File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1111/ffe.13693
- Scopus: eid_2-s2.0-85127616582
- WOS: WOS:000781012900001
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Artificial intelligence-assisted fatigue fracture recognition based on morphing and fully convolutional networks
Title | Artificial intelligence-assisted fatigue fracture recognition based on morphing and fully convolutional networks |
---|---|
Authors | |
Keywords | artificial intelligence failure analysis fatigue fracture fully convolutional network mask R-CNN morphing-based data augmentation |
Issue Date | 2022 |
Citation | Fatigue and Fracture of Engineering Materials and Structures, 2022, v. 45, n. 6, p. 1690-1702 How to Cite? |
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. |
Persistent Identifier | http://hdl.handle.net/10722/329798 |
ISSN | 2023 Impact Factor: 3.1 2023 SCImago Journal Rankings: 0.737 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lyu, Yetao | - |
dc.contributor.author | Yang, Zi | - |
dc.contributor.author | Liang, Hao | - |
dc.contributor.author | Zhang, Beini | - |
dc.contributor.author | Ge, Ming | - |
dc.contributor.author | Liu, Rui | - |
dc.contributor.author | Zhang, Zhefeng | - |
dc.contributor.author | Yang, Haokun | - |
dc.date.accessioned | 2023-08-09T03:35:24Z | - |
dc.date.available | 2023-08-09T03:35:24Z | - |
dc.date.issued | 2022 | - |
dc.identifier.citation | Fatigue and Fracture of Engineering Materials and Structures, 2022, v. 45, n. 6, p. 1690-1702 | - |
dc.identifier.issn | 8756-758X | - |
dc.identifier.uri | http://hdl.handle.net/10722/329798 | - |
dc.description.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. | - |
dc.language | eng | - |
dc.relation.ispartof | Fatigue and Fracture of Engineering Materials and Structures | - |
dc.subject | artificial intelligence | - |
dc.subject | failure analysis | - |
dc.subject | fatigue fracture | - |
dc.subject | fully convolutional network | - |
dc.subject | mask R-CNN | - |
dc.subject | morphing-based data augmentation | - |
dc.title | Artificial intelligence-assisted fatigue fracture recognition based on morphing and fully convolutional networks | - |
dc.type | Article | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1111/ffe.13693 | - |
dc.identifier.scopus | eid_2-s2.0-85127616582 | - |
dc.identifier.volume | 45 | - |
dc.identifier.issue | 6 | - |
dc.identifier.spage | 1690 | - |
dc.identifier.epage | 1702 | - |
dc.identifier.eissn | 1460-2695 | - |
dc.identifier.isi | WOS:000781012900001 | - |