Deep Learning Predicts Stress–Strain Relations of Granular Materials Based on Triaxial Testing Data

Journal Article · 28 June 2021 · Computer Modeling in Engineering & Sciences

DOI: https://doi.org/10.32604/cmes.2021.016172 · OSTI ID:1830592

Qu, Tongming ^[1]; Di, Shaocheng ^[2]; T. Feng, Y. ^[3]; Wang, Min ^[4]; Zhao, Tingting ^[5]; Wang, Mengqi ^[1]

---

1. Swansea Univ. (United Kingdom). Zienkiewicz Centre for Computational Engineering
2. Harbin Engineering Univ. (China)
3. Swansea Univ. (United Kingdom). Zienkiewicz Centre for Computational Engineering; Taiyuan Univ. of Technology (China). Institute of Applied Mechanics and Biomedical Engineering,
4. Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
5. Taiyuan Univ. of Technology (China). Institute of Applied Mechanics and Biomedical Engineering,

This study presents an AI-based constitutive modelling framework wherein the prediction model directly learns from triaxial testing data by combining discrete element modelling (DEM) and deep learning. A constitutive learning strategy is proposed based on the generally accepted frame-indifference assumption in constructing material constitutive models. The low-dimensional principal stress-strain sequence pairs, measured from discrete element modelling of triaxial testing, are used to train recurrent neural networks, and then the predicted principal stress sequence is augmented to other high-dimensional or general stress tensor via coordinate transformation. Through detailed hyperparameter investigations, it is found that long short-term memory (LSTM) and gated recurrent unit (GRU) networks have similar prediction performance in constitutive modelling problems, and both satisfactorily predict the stress responses of granular materials subjected to a given unseen strain path. Furthermore, the unique merits and ongoing challenges of data-driven constitutive models for granular materials are discussed.

• Research Organization: Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
• Sponsoring Organization: USDOE; National Natural Science Foundation of China (NSFC)
• Grant/Contract Number: 89233218CNA000001; 41606213; 51639004; 12072217
• OSTI ID: 1830592
• Report Number(s): LA-UR-21-21583; ISSN 1526-1506
• Journal Information: Computer Modeling in Engineering & Sciences, Vol. 128, Issue 1; ISSN 1526-1492
• Publisher: Tech Science PressCopyright Statement
• Country of Publication: United States
• Language: English