Enhancing Material Characterization: Multifidelity Deep Neural Network for Stress–Strain Curve Prediction From Small Punch Test Data
IEEE Transactions on Instrumentation and Measurement · 2026 · 75 · 1-14
DOI: 10.1109/tim.2026.3676176 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Instrumentation and Measurement, 2026. Verfasst von Zhengni Yang und 8 weiteren Autor:innen. Die Arbeit nennt 48 Literaturangaben. Gefördert von: Jiangsu Provincial Scientific Research Center of Applied Mathematics, Jiangsu Provincial Qinglan Project and Suzhou Science and Technology Program.
Abstract (Originalsprache)
The accurate determination of a material’s true stress–strain relationship is crucial for predicting its performance in engineering applications. However, traditional methods for determining material behavior often depend on extensive experiments. Although these methods are essential, they are inherently complex, time-consuming, and often suffer from limited accuracy and reliability when small sample sizes are involved. To address these challenges, this article introduces a multifidelity deep neural network architecture that utilizes both low-fidelity and high-fidelity datasets to predict true stress–strain curves from small punch test (SPT) data. The low-fidelity data are calculated using an empirical function based on the Swift model, providing an initial understanding of material behavior. In contrast, the finite element method (FEM) provides high-fidelity data, enhancing the model’s ability to capture complex material characteristics. This framework merges low-fidelity and high-fidelity networks to estimate mechanical properties with low-fidelity and high-fidelity data. The effectiveness of the proposed approach has been demonstrated through experimental validation, highlighting its exceptional ability to generalize across material thicknesses and properties beyond the training set. The proposed approach outperformed traditional empirical methods and maintained strong performance even when applied to real-world materials.
Förderung
- Jiangsu Provincial Scientific Research Center of Applied Mathematics
- Jiangsu Provincial Qinglan Project and Suzhou Science and Technology Program
Zitieren
APA
Yang, Z., Yang, R., Han, W., Kang, W., Chen, X., Dong, R., Zhang, J., Tong, C., & Kong, J. (2026). Enhancing Material Characterization: Multifidelity Deep Neural Network for Stress–Strain Curve Prediction From Small Punch Test Data. IEEE Transactions on Instrumentation and Measurement, 75, 1-14. https://doi.org/10.1109/tim.2026.3676176
Vancouver
Yang Z, Yang R, Han W, Kang W, Chen X, Dong R, et al. Enhancing Material Characterization: Multifidelity Deep Neural Network for Stress–Strain Curve Prediction From Small Punch Test Data. IEEE Transactions on Instrumentation and Measurement. 2026;75:1-14. doi:10.1109/tim.2026.3676176
BibTeX
@article{Yang2026,
author = {Yang, Zhengni and Yang, Rui and Han, Weijian and Kang, Wenyuan and Chen, Xiaohan and Dong, Ruihan and Zhang, Jingyi and Tong, Chao and Kong, Jingyu},
title = {Enhancing Material Characterization: Multifidelity Deep Neural Network for Stress–Strain Curve Prediction From Small Punch Test Data},
journal = {IEEE Transactions on Instrumentation and Measurement},
year = {2026},
volume = {75},
pages = {1--14},
doi = {10.1109/tim.2026.3676176}
}
EUVIMED