EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Individualized Prediction of In-Plane Shear Stress–Strain Curves for Composites Using Early-Stage Digital Image Correlation Strain Fields

Chongyu Ruan, Maowen Yao, Xiangyu Zhao, Zhisheng Yu, Guangwu Fang iD

Materials · 17.06.2026 · 19 (12) · 2609

DOI: 10.3390/ma19122609 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Materials, online erschienen am 17.06.2026. Verfasst von Chongyu Ruan und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of General Aviation and Flight, Nanjing University of Aeronautics and Astronautics, Liyang 213300, China. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Key Laboratory of Inlet and Exhaust Technology, Ministry of Education.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The in-plane shear performance of carbon fiber-reinforced polymer (CFRP) composites is critical for structural design but is challenged by significant property scatter. This study aims to achieve individualized prediction of the complete shear stress–strain curve for each composite specimen using only a single early-stage digital image correlation (DIC) strain field. Systematic in-plane shear tests were conducted on 45 laminated carbon fiber/epoxy specimens with synchronized full-field DIC data and macroscopic load–displacement records. A lightweight encoder–decoder convolutional neural network was developed, taking a single DIC strain contour map at 0.2% global strain as input and mapping it directly to the full-range stress–strain curve up to failure for that specific specimen. Data augmentation and Dropout regularization mitigated the small-sample challenge. The proposed model achieved strong predictive performance across the five-fold cross-validation yielded a mean R2 of 0.926 ± 0.022 and a mean RMSE of 6.37 ± 1.14 MPa for stress. Individual specimen predictions on the test set yielded an average R2 of 0.945, with a minimum of 0.821, confirming robust capability across scattered properties. Residual analysis elucidated error characteristics across deformation stages. This research provides a novel paradigm for non-destructive, early-stage individualized assessment of composite mechanical properties, with applications in structural health monitoring and probabilistic design.

Schlagwörter

Stichwörter der Autor:innen

CFRPV-notched shear testconvolutional neural networknon-destructive evaluationproperty scatter

Autor:innen und Institutionen

  • College of General Aviation and Flight, Nanjing University of Aeronautics and Astronautics, Liyang 213300, China.
  • Key Laboratory of Aero-Engine Thermal Environment and Structure, Ministry of Industry and Information Technology, College of Energy and Power Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 2100…

ORCID-Profile: Guangwu Fang

Förderung

  • Key Laboratory of Inlet and Exhaust Technology, Ministry of Education

Zitieren

APA

Ruan, C., Yao, M., Zhao, X., Yu, Z., & Fang, G. (2026). Individualized Prediction of In-Plane Shear Stress–Strain Curves for Composites Using Early-Stage Digital Image Correlation Strain Fields. Materials, 19(12), 2609. https://doi.org/10.3390/ma19122609

Vancouver

Ruan C, Yao M, Zhao X, Yu Z, Fang G. Individualized Prediction of In-Plane Shear Stress–Strain Curves for Composites Using Early-Stage Digital Image Correlation Strain Fields. Materials. 2026;19(12):2609. doi:10.3390/ma19122609

BibTeX
@article{Ruan2026,
  author = {Ruan, Chongyu and Yao, Maowen and Zhao, Xiangyu and Yu, Zhisheng and Fang, Guangwu},
  title = {Individualized Prediction of In-Plane Shear Stress–Strain Curves for Composites Using Early-Stage Digital Image Correlation Strain Fields},
  journal = {Materials},
  year = {2026},
  volume = {19},
  number = {12},
  pages = {2609},
  doi = {10.3390/ma19122609}
}
Kostenlos starten →