EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

1D Stress Evolution Prediction via Thermodynamically-Informed Neural Networks

Alireza Fallahnejad, Emin Semih Perdahcioglu, Ton van den Boogaard

Solid State Phenomena · 17.04.2026 · 390 · 51-61

DOI: 10.4028/p-vj1far ↗

Kurz gefasst

Fachartikel in der Zeitschrift Solid State Phenomena, online erschienen am 17.04.2026. Verfasst von Alireza Fallahnejad und 2 weiteren Autor:innen. Die Arbeit nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate modeling of elastoplastic behavior is crucial for forming simulations, yet conventional constitutive laws require extensive calibration and often fail to generalize across diverse loading paths. To address this limitation, a thermodynamically informed neural-network framework is proposed for predicting one-dimensional stress evolution. The model integrates physical consistency into a data-driven formulation by coupling two neural components: one learns the state evolution, predicting increments of the internal variable, while the other approximates the Helmholtz free-energy potential, from which stresses are obtained via automatic differentiation. Synthetic datasets generated from randomized strain paths with power-law hardening were used for training, ensuring broad coverage of nonlinear responses. The model successfully reproduces monotonic, unloading, reverse, and random loading behaviors with minimal error accumulation and stable recursive inference. Owing to its incremental formulation, the framework maintains predictive accuracy beyond the trained strain range, offering a physically interpretable and data-efficient alternative to conventional constitutive models.

Zitieren

APA

Fallahnejad, A., Perdahcioglu, E. S., & Boogaard, T. V. D. (2026). 1D Stress Evolution Prediction via Thermodynamically-Informed Neural Networks. Solid State Phenomena, 390, 51-61. https://doi.org/10.4028/p-vj1far

Vancouver

Fallahnejad A, Perdahcioglu ES, Boogaard TVD. 1D Stress Evolution Prediction via Thermodynamically-Informed Neural Networks. Solid State Phenomena. 2026;390:51-61. doi:10.4028/p-vj1far

BibTeX
@article{Fallahnejad2026,
  author = {Fallahnejad, Alireza and Perdahcioglu, Emin Semih and Boogaard, Ton van den},
  title = {1D Stress Evolution Prediction via Thermodynamically-Informed Neural Networks},
  journal = {Solid State Phenomena},
  year = {2026},
  volume = {390},
  pages = {51--61},
  doi = {10.4028/p-vj1far}
}
Kostenlos starten →