Machine-learning-assisted prediction of the mechanical properties of Cu-Al alloy

Abstract

The machine-learning approach was investigated to predict the mechanical properties of Cu-Al alloys manufactured using the powder metallurgy technique to increase the rate of fabrication and characterization of new materials and provide physical insights into their properties. Six algorithms were used to construct the prediction models, with chemical composition and porosity of the compacts chosen as the descriptors. The results show that the sequential minimal optimization algorithm for support vector regression with a puk kernel (SMOreg/puk) model demonstrated the best prediction ability. Specifically, its predictions exhibited the highest correlation coefficient and lowest error among the predictions of the six models. The SMOreg/puk model was subsequently applied to predict the tensile strength and hardness of Cu-Al alloys and provide guidance for composition design to achieve the expected values. With the guidance of the SMOreg/puk model, Cu-12Al-6Ni alloy with a tensile strength (390 MPa) and hardness (HB 139) that reached the expected values was developed.

Keywords

powder metallurgy / tensile strength / hardness / machine learning / Cu-Al alloy / SMOreg/puk

References

[1] Liu JL, Huang HY, Xie JX. Effects of aging treatment on the microstructure and superelasticity of columnar-grained Cu₇₁Al₁₈Mn₁₁ shape memory alloy. Int. J. Miner. Metall. Mater., 2016, 23(10): 1157

[2] Izadinia M, Dehghani K. Microstructural evolution and mechanical properties of nanostructured Cu-Al-Ni shape memory alloys. Int. J. Miner. Metall. Mater., 2012, 19(4): 333

[3] Sata A, Ravi B. Comparison of some neural network and multivariate regression for predicting mechanical properties of investment casting. J. Mater. Eng. Perform., 2014, 23(8): 2953

[4] Altinkok N, Koker R. Neural network approach to prediction of bending strength and hardening behaviour of particulate reinforced (Al—Si—Mg)—aluminium matrix composites. Mater. Des., 2004, 25(7): 595

[5] Zhao B, Yu TY, Ding WF, Li XY, Su HH. BP neural network based flexural strength prediction of open-porous Cu—Sn—Ti composites. Prog. Nat. Sci., 2018, 28(3): 315

[6] Tang JL, Cai CZ, Huang SJ, Xiao TT. Strength prediction for Al—Cu—Mg—Ag alloy based on support vector regression. J. Aeronaut. Mater., 2012, 32(5): 92

[7] Liu GX, Jia LN, Kong B, Feng SB, Zhang HR, Zhang H. Artificial neural network application to microstructure design of Nb—Si alloy to improve ultimate tensile strength. Mater. Sci. Eng. A, 2017, 707, 452

[8] Yang XW, Zhu JC, Nong ZS, He D, Lai ZH, Liu Y, Liu FW. Prediction of mechanical properties of A357 alloy using artificial neural network. Trans. Nonferrous Met. Soc. China, 2013, 23(3): 788

[9] Razavi SA, Ashrafizadeh F, Fooladi S. Prediction of age hardening parameters for 17-4PH stainless steel by artificial neural network and genetic algorithm. Mater. Sci. Eng. A, 2016, 675, 147

[10] Wu D, Wang WL, Zhang LG, Wang ZY, Zhou KC, Liu LB. New high-strength Ti—Al—V—Mo alloy: from high-throughput composition design to mechanical properties. Int. J. Miner. Metall. Mater., 2019, 26(9): 1151

[11] Lv YT, Wang LQ, Mao JW, Lu WJ. Recent advances of nickel—aluminum bronze (NAB). Rare Met. Mater. Eng., 2016, 45(3): 815

[12] Deng ZH, Yin HQ, Jiang X, Zhang C, Zhang KQ, Zhang T, Xu B, Zheng QJ, Qu XH. Machine leaning aided study of sintered density in Cu-Al alloy. Comput. Mater. Sci., 2018, 155, 48

[13] Wan H, Si NC, Liu GL, Li M, Xu C, Xu L. Effect of rare earth on abrasion resistance of multi-aluminum bronze. Chin. Rare Earths, 2015, 36(4): 81

[14] Li YY, Xia W, Zhang W, Luo ZQ. Strong and wear resistant aluminum bronze alloy and its tribological characteristics. Chin. J. Nonferrous Met., 1996, 6(3): 76

[15] Lahiri BB, Sarkar A, Bagavathiappan S, Nagesha A, Saravanan T, Sandhya R, Jayakumar T, Philip J. Studies on temperature evolution during fatigue cycling of Ni—Al bronze (NAB) alloy using infrared thermography. Insight: Non-Destr. Test. Cond. Monit., 2016, 58(2): 70

[16] Zhang B, Xu XJ, Chen SD, Jiang W. Effects of zirconium and strontium on microstructure and properties of nickel aluminium bronze ingot. Trans. Mater. Heat Treat., 2015, 36(3): 62

[17] Ji JM, Lu YY, Wu J, Meng GC. Microstructure and wear resistance of new aluminum bronze with Ce. Spec. Cast. Nonferrous Alloys, 2013, 33(7): 672

[18] Guo ZL, Tang WX, Zhang HL, Xu J, He G. Influences of alloying elements on the properties of nickel aluminum bronzes. Dev. Appl. Mater., 2003, 18(2): 39

[19] Thossatheppitak B, Suranuntchai S, Uthaisangsuk V, Manonukul A, Mungsuntisuk P. Mechanical properties at high temperatures and microstructures of a nickel aluminum bronze alloy. Adv. Mater. Res., 2013, 683, 82

[20] Anantapong J, Uthaisangsuk V, Suranuntchai S, Manonukul A. Effect of hot working on microstructure evolution of as-cast nickel aluminum bronze alloy. Mater. Des., 2014, 60, 233

[21] Dai AL, Yan GC, Zhu ZY, Liu JS. Effect of aluminum content on microstructure and properties of casting CuAl_xFe₃. Nonferrous Met. Eng., 2013, 3(4): 22

[22] Wang JH, Jiang XX, Li SZ. Microstructure and properties of boron—aluminum bronze. Acta Metall. Sin., 1996, 32(10): 1039

[23] Wang BW, Wang T, Wang ZT. Copper Alloy and Its Processing Technology, 2007, Beijing, Chemical Industry Press, 45

[24] Li YW, Xiao LR, Zhang W, Zhao XJ, Song YF, Guo L. Microstructure and mechanical properties of aluminum bronze with different Mn contents. Chin. J. Rare Met., 2017, 41(9): 985

[25] Dai AL, Yan GC, Zhu ZY, Zhu K, Chen H, Niu WM. Wear-friction behavior of novel high aluminum bronzes alloy Cu—12Al—X in high temperature condition. Chin. J. Nonferrous Met., 2013, 23(11): 3083

[26] Li WS, Wang ZP, Lu Y, Jin YH, Yuan LH, Wang F. Mechanical and tribological properties of a novel aluminum bronze material for drawing dies. Wear, 2006, 261(2): 155

[27] Jin YH, Lu Y, Wang ZP, Li W S, Xu JL. Anti-frictional characteristic of new complex Al—bronze Cu—14Al. Spec. Cast. Nonferrous Alloys, 2004, 24(3): 32

[28] Xu JL, Wang ZP, Chen C, La PQ. Research into a new high-strength aluminium bronze alloy. Int. J. Mater. Prod. Technol., 2004, 21(5): 443

[29] Li Z, Li CG. The preparation of abrasion-resistive, antifrietional complex aluminum bronze. Shanghai Nonferrous Met., 1993, 14(6): 13

[30] Liu F. Research on Microstructure and Processability of High Aluminium Bronze Alloy, 2014, Ganzhou, Jiangxi University of Science and Technology, 24

[31] Sadayappan M, Sahoo M, Michels HT. Optimization of composition and mechanical properties of aluminum bronze alloy C95400. Trans. Am. Foundry Soc., 2004, 112, 509

[32] Wang AQ, Xu R, Chi CZ. The friction characteristic and tensile properties of casting Al—bronze. J. Liaoning Tech. Univ. (Nat. Sci. Ed.), 2000, 19(1): 87

[33] Dai AL, Yan GC, Zhu ZY, Liu JS. Effects of heating treatment on friction and wear properties of novel high aluminum bronze alloy. Mater. Mech. Eng., 2013, 13(12): 333

[34] Wang CX, Jiang CH, Chai Z, Chen M, Wang LB, Ji V. Estimation of microstructure and corrosion properties of peened nickel aluminum bronze. Surf. Coat. Technol., 2017, 313, 136

[35] Hu DL, Cao JC, Zhou Z, Zhang SQ. Organism and properties of high-strength and wear-resistant bronze. Non-ferrous Met., 1998, 50(3): 99

[36] Qin ZB, Zhang Q, Luo Q, Wu Z, Shen B, Liu L, Hu WB. Microstructure design to improve the corrosion and cavitation corrosion resistance of a nickel—aluminum bronze. Corros. Sci., 2018, 139, 255

[37] Moussa ME, Waly MA, Amin M. Effect of high intensity ultrasonic treatment on microstructural modification and hardness of a nickel—aluminum bronze alloy. J. Alloys Compd., 2018, 741, 804

[38] Xu XJ, Chen SD, Pan L, Wei J, Shi GF. Microstructure and properties of Zr microalloying nickel aluminum bronze ingot. Chin. J. Rare Met., 2014, 38(1): 158

[39] Yaşar M, Altunpak Y. The effect of aging heat treatment on the sliding wear behaviour of Cu-Al-Fe alloys. Mater. Des., 2009, 30(3): 878

[40] Zhang CZ, Sun QX, Zhang HX. Sintering mechanism of Cu-Al system powder billet. J. Northeast Univ. Technol, 1989, 10(5): 561

[41] Wang R, Bao YP, Li YH, Yan ZJ, Li DZ, Kang Y. Influence of metallurgical processing parameters on defects in cold-rolled steel sheet caused by inclusions. Int. J. Miner. Metall. Mater., 2019, 26(4): 440

[42] Panda L, Banerjee PK, Biswal SK, Venugopal R, Mandre NR. Artificial neural network approach to assess selective flocculation on hematite and kaolinite. Int. J. Miner. Metall. Mater., 2014, 21(7): 637

[43] Xu K, Ai YH, Wu XY. Application of multi-scale feature extraction to surface defect classification of hot-rolled steels. Int. J. Miner. Metall. Mater., 2013, 20(1): 37

[44] Zhang KQ, Yin HQ, Jiang X, Liu XQ, He F, Deng ZH, Khan DF, Zheng QJ, Qu XH. A novel approach to predict green density by high-velocity compaction based on the materials informatics method. Int. J. Miner. Metall. Mater., 2019, 26(2): 194

[45] Yang FF, Kang HJ, Guo EY, Li RG, Chen ZN, Zeng YH, Wang TM. The role of nickel in mechanical performance and corrosion behaviour of nickel—aluminium bronze in 3.5wt% NaCl solution. Corros. Sci., 2018, 139, 333

[46] Kang QF, Hu SB, Zeng SQ, Chen GK. Heat treatment strengthening of nickel—aluminum bronze alloy for marine propeller. Chin. J. Nonferrous Met., 2018, 28(1): 107

[47] Tian GQ, Lu Y, Lu K, Li WS. Influence of Co on the wear behavior of high-aluminum bronze. Rare Met. Mater. Eng., 2008, 27(10): 1833

[48] Rathore SS, Dabhade VV. Dimensional change during sintering of Fe—Cu—C alloys: a comparative study. Trans. Indian Inst. Met., 2016, 69(5): 991

[49] Miettinen J. Thermodynamic description of the Cu-Al-Ni system at the Cu-Ni side. Calphad, 2005, 29(1): 40

[50] Lin YL, Hsieh JG, Wu HK, Jeng JH. Three-parameter sequential minimal optimization for support vector machines. Neurocomputing, 2011, 74(17): 3467

[51] Üstün B, Melssen WJ, Buydens LMC. Facilitating the application of support vector regression by using a universal pearson VII function based kernel. Chemom. Intell. Lab. Syst., 2006, 81(1): 29