Image-driven prediction of fatigue crack growth in metal materials via spatiotemporal neural network DOI
J.M. Liang,

Yin Yu,

Yile Hu

и другие.

Engineering Fracture Mechanics, Год журнала: 2024, Номер 310, С. 110442 - 110442

Опубликована: Сен. 1, 2024

Язык: Английский

Multimodal Data Fusion Enhanced Deep Learning Prediction of Crack Path Segmentation in CFRP Composites DOI
Peng Zhang, Keke Tang, Guangxu Chen

и другие.

Composites Science and Technology, Год журнала: 2024, Номер 257, С. 110812 - 110812

Опубликована: Авг. 13, 2024

Язык: Английский

Процитировано

9
A novel machine-learning based framework for calibrating micromechanical fracture model of ultra-low cycle fatigue in steel structures DOI
Mingming Yu, Xu Xie, Zhiyuan Fang

и другие.

Engineering Fracture Mechanics, Год журнала: 2024, Номер 306, С. 110200 - 110200

Опубликована: Май 31, 2024

Язык: Английский

Процитировано

8
Impact of cryogenic machining on the fatigue strength and surface integrity of wrought Ti6Al4V with equiaxed microstructure DOI
Rachele Bertolini,

Andrea Stramare,

Stefania Bruschi

и другие.

Engineering Failure Analysis, Год журнала: 2025, Номер 170, С. 109274 - 109274

Опубликована: Янв. 6, 2025

Язык: Английский

Процитировано

1
A GAN-based stepwise full-field mechanical prediction model for architected metamaterials DOI
Yujie Xiang, Jixin Hou, Xianyan Chen

и другие.

International Journal of Mechanical Sciences, Год журнала: 2024, Номер 284, С. 109771 - 109771

Опубликована: Окт. 8, 2024

Язык: Английский

Процитировано

3
Microstructural evolution and prediction of TC18 titanium alloys by high-throughput technology and machine learning DOI
Xingang Liu,

Haozhe Niu,

Shao Yang Zhao

и другие.

Journal of Alloys and Compounds, Год журнала: 2025, Номер 1017, С. 179202 - 179202

Опубликована: Фев. 1, 2025

Язык: Английский

Процитировано

0
Mechanism investigation of anisotropy in impact fatigue property of laser-deposited Ti-6Al-4V DOI
Sihan Zhao, Kangbo Yuan,

Boli Li

и другие.

International Journal of Fatigue, Год журнала: 2025, Номер unknown, С. 108906 - 108906

Опубликована: Март 1, 2025

Язык: Английский

Процитировано

0
A TCN-based feature fusion framework for multiaxial fatigue life prediction: Bridging loading dynamics and material characteristics DOI
Peng Zhang, Keke Tang

International Journal of Fatigue, Год журнала: 2025, Номер unknown, С. 108915 - 108915

Опубликована: Март 1, 2025

Язык: Английский

Процитировано

0
Trustworthy Contextual Neural Networks for Deciphering Fracture in Metals DOI
Dharanidharan Arumugam, Ravi Kiran

Fatigue & Fracture of Engineering Materials & Structures, Год журнала: 2025, Номер unknown

Опубликована: Май 24, 2025

ABSTRACT A novel approach was proposed and implemented to assess the confidence of individual class predictions made by convolutional neural networks trained identify type fracture in metals. This involves utilizing contextual evidence form images scores, which serve as indicators for determining certainty predictions. first tested on both shallow deep employing four publicly available image datasets: MNIST, EMNIST, FMNIST, CIFAR10, subsequently validated an in‐house steel dataset—FRAC, containing ductile brittle images. The effectiveness method is producing scores data other datasets selected from datasets. CIFAR‐10 dataset yielded lowest mean score 78 model, with over 50% representative test instances receiving a below 90, indicating lower model's In contrast, CNN model used achieved 99, 0% suggesting high level its enhances interpretability provides greater insight into their outputs.

Язык: Английский

Процитировано

0
Graphical Feature Construction-Based Deep Learning Model for Fatigue Life Prediction of AM Alloys DOI Open Access
Hao Wu, Anbin Wang, Zhiqiang Gan

и другие.

Materials, Год журнала: 2024, Номер 18(1), С. 11 - 11

Опубликована: Дек. 24, 2024

Fatigue failure poses a serious challenge for ensuring the operational safety of critical components subjected to cyclic/random loading. In this context, various machine learning (ML) models have been increasingly explored, due their effectiveness in analyzing relationship between fatigue life and multiple influencing factors. Nevertheless, existing ML hinge heavily on numeric features as inputs, which encapsulate limited information process interest. To cure deficiency, novel model based upon convolutional neural networks is developed, where are transformed into graphical ones by introducing two enrichment operations, namely, Shapley Additive Explanations Pearson correlation coefficient analysis. Additionally, attention mechanism introduced prioritize important regions image-based inputs. Extensive validations using experimental results laser powder bed fusion-fabricated metals demonstrate that proposed possesses better predictive accuracy than conventional models.

Язык: Английский

Процитировано

2
Image-driven prediction of fatigue crack growth in metal materials via spatiotemporal neural network DOI
J.M. Liang,

Yin Yu,

Yile Hu

и другие.

Engineering Fracture Mechanics, Год журнала: 2024, Номер 310, С. 110442 - 110442

Опубликована: Сен. 1, 2024

Язык: Английский

Процитировано

0