A generative adversarial neural network for modelling state-dependent sand behaviour
Acta Geotechnica · 2026-09 · 21 (9) · 6027-6043
DOI: 10.1007/s11440-026-03043-0 ↗Kurz gefasst
Fachartikel in der Zeitschrift Acta Geotechnica, online erschienen am 26.05.2026. Verfasst von Qianxu Chen und 2 weiteren Autor:innen. Die Arbeit nennt 67 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Data-driven methods are increasingly explored as alternatives to classical plasticity theory for constitutive modelling of sand. This study introduces a conditional generative adversarial network (cGAN-LD) for modelling state-dependent sand behaviour by integrating the predictions from the Li-Dafalias (LD) model with experimental data. The generator network learns the discrepancy between the LD model prediction and real data, producing a residual stress–strain response conditioned on the initial state. Adding this learned residual to the LD predictions yields the synthetic states. The discriminator network guides the generator training process so that the predicted states are indistinguishable from the real data. The predictive performance of the cGAN-LD model is validated using drained triaxial compression tests on Karlsruhe fine sand and undrained triaxial compression tests on Toyoura sand. Comparative studies with standard GAN, GAN-LD, and Wasserstein-GAN-LD architectures demonstrate that cGAN-LD provides the most accurate and physically consistent predictions among the tested approaches.
Zitieren
APA
Chen, Q., Febrianto, E., & Gao, Z. (2026). A generative adversarial neural network for modelling state-dependent sand behaviour. Acta Geotechnica, 21(9), 6027-6043. https://doi.org/10.1007/s11440-026-03043-0
Vancouver
Chen Q, Febrianto E, Gao Z. A generative adversarial neural network for modelling state-dependent sand behaviour. Acta Geotechnica. 2026;21(9):6027-6043. doi:10.1007/s11440-026-03043-0
BibTeX
@article{Chen2026,
author = {Chen, Qianxu and Febrianto, Eky and Gao, Zhiwei},
title = {A generative adversarial neural network for modelling state-dependent sand behaviour},
journal = {Acta Geotechnica},
year = {2026},
volume = {21},
number = {9},
pages = {6027--6043},
doi = {10.1007/s11440-026-03043-0}
}
EUVIMED