Prediction of properties and mechanism of Cu-Ni-Co-Si alloys based on machine learning and genetic algorithm

doi:10.13251/j.issn.0254-6051.2025.01.040

Abstract

Abstract: Application of machine learning in materials research is extensive. However, the task of designing alloys based on many composition and process factors remains a significant difficulty. A machine learning approach to develop alloys by considering the physicochemical qualities, composition, and process of the material was proposed. The property prediction of the Cu-Ni-Co-Si alloy was then optimized by using a genetic algorithm. The recursive elimination method was employed to investigate the potential correlation between the characteristics and alloy properties. The results show that the primary factors influencing the hardness and conductivity characteristics of the alloys are the aging treatment and cold rolling deformation. Furthermore, the physicochemical properties primarily influence the conductivity of the alloy by impacting the density of free electrons and the free path of free electron migration. It affects the hardness of the alloy by exerting influence on solution strengthening and dislocation strengthening.

Key words: machine learning, genetic algorithm, aging processing, cold rolling deformation, prediction of properties

CLC Number:

Zhang Yingfan, Chen Huiqin, Dang Shue, Chen Juan, Xu Quan, Fang Xiaotian, Shi Tenglong, Dai Yunyun. Prediction of properties and mechanism of Cu-Ni-Co-Si alloys based on machine learning and genetic algorithm[J]. Heat Treatment of Metals, 2025, 50(1): 255-265.

References

[1]Azzeddine H, Bourezg Y I, Khereddine A Y, et al. An investigation of the stored energy and thermal stability in a Cu-Ni-Si alloy processed by high-pressure torsion[J]. Philosophical Magazine, 2020, 100(6): 688-712.
[2]Kale A S, Nemeth W, Perkins C L, et al. Thermal stability of copper-nickel and copper-nickel silicide contacts for crystalline silicon[J]. ACS Applied Energy Materials, 2018, 1(6): 2841-2848.
[3]Zhao Z, Zhang Y, Tian B H, et al. Co effects on Cu-Ni-Si alloys microstructure and physical properties[J]. Journal of Alloys and Compounds, 2019, 797: 1327-1337.
[4]Liu F, Li J, Peng L J, et al. Simultaneously enhanced hardness and electrical conductivity in a Cu-Ni-Si alloy by addition of cobalt[J]. Journal of Alloys and Compounds, 2021, 862: 158667.
[5]Liu F, Ma J M, Peng L J, et al. Hot deformation behavior and microstructure evolution of Cu-Ni-Co-Si alloys[J]. Materials, 2020, 13(9): 2042.
[6]Wei H, Chen Y L, Li Z L, et al. Microstructure evolution and dislocation strengthening mechanism of Cu-Ni-Co-Si alloy[J]. Materials Science and Engineering A, 2021, 826: 142023.
[7]Sanchez-Lengeling B, Aspuru-Guzik A. Inverse molecular design using machine learning: Generative models for matter engineering[J]. Science, 2018, 361: 360-365.
[8]Himanen L, Geurts A, Foster A S, et al. Data-driven materials science: Status, challenges, and perspectives[J]. Advanced Science, 2019, 6(21): 1900808.
[9]Butler K T, Davies D W, Cartwright H, et al. Machine learning for molecular and materials science[J]. Nature, 2018, 559: 547-55.
[10]Wen C, Wang C, Zhang Y K, et al. Modeling solid solution strengthening in high entropy alloys using machine learning[J]. Acta Materialia, 2021, 212: 116917.
[11]Xiong J, Shi S Q, Zhang T Y. Machine learning of phases and mechanical properties in complex concentrated alloys[J]. Journal of Materials Science and Technology, 2021, 87: 133-142.
[12]Zou C X, Li J S, Wang W Y, et al. Integrating data mining and machine learning to discover high-strength ductile titanium alloys[J]. Acta Materialia, 2021, 202: 211-221.
[13]Li J, Xie B B, Fang Q H, et al. High-throughput simulation combined machine learning search for optimum elemental composition in medium entropy alloy[J]. Journal of Materials Science and Technology, 2021, 68: 70-75.
[14]Verdi C, Karsai F, Liu P T, et al. Thermal transport and phase transitions of zirconia by on-the-fly machine-learned interatomic potentials[J]. NPJ Computational Materials, 2021, 7(1): 156.
[15]Ozerdem M S, Kolukisa S. Artificial neural network approach to predict the mechanical properties of Cu-Sn-Pb-Zn-Ni cast alloys[J]. Materials and Design, 2009, 30(3): 764-769.
[16]Xie Q, Suvarna M, Li J L, et al. Online prediction of mechanical properties of hot rolled steel plate using machine learning[J]. Materials and Design, 2021, 197: 109201.
[17]Deng Z H, Yin H Q, Jiang X, et al. Machine-learning-assisted prediction of the mechanical properties of Cu-Al alloy[J]. International Journal of Minerals Metallurgy and Materials, 2020, 27(3): 362-373.
[18]Kwak S, Kim J, Ding H S, et al. Machine learning prediction of the mechanical properties of γ-TiAl alloys produced using random forest regression model[J]. Journal of Materials Research and Technology, 2022, 18: 520-530.
[19]Gu H H, Wang R Z, Zhu S P, et al. Machine learning assisted probabilistic creep-fatigue damage assessment[J]. International Journal of Fatigue, 2022, 156: 106677.
[20]Wang B X, Zhao W G, Du Y L, et al. Prediction of fatigue stress concentration factor using extreme learning machine[J]. Computational Materials Science, 2016, 125: 136-145.
[21]Rovinelli A, Sangid M D, Proudhon H, et al. Using machine learning and a data-driven approach to identify the small fatigue crack driving force in polycrystalline materials[J]. npj Computational Materials, 2018, 4: 35.
[22]Agrawal A, Choudhary A. An online tool for predicting fatigue strength of steel alloys based on ensemble data mining[J]. International Journal of Fatigue, 2018, 113: 389-400.
[23]Xiong J, Shi S Q, Zhang T Y. A machine-learning approach to predicting and understanding the properties of amorphous metallic alloys[J]. Materials & Design, 2020, 187: 108378.
[24]Muhammad W, Brahme A P, Ibragimova O, et al. A machine learning framework to predict local strain distribution and the evolution of plastic anisotropy & fracture in additively manufactured alloys[J]. International Journal of Plasticity, 2021, 136: 102867.
[25]Roy A, Babuska T, Krick B, et al. Machine learned feature identification for predicting phase and Young's modulus of low-, medium- and high-entropy alloys[J]. Scripta Materialia, 2020, 185: 152-158.
[26]Hoyt R A, Montemore M M, Fampiou I, et al. Machine learning prediction of H adsorption energies on Ag alloys[J]. Journal of Chemical Information and Modeling, 2019, 59(4): 1357-1365.
[27]Li X, Li B, Yang Z, et al. A transferable machine-learning scheme from pure metals to alloys for predicting adsorption energies[J]. Journal of Materials Chemistry A, 2022, 10(2): 872-880.
[28]Gao C, Yang X Y, Jiang M, et al. Machine learning-enabled band gap prediction of monolayer transition metal chalcogenide alloys[J]. Physical Chemistry Chemical Physics, 2022, 24(7): 4653-4665.
[29]Zhao F, Lei C H, Zhao Q K, et al. Predicting the property contour-map and optimum composition of Cu-Co-Si alloys via machine learning[J]. Materials Today Communications, 2022, 30: 103318.
[30]Magar R, Farimani A B. Learning from mistakes: Sampling strategies to efficiently train machine learning models for material property prediction[J]. Computational Materials Science, 2023, 224: 112167.
[31]Zhao Q K, Yang H Y, Liu J B, et al. Machine learning-assisted discovery of strong and conductive Cu alloys: Data mining from discarded experiments and physical features[J]. Materials and Design, 2021, 197: 109248.
[32]Zhang Y, Wen C, Wang C X, et al. Phase prediction in high entropy alloys with a rational selection of materials descriptors and machine learning models[J]. Acta Materialia, 2020, 185: 528-539.
[33]Wang C C, Wei X L, Ren D, et al. High-throughput map design of creep life in low-alloy steels by integrating machine learning with a genetic algorithm[J]. Materials and Design, 2022, 213: 110326.
[34]Zhang H T, Fu H D, He X Q, et al. Dramatically enhanced combination of ultimate tensile strength and electric conductivity of alloys viamachine learning screening[J]. Acta Materialia, 2020, 200: 803-810.
[35]Singh D, Singh B. Investigating the impact of data normalization on classification performance[J]. Applied Soft Computing, 2020, 97: 105524.
[36]Fei N, Gao Y, Lu Z, et al. Z-score normalization, hubness, and few-shot learning[C]//2021 IEEE/CVF International Conference on Computer Vision(ICCV). 2021: 142-151.
[37]Guyon I, Weston J, Barnhill S, et al. Gene selection for cancer classification using support vector machines[J]. Machine Learning, 2002, 46(1-3): 389-422.
[38]Zhong M, Zeng W, Liu F S, et al. Explanation of the conductivity difference of half-Heusler transparent conductors by ionization energy[J]. Physical Chemistry Chemical Physics, 2021, 23: 9285-9293.
[39]Stamminger A, Ziebarth B, Mrovec M, et al. Ionic conductivity and its dependence on structural disorder in halogenated argyrodites Li6PS5X(X=Br, Cl, I)[J]. Chemistry of Materials, 2019, 31: 8673-8678.
[40]Giannini S, Carof A, Ellis M, et al. Quantum localization and delocalization of charge carriers in organic semiconducting crystals[J]. Nature Communications, 2019, 10: 3843.
[41]Zhang L, Chen H M, Tao X M, et al. Machine learning reveals the importance of the formation enthalpy and atom-size difference in forming phases of high entropy alloys[J]. Materials and Design, 2020, 193: 108835.
[42]Roy A, Sreeramagiri P, Babuska T, et al. Lattice distortion as an estimator of solid solution strengthening in high-entropy alloys[J]. Materials Characterization, 2021, 172: 110877.
[43]Fang W, Yu H Y, Chang R B, et al. Microstructure and mechanical properties of Cr-rich Co-Cr-Fe-Ni high entropy alloys designed by valence electron concentration[J]. Materials Chemistry and Physics, 2019, 238: 121897.
[44]Hu Y L, Bai L H, Tong Y G, et al. First-principle calculation investigation of NbMoTaW based refractory high entropy alloys[J]. Journal of Alloys and Compounds, 2020, 827: 153963.
[45]Ulrich A S, Pfizenmaier P, Solimani A, et al. Strengthened Cr-Si-base alloys for high temperature applications[J]. International Journal of Refractory Metals & Hard Materials, 2018, 76: 72-81.
[46]Zhang Y, Chen X, Jayalakshmi S, et al. Factors determining solid solution phase formation and stability in CoCrFeNiX_0.4(X=Al, Nb, Ta) high entropy alloys fabricated by powder plasma arc additive manufacturing[J]. Journal of Alloys and Compounds, 2020, 857: 157625.