Understanding microstructure-property relationships of HPDC Al-Si alloy based on machine learning and crystal plasticity simulation

Abstract

Al-Si alloys manufactured via high-pressure die casting (HPDC) are suitable for a wide range of applications. However, the heterogeneous microstructure and unpredictable pore distribution of Al-Si high-pressure die castings result in significant variations in the mechanical properties, thus leading to a complicated microstructure-property relationship that is difficult to capture. Hence, a computational framework incorporating machine learning and crystal plasticity method is proposed. This framework aims to provide a systematic and comprehensive understanding of this relationship and enable the rapid prediction of macroscopic mechanical properties based on the microstructure. Firstly, we select eight variables that can effectively characterize the microstructural features and then obtain their statistical information. Subsequently, based on 160 samples obtained via the Latin hypercube sampling method, representative volume elements are constructed, and the crystal plasticity fast Fourier transformation method is executed to obtain the macroscopic mechanical properties. Next, the yield strength, elastic modulus, strength coefficient, and strain-hardening exponent are used to characterize the stress-strain curve, and Gaussian process regression models and microstructural variables are developed. Finally, sensitivity and univariate analyses based on these machine-learning models are performed to obtain insights into the microstructure-property relationships of the HPDC Al-Si alloy. The results show that the Gaussian process regression models exhibit high accuracy (R ² greater than 0.84), thus confirming the viability of the proposed method. The results of sensitivity analysis indicate that the pore size exerts the most significant effect on the mechanical properties. Furthermore, the proposed framework can not only be transferred to other alloys but also be employed for material design.

Keywords

High-pressure die casting (HPDC) / Machine learning / Crystal plasticity / Aluminum alloys

References

[1.] Timelli G, Fabrizi A. The effects of microstructure heterogeneities and casting defects on the mechanical properties of high-pressure die-cast AlSi₉Cu₃ (Fe) alloys. Metall Mater Trans A, 2014, 45: 5486-5498.

[2.] Kong D, Sun DZ, Yang B, et al. Characterization and modeling of damage behavior of a casting aluminum wheel considering inhomogeneity of microstructure and microdefects. Eng Fail Anal, 2023, 145.

[3.] Zhang Y, Li J, Shen F, et al. Microstructure-property relationships in HPDC Aural-2 alloy: experimental and CP modeling approaches. Mat Sci Eng A-Struct, 2022, 848.

[4.] Tan Q, Zhang J, Mo N, et al. A novel method to 3D-print fine-grained AlSi10Mg alloy with isotropic properties via inoculation with LaB₆ nanoparticles. Addit Manuf, 2020, 32.

[5.] Takata N, Kodaira H, Sekizawa K, et al. Change in microstructure of selectively laser melted AlSi10Mg alloy with heat treatments. Mat Sci Eng A-Struct, 2017, 704: 218-228.

[6.] Kang HJ, Yoon PH, Lee GH, et al. Evaluation of the gas porosity and mechanical properties of vacuum assisted pore-free die-cast Al-Si-Cu alloy. Vacuum, 2021, 184.

[7.] Zhang Y, Lordan E, Dou K, et al. Influence of porosity characteristics on the variability in mechanical properties of high pressure die casting (HPDC) AlSi7MgMn alloys. J Manuf Process, 2020, 56: 500-509.

[8.] Liu R, Zheng J, Godlewski L, et al. Influence of pore characteristics and eutectic particles on the tensile properties of Al-Si-Mn-Mg high pressure die casting alloy. Math Sci Eng A-Struct, 2020, 783.

[9.] Liu PW, Wang Z, Xiao YH, et al. Integration of phase-field model and crystal plasticity for the prediction of process-structure-property relation of additively manufactured metallic materials. Int J Plasticity, 2020, 128.

[10.] Moulinec H, Suquet P. A numerical method for computing the overall response of nonlinear composites with complex microstructure. Comput Method Appl M, 1998, 157(1/2): 69-94.

[11.] Tran A, Robbe P, Lim H. Multi-fidelity microstructure-induced uncertainty quantification by advanced Monte Carlo methods. Materialia, 2023, 27.

[12.] Diehl M, Groeber M, Haase C, et al. Identifying structure–property relationships through DREAM.3D representative volume elements and DAMASK crystal plasticity simulations: an integrated computational materials engineering approach. JOM, 2017, 69: 848-855.

[13.] Liu W, Lian J, Aravas N, et al. A strategy for synthetic microstructure generation and crystal plasticity parameter calibration of fine-grain-structured dual-phase steel. Int J Plasticity, 2020, 126.

[14.] Motaman SAH, Roters F, Haase C. Anisotropic polycrystal plasticity due to microstructural heterogeneity: a multi-scale experimental and numerical study on additively manufactured metallic materials. Acta Mater, 2020, 185: 340-369.

[15.] Li YZ, Huang MX. A dislocation-based flow rule with succinct power-law form suitable for crystal plasticity finite element simulations. Int J Plasticity, 2021, 138.

[16.] Ganesan S, Yaghoobi M, Githens A, et al. The effects of heat treatment on the response of WE43 Mg alloy: crystal plasticity finite element simulation and SEM-DIC experiment. Int J Plasticity, 2021, 137.

[17.] Acar P. Machine learning reinforced crystal plasticity modeling under experimental uncertainty. AIAA J, 2020, 58(8): 3569-3576.

[18.] Eghtesad A, Luo Q, Shang SL, et al. Machine learning-enabled identification of micromechanical stress and strain hotspots predicted via dislocation density-based crystal plasticity simulations. Int J Plasticity, 2023, 166.

[19.] Tu Y, Liu Z, Carneiro L, et al. Towards an instant structure-property prediction quality control tool for additive manufactured steel using a crystal plasticity trained deep learning surrogate. Mater Design, 2022, 213.

[20.] Veasna K, Feng Z, Zhang Q, et al. Machine leaning-based multi-objective optimization for efficient identification of crystal plasticity model parrameters. Cnmput Method Appl M, 2023, 403.

[21.] Sedighiani K, Diehl M, Traka K, et al. An efficient and robust approach to determine material parameters of crystal plasticity constitutive laws from macro-scale stress-strain curves. Int J Plasticity, 2020, 134.

[22.] Heidenreich JN, Gorji MB, Mohr D. Modeling structure-property relationships with convolutional neural networks: yield surface prediction based on microstructure images. Int J Plasticity, 2023, 163.

[23.] Hu Y, Zhou G, Yuan X, et al. An artificial neural network-based model for roping prediction in aluminum alloy sheet. Acta Mater, 2023, 245.

[24.] Zhang XX, Bauer PP, Lutz A, et al. Microplasticity and macroplasticity behavior of additively manufactured Al-Mg-Sc-Zr alloys: in-situ experiment and modeling. Int J Plastic, 2023.

[25.] Roters F, Eisenlohr P, Hantcherli L, et al. Overview of constitutive laws, kinematics, homogenization and multiscale methods in crystal plasticity finite-element modeling: theory, experiments, applications. Acta Mater, 2010, 58(4): 1152-1211.

[26.] Smola AJ, Schölkopf B. A tutorial on support vector regression. Stat Comput, 2004, 14(3): 199-222.

[27.] Seeger M. Gaussian processes for machine learning. Int J Neural Syst, 2014, 14(2): 69-106.

[28.] Liu JF, Jiang C, Zheng J. Uncertainty propagation method for high-dimensional black-box problems via Bayesian deep neural network. Struct Multidiscip Optim, 2022, 65(3): 1-21.

[29.] Deringer VL, Bartók AP, Bernstein N, et al. Gaussian process regression for materials and molecules. Chem Rev, 2021, 121(16): 10073-10141.

[30.] Schulz E, Speekenbrink M, Krause A. A tutorial on Gaussian process regression: modelling, exploring, and exploiting functions. J Math Psychol, 2018, 85: 1-16.

[31.] Zhang H, Zhang L, Xu C, et al. Global sensitivity analysis of mechanical properties in hybrid single lap aluminum-CFRP (plain woven) joints based on uncertainty quantification. Compos Struct, 2022, 280.

[32.] Soboĺ IM. Sensitivity estimates for nonlinear mathematical models. Math Model Comput Exp, 1993, 1(4): 407-414.

[33.] Groeber MA, Jackson MA. DREAM. 3D: a digital representation environment for the analysis of microstructure in 3D. Integr Mater Manuf I, 2014, 3: 56-72.

[34.] Roters F, Diehl M, Shanthraj P, et al. DAMASK–The Düsseldorf advanced material simulation kit for modeling multi-physics crystal plasticity, thermal, and damage phenomena from the single crystal up to the component scale. Comp Mater Sci, 2019, 158: 420-478.

[35.] Gong X, Bustillo J, Blancd L, et al. FEM simulation on elastic parameters of porous silicon with different pore shapes. Int J Solids Struct, 2020, 190: 238-243.

[36.] Zhang XX, Lutz A, Andrä H, et al. Evolution of microscopic strains, stresses, and dislocation density during in-situ tensile loading of additively manufactured AlSi10Mg alloy. Int J Plasticity, 2021, 139.

[37.] Zhang K, Holmedal B, Hopperstad OS, et al. Multi-level modelling of mechanical anisotropy of commercial pure aluminium plate: crystal plasticity models, advanced yield functions and parameter identification. Int J Plasticity, 2015, 66: 3-30.

[38.] Zhang XX, Andrä H. Crystal plasticity simulation of the macroscale and microscale stress–strain relations of additively manufactured AlSi10Mg alloy. Comp Mater Sci, 2021, 200.

[39.] Abraham ST, Bhat SS. Crystal plasticity finite element modelling on the influence of grain size and shape parameters on the tensile stiffness and yield strength. Mat Sci Eng A-Struct, 2023, 877.

[40.] Deda E, Berman TD, Allison JE. The influence of Al content and thickness on the microstructure and tensile properties in high-pressure die cast magnesium alloys. Metall Mater Trans A, 2017, 48: 1999-2014.

Funding

National Natural Science Foundation of China http://dx.doi.org/10.13039/501100001809(52375256); Natural Science Foundation of Shanghai Municipality http://dx.doi.org/10.13039/100007219(23ZR1431600)