In this study, structure – property relationships (SPR) have been investigated using machine learning methods (ML). The research objective was to create a ML model that can predict the stress – strain response of materials at different temperatures from a given microstructure with industrially acceptable accuracy and high computational efficiency. Automated microstructure generation techniques and numerical simulations were developed to create a dataset for the ML model. Two – phase 3D representative volume elements (RVEs) were analyzed using finite element analysis (FEA) to obtain the stress – strain responses of the RVEs. The phase arrangement of the RVEs, the temperature, and the stress – strain responses were used to train the ML model. The microstructure arrangement and the temperature – dependent mechanical properties of each phase were known parameters, while the output parameter was the stress – strain response of the two – phase RVE. The ML model has shown excellent prediction accuracy in the temperature range from 20 °C to 250 °C. In addition, the model showed very high computational efficiency compared to FEA, allowing much faster prediction of the stress – strain curves at specific temperatures.
Révisé le :
Accepté le :
Publié le :
CC-BY 4.0
@article{CRMECA_2023__351_G1_151_0,
author = {Filip Nikoli\'c and Marko \v{C}ana{\dj}ija},
title = {Deep {Learning} of {Temperature} {\textendash} {Dependent} {Stress} {\textendash} {Strain} {Hardening} {Curves}},
journal = {Comptes Rendus. M\'ecanique},
pages = {151--170},
publisher = {Acad\'emie des sciences, Paris},
volume = {351},
year = {2023},
doi = {10.5802/crmeca.185},
language = {en},
}
Filip Nikolić; Marko Čanađija. Deep Learning of Temperature – Dependent Stress – Strain Hardening Curves. Comptes Rendus. Mécanique, Volume 351 (2023), pp. 151-170. doi : 10.5802/crmeca.185. https://comptes-rendus.academie-sciences.fr/mecanique/articles/10.5802/crmeca.185/
[1] Predicting the effective mechanical property of heterogeneous materials by image based modeling and deep learning, Comput. Methods Appl. Mech. Eng., Volume 347 (2019), pp. 735-753 | DOI | MR | Zbl
[2] An efficient machine learning approach to establish structure-property linkages, Comput. Mater. Sci., Volume 156 (2019), pp. 17-25 | DOI
[3] A novel structure-property relationship model based on machine learning, Model. Simul. Mat. Sci. Eng., Volume 28 (2020) no. 3, 035002 | DOI
[4] Data-driven reduced order models for effective yield strength and partitioning of strain in multiphase materials, J. Comput. Phys., Volume 346 (2017), pp. 242-261 | DOI | MR
[5] Deep learning approaches for mining structure-property linkages in high contrast composites from simulation datasets, Comput. Mater. Sci., Volume 151 (2018), pp. 278-287 | DOI
[6] Material structure-property linkages using three-dimensional convolutional neural networks, Acta Mater., Volume 146 (2018), pp. 76-84 | DOI
[7] Mining structure–property relationships in polymer nanocomposites using data driven finite element analysis and multi-task convolutional neural networks, Mol. Syst. Des. Eng., Volume 5 (2020) no. 5, pp. 962-975 | DOI
[8] Transfer learning of deep material network for seamless structure–property predictions, Comput. Mech., Volume 64 (2019) no. 2, pp. 451-465 | DOI | MR | Zbl
[9] Parametrically homogenized constitutive models (PHCMs) from micromechanical crystal plasticity FE simulations, part I: Sensitivity analysis and parameter identification for Titanium alloys, Int. J. Plast., Volume 120 (2019), pp. 296-319 | DOI
[10] Mesh-based graph convolutional neural network models of processes with complex initial states (2021) (https://arxiv.org/abs/2107.00090)
[11] Prediction of composite microstructure stress-strain curves using convolutional neural networks, Mater. Des., Volume 189 (2020), 108509 | DOI
[12] Data-driven ultimate conditions prediction and stress-strain model for FRP-confined concrete, Compos. Struct., Volume 242 (2020), 112094 | DOI
[13] Physics-driven machine learning model on temperature and time-dependent deformation in lithium metal and its finite element implementation, J. Mech. Phys. Solids, Volume 153 (2021), 104481 | DOI
[14] Data driven modeling of plastic deformation, Comput. Methods Appl. Mech. Eng., Volume 318 (2017), pp. 981-1004 | DOI | Zbl
[15] Extending a physics-based constitutive model using genetic programming, Applications in Engineering Science, Volume 9 (2022), 100080 | DOI
[16] Simplified ResNet approach for data driven prediction of microstructure-fatigue relationship, Mech. Mater., Volume 151 (2020), 103625 | DOI
[17] Deep learning prediction of stress fields in additively manufactured metals with intricate defect networks, Mech. Mater., Volume 165 (2022), 104191 | DOI
[18] Stress field prediction in fiber-reinforced composite materials using a deep learning approach, Compos. B. Eng., Volume 238 (2022), 109879 | DOI
[19] Using machine-learning to understand complex microstructural effects on the mechanical behavior of Ti-6Al-4V alloys, Comput. Mater. Sci., Volume 208 (2022), 111267 | DOI
[20] Predicting microstructure-dependent mechanical properties in additively manufactured metals with machine- and deep-learning methods, Comput. Mater. Sci., Volume 175 (2020), 109599 | DOI
[21] Three-dimensional convolutional neural network (3D-CNN) for heterogeneous material homogenization, Comput. Mater. Sci., Volume 184 (2020), 109850 | DOI
[22] Prediction and optimization of mechanical properties of composites using convolutional neural networks, Compos. Struct., Volume 227 (2019), 111264 | DOI
[23] Deep neural network method for predicting the mechanical properties of composites, Appl. Phys. Lett., Volume 115 (2019) no. 16, 161901 | DOI
[24] Prediction of Energetic Material Properties from Electronic Structure Using 3D Convolutional Neural Networks, J. Chem. Inf. Model., Volume 60 (2020) no. 10, pp. 4457-4473 | DOI
[25] DREAM.3D: a digital representation environment for the analysis of microstructure in 3D, Integr. Mater. Manuf. Innov., Volume 3 (2014) no. 1, pp. 56-72 | DOI
[26] Microstructure-based finite element analysis of failure prediction in particle-reinforced metal-matrix composite, J. Mater. Process. Technol., Volume 207 (2008) no. 1-3, pp. 53-62 | DOI
[27] Predicting the constitutive behavior of semi-solids via a direct finite element simulation: application to AA5182, Model. Simul. Mat. Sci. Eng., Volume 17 (2009) no. 5, 055011 | DOI
[28] Two-dimensional finite element simulation of fracture and fatigue behaviours of alumina microstructures for hip prosthesis, Proc. Inst. Mech. Eng. H., Volume 225 (2011) no. 12, pp. 1158-1168 | DOI
[29] Finite element analysis of the microstructure of AlN-TiN composites, Strain, Volume 50 (2014) no. 3, pp. 250-261 | DOI
[30] Generating three-dimensional structures from a two-dimensional slice with generative adversarial network-based dimensionality expansion, Nat. Mach. Intell., Volume 3 (2021) no. 4, pp. 299-305 | DOI
[31] Micromechanical material models for polymer composites through advanced numerical simulation techniques, Ph. D. Thesis, RWTH Aachen University, Aachen, Germany (2010)
[32] Multi-scale constitutive modelling of heterogeneous materials with a gradient-enhanced computational homogenization scheme, Int. J. Numer. Methods Eng., Volume 54 (2002) no. 8, pp. 1235-1260 | DOI | Zbl
[33] Multi-scale computational homogenization: Trends and challenges, J. Comput. Appl. Math., Volume 234 (2010) no. 7, pp. 2175-2182 | DOI | Zbl
[34] ABAQUS/Standard User’s Manual, Version 6.9, 2009
[35] Machine learning in materials science, InfoMat, Volume 1 (2019) no. 3, pp. 338-358 | DOI
[36] Predicting microstructure-dependent mechanical properties in additively manufactured metals with machine-and deep-learning methods, Comput. Mater. Sci., Volume 175 (2020), 109599 | DOI
[37] Atomic column heights detection in metallic nanoparticles using deep convolutional learning, Comput. Mater. Sci., Volume 180 (2020), 109722 | DOI
[38] Structural vibration-based classification and prediction of delamination in smart composite laminates using deep learning neural network, Compos. B. Eng., Volume 161 (2019), pp. 586-594 | DOI
[39] Advanced steel microstructural classification by deep learning methods, Sci. Rep., Volume 8 (2018) no. 1, 2128 | DOI
[40] A transfer learning approach for microstructure reconstruction and structure-property predictions, Sci. Rep., Volume 8 (2018) no. 1, 13461 | DOI
[41] High Throughput Quantitative Metallography for Complex Microstructures Using Deep Learning: A Case Study in Ultrahigh Carbon Steel, Microsc. Microanal., Volume 25 (2019) no. 1, pp. 21-29 | DOI
[42] Detection and segmentation of manufacturing defects with convolutional neural networks and transfer learning, Smart Sustain Manuf Syst., Volume 2 (2018) | DOI
[43] Inverse characterization of composites using guided waves and convolutional neural networks with dual-branch feature fusion, Mech. Adv. Mater. Struct. (2021) | DOI
[44] A deep learning approach based on a data-driven tool for classification and prediction of thermoelastic waves band structures for phononic crystals, Mech. Adv. Mater. Struct., Volume 29 (2021) no. 27, pp. 6612-6625 | DOI
[45] Casting Microstructure Inspection Using Computer Vision: Dendrite Spacing in Aluminum Alloys, Metals, Volume 11 (2021) no. 5, p. 756 | DOI
[46] Casting Defects Detection in Aluminum Alloys Using Deep Learning: a Classification Approach, Inter. Metalcast. (2022) | DOI
[47] Prediction of two-phase composite microstructure properties through deep learning of reduced dimensional structure-response data, Compos. B. Eng., Volume 225 (2021), 109282 | DOI
Cité par Sources :
Commentaires - Politique
Theoretical models for single-molecule DNA and RNA experiments: from elasticity to unzipping
Simona Cocco; John F. Marko; Rémi Monasson
C. R. Phys (2002)
Bertille Claude; Grégory Girault; Bruno Leblé; ...
C. R. Méca (2023)