Learning the non-proportional multiaxial elastic–plastic response of an aluminium alloy with neural networks
Source abstract
Abstract
We present a surrogate model for the elastic–plastic response of an aluminium alloy, based on simple neural networks trained on measurements taken in tension–torsion and compression-torsion experiments. In these tests hollow cylindrical test specimens are subjected to pseudo-random time histories of applied axial force and torque. Multiple random experiments are conducted to explore the strain and stress space in both the elastic and elastic–plastic regimes of material behaviour. The corresponding histories of axial and shear stress and strain are subdivided in small increments, each of which representing a unit training datapoint. A surrogate model in strain control, based on feed-forward neural networks, is implemented; this comprises a classification network, which distinguishes elastic from elastic-plastic increments, and a regression network to compute the increment in stress as a function of the increment in total strain. The accuracy of the model is evaluated by predicting the material’s response to random loading histories not included in the training dataset.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Metallurgy and Material Forming · Non-Destructive Testing Techniques · Advanced machining processes and optimization
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (50)
Show source-provided references
1. Artificial intelligence and machine learning in design of mechanical materials10.1039/D0MH01451F ↗
2. Machine learning for alloys10.1038/s41578-021-00340-w ↗
3. What machine learning can do for computational solid mechanics
4. Recent advances and applications of machine learning in experimental solid mechanics: a review10.1115/1.4062966 ↗
5. Perspective: machine learning in experimental solid mechanics10.1016/j.jmps.2023.105231 ↗
6. Teaching solid mechanics to artificial intelligence—a fast solver for heterogeneous materials10.1038/s41524-021-00571-z ↗
7. Constitutive artificial neural networks: a fast and general approach to predictive data-driven constitutive modeling by deep learning10.1016/j.jcp.2020.110010 ↗
8. Microstructure-guided deep material network for rapid nonlinear material modeling and uncertainty quantification10.1016/j.cma.2022.115197 ↗
9. A new ANN based crystal plasticity model for FCC materials and its application to non-monotonic strain paths10.1016/j.ijplas.2021.103059 ↗
10. Mechanistically informed artificial neural network model for discovering anisotropic path-dependent plasticity of metals10.1016/j.matdes.2023.111697 ↗
11. Deep learning predicts path-dependent plasticity10.1073/pnas.1911815116 ↗
12. Accelerating multiscale finite element simulations of history-dependent materials using a recurrent neural network
13. An artificial neural network for surrogate modeling of stress fields in viscoplastic polycrystalline materials10.1038/s41524-023-00991-z ↗
14. Calibrating constitutive models with full‐field data via physics informed neural networks10.1111/str.12431 ↗
15. Productive automation of calibration processes for crystal plasticity model parameters via reinforcement learning10.1016/j.matdes.2024.113470 ↗
16. A micromechanics-based artificial neural networks model for rapid prediction of mechanical response in short fiber reinforced rubber composites10.1016/j.ijsolstr.2024.113093 ↗
17. Micromechanics-informed parametric deep material network for physics behaviour prediction of heterogeneous materials with a varying morphology10.1016/j.cma.2023.116687 ↗
18. Learning dislocation dynamics mobility laws from large-scale MD simulations10.1038/s41524-024-01378-4 ↗
19. Data-driven modeling of dislocation mobility from atomistics using physics-informed machine learning10.1038/s41524-024-01394-4 ↗
20. A deep material network for multiscale topology learning and accelerated nonlinear modeling of heterogeneous materials10.1016/j.cma.2018.09.020 ↗
21. Machine learning assisted prediction of mechanical properties of graphene/aluminium nanocomposite based on molecular dynamics simulation10.1016/j.matdes.2021.110334 ↗
22. A thermodynamics-informed neural network for elastoplastic constitutive modeling of granular materials10.1016/j.cma.2024.117246 ↗
23. Application of machine learning for advanced material prediction and design10.1002/eom2.12194 ↗
24. A strategy to train machine learning material models for finite element simulations on data acquirable from physical experiments10.1016/j.cma.2023.115894 ↗
25. A machine learning based plasticity model using proper orthogonal decomposition10.1016/j.cma.2020.113008 ↗
26. A data-driven model of the yield and strain hardening response of commercially pure titanium in uniaxial stress
27. A data-driven rate and temperature dependent constitutive model of the compression response of a syntactic foam
28. Machine-learning based temperature-and rate-dependent plasticity model: application to analysis of fracture experiments on DP steel10.1016/j.ijplas.2019.02.012 ↗
29. A machine learning study of grain boundary damage in Mg alloy10.1016/j.msea.2023.144721 ↗
30. Investigation on dynamic strength of 3D‐printed continuous ramie fiber reinforced biocomposites at various strain rates using machine learning methods10.1002/pc.26816 ↗
31. Coupling in situ experiments and modeling–Opportunities for data fusion, machine learning, and discovery of emergent behavior10.1016/j.cossms.2019.100797 ↗
32. Study of the constitutive behavior of 7075-T651 aluminum alloy10.1016/j.ijimpeng.2017.05.002 ↗
33. A physical-based constitutive model to describe the strain-hardening and dynamic recovery behaviors of 5754 aluminum alloy10.1016/j.msea.2017.04.086 ↗
34. A physically-based constitutive model applied to AA6082 aluminium alloy at large strains, high strain rates and elevated temperatures10.1016/j.matdes.2016.04.047 ↗
35. Plasticity evolution of an aluminum-magnesium alloy under abrupt strain path changes10.1007/s12289-022-01692-6 ↗
36. A strategy to formulate data-driven constitutive models from random multiaxial experiments
37. Determination of the effect of stress state on the onset of ductile fracture through tension-torsion experiments10.1007/s11340-013-9788-4 ↗
38. Young WC, & Budynas RG, Roark’s Formulas for Stress and Strain 709–742 (McGraw-Hill, 2012).
39. Study on constitutive model of cyclic elastoplastic behavior of 6082-T6 aluminum alloy10.1061/JMCEE7.MTENG-16970 ↗
40. Goodfellow I, Bengio Y, and Courville A, Deep Learning, The M.I.T. Press, 2016.
41. Singh P, Manure A, Introduction to TensorFlow 2.0. In: Learn TensorFlow 2.0. Apress, Berkeley, CA., 1-24, 2020.10.1007/978-1-4842-5558-2_1 ↗
42. Nwankpa C, Ijomah W, Gachagan A, and Marshall S, Activation functions: Comparison of trends in practice and research for deep learning, arXiv preprint arXiv:1811.03378, 2018. doi: 10.48550/arXiv.1811.03378.
43. Kingma DP and Ba JL, Adam: A method for stochastic optimization, ICLR 2015, 1412, 6980, 2014.
44. Scikit-learn: Machine Learning in Python, the
45. A computational framework to establish data-driven constitutive models for time-or path-dependent heterogeneous solids
46. Temperature effect induced by uniaxial tensile loading10.1007/BF01130102 ↗
47. Data-driven homogenisation of the response of heterogeneous ductile solids with isotropic damage10.1016/j.matdes.2024.112738 ↗
48. Data-driven constitutive models for brittle solids displaying progressive anisotropic damage
49. A new stiffness-sensing test to measure damage evolution in solids
50. Dynamic mechanical behaviors of 6082-T6 aluminum alloy10.1155/2013/878016 ↗