A physics‐informed neural network framework based on fatigue indicator parameters for very high cycle fatigue life prediction of an additively manufactured titanium alloy
Fatigue & Fracture of Engineering Materials & Structures · 2024-09 · 47 (9) · 3171-3188
DOI: 10.1111/ffe.14363 ↗Kurz gefasst
Fachartikel in der Zeitschrift Fatigue & Fracture of Engineering Materials & Structures, online erschienen am 17.06.2024. Verfasst von Hang Li und 4 weiteren Autor:innen. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 57 Literaturangaben. Gefördert von: National Natural Science Foundation of China, National Major Science and Technology Projects of China.
Abstract (Originalsprache)
The exploitation of fatigue life prediction methods based on fatigue indicator parameters revealed the influence of the defect size, position, and morphology on the fatigue life and fatigue behavior of additively manufactured metals. Meanwhile, Data‐driven life prediction methods are time‐efficient but inexplainable. Current machine learning‐based fatigue life prediction methods call for not only the accuracy but also the interpretability and stability of prediction results. Thus, the fusion of physical methods and machine learning methods has been a prevailing research topic in fatigue life prediction. In this study, a novel physics‐informed neural network framework is proposed by integrating a fatigue indicator parameter based on defects into the physical constraints term of a loss function. This method outperforms conventional machine learning methods in high‐cycle and very high‐cycle regimes, exhibiting superior prediction performance and generalization ability. Furthermore, the prediction results can be explained from a physical standpoint, correlating with the applicability range of the introduced physical equation describing defect positions.
Förderung
- National Natural Science Foundation of China
- National Major Science and Technology Projects of China
Zitieren
APA
Li, H., Sun, G., Tian, Z., Huang, K., & Zhao, Z. (2024). A physics‐informed neural network framework based on fatigue indicator parameters for very high cycle fatigue life prediction of an additively manufactured titanium alloy. Fatigue & Fracture of Engineering Materials & Structures, 47(9), 3171-3188. https://doi.org/10.1111/ffe.14363
Vancouver
Li H, Sun G, Tian Z, Huang K, Zhao Z. A physics‐informed neural network framework based on fatigue indicator parameters for very high cycle fatigue life prediction of an additively manufactured titanium alloy. Fatigue & Fracture of Engineering Materials & Structures. 2024;47(9):3171-3188. doi:10.1111/ffe.14363
BibTeX
@article{Li2024,
author = {Li, Hang and Sun, Guanze and Tian, Zhao and Huang, Kezhi and Zhao, Zihua},
title = {A physics‐informed neural network framework based on fatigue indicator parameters for very high cycle fatigue life prediction of an additively manufactured titanium alloy},
journal = {Fatigue & Fracture of Engineering Materials & Structures},
year = {2024},
volume = {47},
number = {9},
pages = {3171--3188},
doi = {10.1111/ffe.14363}
}
EUVIMED