EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Stress Field Prediction and DIC-Informed Spatial Regularization for AlSi10Mg Alloy Tensile Specimens Based on Graph Neural Networks

Zhongying Dong, Xingbo Xie, Guili Yang, Zhangdong Li, Xinghua Li, Huayuan Ma

Materials · 19.09.2026 · 19 (18) · 3979

DOI: 10.3390/ma19183979 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Materials, online erschienen am 19.09.2026. Verfasst von Zhongying Dong und 5 weiteren Autor:innen. Beteiligte Einrichtung: College of Field Engineering, Army Engineering University of PLA, Nanjing 210007, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

High-fidelity finite-element (FE) simulation of nonlinear full-field responses in AlSi10Mg tensile specimens is computationally expensive, while the available digital image correlation (DIC) data in this study consist only of engineering-strain screenshots rather than exportable numerical fields. This work therefore develops a simulation-to-experiment framework for rapid full-field stress prediction and weakly supervised DIC-informed spatial regularization. Two hundred independent Abaqus/Explicit loading cases generated 5600 graph samples, which were used to train an eight-layer FiLM-conditioned graph neural network for nodal von Mises stress and three-component displacement prediction, together with a decoupled structured force–displacement branch. On independent FE tests, von Mises stress prediction achieved R2 = 0.9984 with an RMSE of 4.60 MPa, while the dense force–displacement curve achieved R2 = 0.9957 and RMSE = 59.70 N. Five machine tensile tests gave mean pre-fracture curve NRMSEs of 4.40% for FE versus experiment and 5.31% for GNN versus experiment. On independent specimens L-7 and L-8, the constrained adapter reduced DIC spatial shape loss by 3.21% with a mean absolute stress correction of 0.232 MPa. The framework therefore provides rapid FE-surrogate prediction with conservative experiment-informed spatial regularization rather than experimental stress inversion.

Schlagwörter

Stichwörter der Autor:innen

AlSi10MgDIC-informed spatial regularizationablation studydigital image correlationfull-field stress predictiongraph neural network

Autor:innen und Institutionen

  • College of Field Engineering, Army Engineering University of PLA, Nanjing 210007, China.

Zitieren

APA

Dong, Z., Xie, X., Yang, G., Li, Z., Li, X., & Ma, H. (2026). Stress Field Prediction and DIC-Informed Spatial Regularization for AlSi10Mg Alloy Tensile Specimens Based on Graph Neural Networks. Materials, 19(18), 3979. https://doi.org/10.3390/ma19183979

Vancouver

Dong Z, Xie X, Yang G, Li Z, Li X, Ma H. Stress Field Prediction and DIC-Informed Spatial Regularization for AlSi10Mg Alloy Tensile Specimens Based on Graph Neural Networks. Materials. 2026;19(18):3979. doi:10.3390/ma19183979

BibTeX
@article{Dong2026,
  author = {Dong, Zhongying and Xie, Xingbo and Yang, Guili and Li, Zhangdong and Li, Xinghua and Ma, Huayuan},
  title = {Stress Field Prediction and DIC-Informed Spatial Regularization for AlSi10Mg Alloy Tensile Specimens Based on Graph Neural Networks},
  journal = {Materials},
  year = {2026},
  volume = {19},
  number = {18},
  pages = {3979},
  doi = {10.3390/ma19183979}
}
Kostenlos starten →