A mechanics-informed deep learning constitutive model for sequential prediction of strain rate-dependent behavior and microstructural evolution

Abstract

Classical constitutive models explicitly couple macroscopic mechanical responses with underlying microstructural evolution, which is crucial for capturing complex deformation mechanisms across varying strain rates. However, current deep learning (DL) constitutive models predominantly focus on macroscopic stress-strain mapping, often neglecting these critical microstructural transitions. To bridge this gap, this work proposes a mechanics-informed deep learning constitutive model (MIDLCM) that integrates gated recurrent units and multi-head attention with a mechanics-informed layer and a mechanics-informed loss, enabling simultaneous prediction of stress response and microstructural descriptors. Trained on a CrFeNi FCC alloy dataset spanning strain rates from 10^-4 to 5,000 s^-1, MIDLCM accurately reproduces strain-rate-dependent stress-strain behavior and captures the associated evolution of dislocation density and twin volume fraction. Crucially, the model successfully represents the distinct dislocation accumulation regimes and the dynamic transition of plasticity mechanisms - from dislocation-dominated to twinning-assisted - across extreme dynamic loading, consistent with experimental trends and crystal-plasticity-based references. Ablation studies show that attention-based temporal encoding and mechanics-informed constraints contribute complementary improvements while preserving inference efficiency. By explicitly tracking these internal state variables, the proposed framework provides a mechanism-level interpretable and computationally efficient microstructure-mechanics coupled alternative for rate-dependent constitutive modeling and is readily extendable to other alloy systems and loading paths.

Keywords

Deep learning constitutive model / strain rate sensitivity / mechanics-informed design / multi-element alloys

References

[1] Tomé C. N.,Lebensohn R. A.. Material modeling with the visco-plastic self-consistent (VPSC) approach: theory and practical applications; Elsevier, 2023

[2] He L.,Li Y.,Torrent D.,Zhuang X.,Rabczuk T.,Jin Y.. Machine learning assisted intelligent design of meta structures: a review Microstructures 2023 3 2023034

[3] Miao B.,Lin G.,Zhang Y.,Cheng Y.,Yang H.. Machine learning applications in metallic materials: Recent advances and future perspectives J. Alloys Compd. 2026 1062 187486

[4] Li W.,Xie D.,Li D.,Zhang Y.,Gao Y.,Liaw P. K.. Mechanical behavior of high-entropy alloys Prog. Mater. Sci. 2021 118 100777

[5] Wang Y.,Jiao Z.,Bian G..et al. Dynamic tension and constitutive model in Fe₄₀Mn₂₀Cr₂₀Ni₂₀ high-entropy alloys with a heterogeneous structure Mat. Sci. Eng. A-Struct. 2022 839 142837

[6] Zhang Z.,Sheng H.,Wang Z..et al. Dislocation mechanisms and 3D twin architectures generate exceptional strength-ductility-toughness combination in CrCoNi medium-entropy alloy Nat. Commun. 2017 8 14390 PMC5321736

[7] Dowding I.,Schuh C. A.. Metals strengthen with increasing temperature at extreme strain rates Nature 2024 630 91 5 PMC11153132

[8] Borodin E. N.,Gruzdkov A. A.,Mayer A. E.,Selyutina N. S.. Physical nature of strain rate sensitivity of metals and alloys at high strain rates J. Phys: Conf. Ser. 2018 991 012012

[9] Fan H.,Wang Q.,El-awady J. A.,Raabe D.,Zaiser M.. Strain rate dependency of dislocation plasticity Nat. Commun. 2021 12 1845 PMC7988163

[10] Liang Z.,Wang X.,Huang W.,Huang M.. Strain rate sensitivity and evolution of dislocations and twins in a twinning-induced plasticity steel Acta Mater. 2015 88 170 9

[11] Li C.,Cao F.,Chen Y.,Wang H.,Dai L.. Crystal plasticity model analysis of the effect of short-range order on strength-plasticity of medium entropy alloys Metals 2022 12 1757

[12] Ma E.. Unusual dislocation behavior in high-entropy alloys Scr. Mater. 2020 181 127 33

[13] Chandan A. K.,Tripathy S.,Ghosh M.,Chowdhury S. G.. Evolution of substructure of a non-equiatomic FeMnCrCo high entropy alloy deformed at ambient temperature Metall. Mater. Trans. A. 2019 50 5079 90

[14] Choudhuri D.,Gwalani B.,Gorsse S..et al. Enhancing strength and strain hardenability via deformation twinning in fcc-based high entropy alloys reinforced with intermetallic compounds Acta Mater. 2019 165 420 30

[15] Cho K.,Van Merrienboer B.,Gulcehre C..et al. Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), Doha, Qatar, September, 2014; Association for Computational Linguistics: Stroudsburg, PA, USA, 2014, pp 1724-34

[16] Mozaffar M.,Bostanabad R.,Chen W.,Ehmann K.,Cao J.,Bessa M. A.. Deep learning predicts path-dependent plasticity Proc. Natl. Acad. Sci. U.S.A. 2019 116 26414 20 PMC6936363

[17] Hu C.,Martin S.,Dingreville R.. Accelerating phase-field predictions via recurrent neural networks learning the microstructure evolution in latent space Comput. Methods Appl. Mech. Eng. 2022 397 115128

[18] Bonatti C.,Mohr D.. On the importance of self-consistency in recurrent neural network models representing elasto-plastic solids J. Mech. Phys. Solids 2022 158 104697

[19] Heidenreich J. N.,Mohr D.. Recurrent neural network plasticity models: Unveiling their common core through multi-task learning Comput. Methods Appl. Mech. Eng. 2024 426 116991

[20] Lim B.,Zohren S.. Time-series forecasting with deep learning: a survey Phil. Trans. R. Soc. A. 2021 379 20200209

[21] Vaswani A.,Shazeer N.,Parmar N..et al. Attention is All you Need. In Advances in Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA, 2017; Vol. 30, pp 5998-6008

[22] Borkowski L.,Sorini C.,Chattopadhyay A.. Recurrent neural network-based multiaxial plasticity model with regularization for physics-informed constraints Comput. Struct. 2022 258 106678

[23] Liu X.,He J.,Huang S.. Mechanistically informed artificial neural network model for discovering anisotropic path-dependent plasticity of metals Mater. Des. 2023 226 111697

[24] Eghtesad A.,Tan J.,Fuhg J. N.,Bouklas N.. NN-EVP: A physics informed neural network-based elasto-viscoplastic framework for predictions of grain size-aware flow response Int. J. Plast. 2024 181 104072

[25] Long X.,Steve N. T. N. A.,Wahaajuddin K. K.. Physics-constrained machine learning for constitutive modelling of high-strength concrete across strain rates Eng. Appl. Artif. Intell. 2026 171 114314

[26] Wang K.,Jin X.,Zhang Y.,Liaw P. K.,Qiao J.. Dynamic tensile mechanisms and constitutive relationship in CrFeNi medium entropy alloys at room and cryogenic temperatures Phys. Rev. Mater. 2021 5 113608

[27] Ibragimova O.,Brahme A.,Muhammad W.,Lévesque J.,Inal K.. A new ANN based crystal plasticity model for FCC materials and its application to non-monotonic strain paths Int. J. Plast. 2021 144 103059

[28] Hou J.,Qiao J.,Lian J.,Liaw P. K.. Revealing the relationship between microstructures, textures, and mechanical behaviors of cold-rolled Al_0.1CoCrFeNi high-entropy alloys Mat. Sci. Eng. A-Struct. 2021 804 140752

[29] Zecevic M.,Cawkwell M.,Ramos K.,Luscher D.. Crystal plasticity including a phase-field deformation twinning model for the high-rate deformation of cyclotetramethylene tetranitramine J. Mech. Phys. Solids 2022 163 104872

[30] Wu K.,Sun X.,Liu B..et al. A multiscale investigation into the electroplastic effects in copper: Experiments and crystal plasticity modeling J. Mech. Phys. Solids 2026 212 106597

[31] Sun X.,Zhou K.,Liu C..et al. A crystal plasticity based strain rate dependent model across an ultra-wide range Int. J. Plast. 2024 180 104056

[32] Orowan E.. Problems of plastic gliding Proc. Phys. Soc. 1940 52 8 22

[33] Beyerlein I.,Tomé C.. A dislocation-based constitutive law for pure Zr including temperature effects Int. J. Plast. 2008 24 867 95

[34] Zinovev A.,Terentyev D.,Dubinko A.,Delannay L.. Constitutive law for thermally-activated plasticity of recrystallized tungsten J. Nucl. Mater. 2017 496 325 32

[35] Hall E. O.. The deformation and ageing of mild steel: III discussion of results Proc. Phys. Soc. B. 1951 64 747 53

[36] Petch N. J.. The cleavage strength of polycrystals J. Iron Steel Inst. 1953 174 25 28

[37] Conrad H.,Feuerstein S.,Rice L.. Effects of grain size on the dislocation density and flow stress of niobium Mater. Sci. Eng. 1967 2 157 68

[38] Ashby M. F.. The deformation of plastically non-homogeneous materials Philos. Mag. 2006 21 399 424

[39] Cordero Z. C.,Knight B. E.,Schuh C. A.. Six decades of the Hall-Petch effect - a survey of grain-size strengthening studies on pure metals Int. Mater. Rev. 2016 61 495 512

[40] Zhu T.,Li J.,Samanta A.,Kim H. G.,Suresh S.. Interfacial plasticity governs strain rate sensitivity and ductility in nanostructured metals Proc. Natl. Acad. Sci. U.S.A. 2007 104 3031 6 PMC1805608

[41] Beyerlein I.,Mccabe R.,Tomé C.. Effect of microstructure on the nucleation of deformation twins in polycrystalline high-purity magnesium: A multi-scale modeling study J. Mech. Phys. Solids 2011 59 988 1003

[42] Loshchilov I.,Hutter F.. Decoupled weight decay regularization. In Proceedings of the 7th International Conference on Learning Representations (ICLR 2019), New Orleans, LA, USA, May 6-9, 2019; Curran Associates, Inc.: Red Hook, NY, USA, 2019, pp. 4061-78. Available from: https://openreview.net/pdf?id=Bkg6RiCqY7 [accessed on 2026-6-2]

[43] Akiba T.,Sano S.,Yanase T.,Ohta T.,Koyama M.. Optuna. In KDD '19: The 25th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Anchorage AK USA; ACM: New York, NY, USA, 2019, pp 2623-31

[44] Long X.,Su T.,Lu C.,Wang S.,Huang J.,Chang C.. An insight into dynamic properties of SAC305 lead-free solder under high strain rates and high temperatures Int. J. Impact Eng. 2023 175 104542

[45] Long X.,Shen Z.,Li J..et al. Size effect of nickel-based single crystal superalloy revealed by nanoindentation with low strain rates J. Mater. Res. Technol. 2024 29 2437 47

[46] Long X.,Hu Y.,Su T..et al. Thermomechanical constitutive behaviour of 3D printed biomimetic polymer material under high strain rates Polym. Test. 2024 134 108439

[47] Samaniego E.,Anitescu C.,Goswami S..et al. An energy approach to the solution of partial differential equations in computational mechanics via machine learning: Concepts, implementation and applications Comput. Methods Appl. Mech. Eng. 2020 362 112790

[48] Goswami S.,Anitescu C.,Chakraborty S.,Rabczuk T.. Transfer learning enhanced physics informed neural network for phase-field modeling of fracture Theor. Appl. Fract. Mech. 2020 106 102447