue analysis architecture can complete the failure analysis procedure in 0.5 s and prove the feasibility of fatigue failure analysis. The segmentation accuracy of self-developed network achieves 95.4% for the fatigue crack propagation region, as well as 97.2% for the fast fracture region. Not only for semantic segmentation DNN, we also prove that our novel data augmentation method can applied at the instance segmentation DNN, such as mask regional convolutional neural network (mask R-CNN), one state-of-the-art deep learning network for instance segmentation, to achieve similar accuracy. |
Keyword | artificial intelligence failure analysis fatigue fracture fully convolutional network mask R-CNN morphing-based data augmentation |
Funding Organization | CRD Program of Hong Kong Productivity Council ; Shenzhen Institute of Artificial Intelligence and Robotics for Society ; National Natural Science Foundation of China (NSFC) |
DOI | 10.1111/ffe.13693 |
Indexed By | SCI |
Language | 英语 |
Funding Project | CRD Program of Hong Kong Productivity Council[10008787] ; CRD Program of Hong Kong Productivity Council[10009455] ; Shenzhen Institute of Artificial Intelligence and Robotics for Society[AC01202005025] ; National Natural Science Foundation of China (NSFC)[51901230] |
WOS Research Area | Engineering ; Materials Science |
WOS Subject | Engineering, Mechanical ; Materials Science, Multidisciplinary |
WOS ID | WOS:000781012900001 |
Publisher | WILEY |
Citation statistics | |
Document Type | 期刊论文 |
Identifier | http://ir.imr.ac.cn/handle/321006/172810 |
Collection | 中国科学院金属研究所 |
Corresponding Author | Lyu, Yetao; Yang, Haokun |
Affiliation | 1.Hong Kong Prod Council HKPC, Robot & Artificial Intelligence Div, Hong Kong, Peoples R China 2.Hong Kong Prod Council HKPC, Smart Mfg Div, Hong Kong, Peoples R China 3.Hong Kong Univ Sci & Technol HKUST, Dept Phys, Hong Kong, Peoples R China 4.Hong Kong Ind Artificial Intelligence & Robot Ctr, Hong Kong, Peoples R China 5.Chinese Acad Sci, Shi Changxu Innovat Ctr Adv Mat, Inst Met Res, Shenyang, Peoples R China |
Recommended Citation GB/T 7714 | Lyu, Yetao,Yang, Zi,Liang, Hao,et al. Artificial intelligence-assisted fatigue fracture recognition based on morphing and fully convolutional networks[J]. FATIGUE & FRACTURE OF ENGINEERING MATERIALS & STRUCTURES,2022:13. |
APA | Lyu, Yetao.,Yang, Zi.,Liang, Hao.,Zhang, Beini.,Ge, Ming.,...&Yang, Haokun.(2022).Artificial intelligence-assisted fatigue fracture recognition based on morphing and fully convolutional networks.FATIGUE & FRACTURE OF ENGINEERING MATERIALS & STRUCTURES,13. |
MLA | Lyu, Yetao,et al."Artificial intelligence-assisted fatigue fracture recognition based on morphing and fully convolutional networks".FATIGUE & FRACTURE OF ENGINEERING MATERIALS & STRUCTURES (2022):13. |
Files in This Item: | There are no files associated with this item. |
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment