Processing map for oxide dispersion strengthening Cu alloys based on experimental results and machine learning modelling

Abstract

Oxide dispersion strengthened (ODS) alloys are extensively used owing to high thermostability and creep strength contributed from uniformly dispersed fine oxides particles. However, the existence of these strengthening particles also deteriorates the processability and it is of great importance to establish accurate processing maps to guide the thermomechanical processes to enhance the formability. In this study, we performed particle swarm optimization-based back propagation artificial neural network model to predict the high temperature flow behavior of 0.25wt% Al₂O₃ particle-reinforced Cu alloys, and compared the accuracy with that of derived by Arrhenius-type constitutive model and back propagation artificial neural network model. To train these models, we obtained the raw data by fabricating ODS Cu alloys using the internal oxidation and reduction method, and conducting systematic hot compression tests between 400 and 800°C with strain rates of 10⁻²–10 s⁻¹. At last, processing maps for ODS Cu alloys were proposed by combining processing parameters, mechanical behavior, microstructure characterization, and the modeling results achieved a coefficient of determination higher than >99%.

Keywords

oxide dispersion strengthened Cu alloys / constitutive model / machine learning / hot deformation / processing maps

References

[1] Liu FX, Liu XH, Xie GL, Wu Y, Chen CG. Studies on thermal stability, softening behavior and mechanism of an ADS copper alloy at elevated temperatures. J. Mater. Sci. Technol., 2024, 186: 79.

[2] Li P, Chen CG, Zhang CZ, et al. . Effects of ball milling on powder particle boundaries and properties of ODS copper. High Temp. Mater. Process., 2021, 40(1): 361.

[3] Nagorka MS, Levi CG, Lucas GE, Ridder SD. The potential of rapid solidification in oxide-dispersion-strengthened copper alloy development. Mater. Sci. Eng. A, 1991, 142(2): 277.

[4] Liao QY, Jiang YC, Le QC, et al. . Hot deformation behavior and processing map development of AZ110 alloy with and without addition of La-rich Mish Metal. J. Mater. Sci. Technol., 2021, 61: 1.

[5] Lu DD, Li JF, Guo YJ, et al. . Hot processing map and dynamic precipitation behavior of 1460 Al–Li alloy during hot deformation. Met. Mater. Int., 2023, 29(6): 1652.

[6] Sui FL, Xu LX, Chen LQ, Liu XH. Processing map for hot working of Inconel 718 alloy. J. Mater. Process. Technol., 2011, 211(3): 433.

[7] Rajput SK, Chaudhari GP, Nath SK. Characterization of hot deformation behavior of a low carbon steel using processing maps, constitutive equations and Zener-Hollomon parameter. J. Mater. Process. Technol., 2016, 237: 113.

[8] Ahmad S, Alankar A, Tathavadkar V, Narasimhan K. Investigation of tensile flow behavior of Al–Mg alloy at warm temperature: Constitutive modelling and microstructural evolution. Met. Mater. Int., 2024, 30(7): 1831.

[9] Athimulam MR, Paul J, Gangolu S, Babu SMJ. Development of constitutive models and hot-working processing map for Al–12Ce–0.4Sc alloys. Int. J. Miner. Metall. Mater., 2025, 32(7): 1655.

[10] G.L. Tian, L.J. Xu, H. Fang, et al., Deformation behavior and microstructure evolution of TZM alloy with 1.0 wt%ZrO₂ under high temperature compression, Int. J. Refract. Met. Hard Mater., 117(2023), art. No. 106382.

[11] Zhou X, Wang KL, Lu SQ, Li X, Ouyang DL. Hot deformation behavior of Ti2041 alloy based on BP neural network and 3D processing map. Rare Met. Mater. Eng., 2021, 50(4): 1233

[12] D.W. Li, J.X. Liu, Y.S. Fan, X.G. Yang, and W.Q. Huang, A preliminary discussion about the application of machine learning in the field of constitutive modeling focusing on alloys, J. Alloy. Compd., 976(2024), art. No. 173210.

[13] Kareem SA, Anaele JU, Aikulola EO, et al. . Hot deformation behaviour, constitutive model description, and processing map analysis of superalloys: An overview of nascent developments. J. Mater. Res. Technol., 2023, 26: 8624.

[14] M. Karimzadeh, M. Malekan, H. Mirzadeh, N. Saini, and L. Li, Hot deformation behavior analysis of as-cast CoCrFeNi high entropy alloy using Arrhenius-type and artificial neural network models, Intermetallics, 168(2024), art. No. 108240.

[15] C.Z. Fu, C.C. Tao, H.J. Huang, et al., Exploring microstructure evolution and machine-learning methods based on SCAT-CIWOA-BP-DMM theory during hot deformation of 56Ni–32Ti–12Hf alloy, Intermetallics, 171(2024), art. No. 108342.

[16] Z.X. Wei, X.X. Su, D.X. Wang, et al., Three-dimensional processing map based on BP-ANN and interface microstructure of Fe/Al laminated sheet, Mater. Chem. Phys., 297(2023), art. No. 127431.

[17] Kareem SA, Anaele JU, Olanrewaju OF, et al. . Insights into hot deformation of medium entropy alloys: Softening mechanisms, microstructural evolution, and constitutive modelling: A comprehensive review. J. Mater. Res. Technol., 2024, 29: 5369.

[18] Wan P, Zou H, Wang KL, Zhao ZZ. Hot deformation behaviors of Ti–22Al–26Nb–2Ta alloy based on GA-LSSVM and 3D processing map. Met. Mater. Int., 2021, 27(10): 4235.

[19] Pan GF, Wang FY, Shang CL, et al. . Advances in machine learning- and artificial intelligence-assisted material design of steels. Int. J. Miner. Metall. Mater., 2023, 30(6): 1003.

[20] Wu SW, Zhou XG, Cao GM, Liu ZY, Wang GD. The improvement on constitutive modeling of Nb–Ti micro alloyed steel by using intelligent algorithms. Mater. Des., 2017, 116: 676.

[21] Jain R, Umre P, Sabat RK, Kumar V, Samal S. Constitutive and artificial neural network modeling to predict hot deformation behavior of CoFeMnNiTi eutectic high-entropy alloy. J. Mater. Eng. Perform., 2022, 31(10): 8124.

[22] Ashtiani HRR, Shayanpoor AA. Hot deformation characterization of pure aluminum using artificial neural network (ANN) and processing map considering initial grain size. Met. Mater. Int., 2021, 27(12): 5017.

[23] Hu W, Ma ZW, Ji SD, Qi S, Chen MF, Jiang WH. Improving the mechanical property of dissimilar Al/Mg hybrid friction stir welding joint by PIO-ANN. J. Mater. Sci. Technol., 2020, 53: 41.

[24] P. Wan, H. Zou, K.L. Wang, and Z.Z. Zhao, Research on hot deformation behavior of Zr-4 alloy based on PSO-BP artificial neural network, J. Alloy. Compd., 826(2020), art. No. 154047.

[25] Wu F, Chen Y. Maximizing English teaching efficacy with particle swarm optimization-driven neural network training. IEEE Access, 2024, 12: 86232.

[26] D.L. Zhang, X.P. Huang, T.T. Wang, M. Habibi, I. Albaijan, and E. Toghroli, Dynamic stability improvement in spinning FG-piezo cylindrical structure using PSO-ANN and firefly optimization algorithm, Mater. Sci. Eng. B, 302(2024), art. No. 117210.

[27] Eldeghady GS, Kamal HA, Hassan MAM. Fault diagnosis for PV system using a deep learning optimized via PSO heuristic combination technique. Electr. Eng., 2023, 105(4): 2287.

[28] Zhou XY, Yi DQ, Nyborg L, Hu Z, Huang J, Cao Y. Influence of Ag addition on the microstructure and properties of copper-alumina composites prepared by internal oxidation. J. Alloy. Compd., 2017, 722: 962.

[29] Rajkovic V, Bozic D, Devecerski A, Jovanovic MT. Characteristic of copper matrix simultaneously reinforced with nano- and micro-sized Al₂O₃ particles. Mater. Charact., 2012, 67: 129.

[30] Zhang YF, Ji Z, Jia CC, Liu GM, Wan FR, Zhan Q. Influence of lanthanum on enhancement of mechanical and electrical properties of Cu–Al₂O₃ composites. J. Rare Earths, 2019, 37(5): 534.

[31] Y.C. Zhao, L.J. Xu, M.Y. Guo, et al., Microstructure evolution of W-1.0m-ZrO₂ alloy during high temperature deformation, J. Alloy. Compd., 921(2022), art. No. 166153.

[32] L.J. Xu, T.L. Sun, Y.C. Zhou, F.N. Xiao, M.J. Zhang, and S.Z. Wei, Evaluating compressive property and hot deformation behavior of molybdenum alloy reinforced by nanoscale zirconia particles, J. Alloy. Compd., 860(2021), art. No. 158289.

[33] Yao ZH, Wu SC, Dong JX, Yu QY, Zhang MC, Han GW. Constitutive behavior and processing maps of low-expansion GH909 superalloy. Int. J. Miner. Metall. Mater., 2017, 24(4): 432.

[34] Broyles SE, Anderson KR, Groza JR, Gibeling JC. Creep deformation of dispersion-strengthened copper. Metall. Mater. Trans. A, 1996, 27(5): 1217.

[35] Wang FL, Li YP, Xie GQ, et al. . Investigation on hot deformation behavior of nanoscale TiC-strengthened Cu alloys fabricated by mechanical milling. Mater. Sci. Eng. A, 2016, 668: 1.

[36] Sellars CM, McTegart WJ. On the mechanism of hot deformation. Acta Metall., 1966, 14(9): 1136.

[37] Ding ZY, Hu QD, Zeng L, Li JG. Hot deformation characteristics of as-cast high-Cr ultra-super-critical rotor steel with columnar grains. Int. J. Miner. Metall. Mater., 2016, 23(11): 1275.

[38] Lu HT, Li DZ, Li SY, Chen YA. Hot deformation behavior of Fe–27.34Mn–8.63Al–1.03C lightweight steel. Int. J. Miner. Metall. Mater., 2023, 30(4): 734.

[39] Chen H, Yang YM, Hu CL, et al. . Hot deformation behavior of novel high-strength Mg–0.6Mn–0.5Al–0.5Zn–0.4Ca alloy. Int. J. Miner. Metall. Mater., 2023, 30(12): 2397.

[40] Medina SF, Hernandez CA. General expression of the Zener-Hollomon parameter as a function of the chemical composition of low alloy and microalloyed steels. Acta Mater., 1996, 44(1): 137.

[41] Li Z, Chen YB, Wei SZ, Xiao FN, Siyal SH, Xu LJ. Flow behavior and processing map for hot deformation of W–1.5ZrO₂ alloy. J. Alloy. Compd., 2019, 802: 118.

[42] J.C. Long, Q.X. Xia, G.F. Xiao, Y. Qin, and S. Yuan, Flow characterization of magnesium alloy ZK61 during hot deformation with improved constitutive equations and using activation energy maps, Int. J. Mech. Sci., 191(2021), art. No. 106069.

[43] N.N. Moghadam and S. Serajzadeh, Warm and hot deformation behaviors and hot workability of an aluminum–magnesium alloy using artificial neural network, Mater. Today Commun., 35(2023), art. No. 105986.

[44] W.H. Liao, C.W. Tsai, Y.C. Tzeng, W.R. Wang, C.S. Chen, and J.W. Yeh, Exploring hot deformation behavior of equimolar CoCrFeNi high-entropy alloy through constitutive equations and microstructure characterization, Mater. Charact., 205(2023), art. No. 113234.

[45] Lin YC, Chen MS, Zhong J. Constitutive modeling for elevated temperature flow behavior of 42CrMo steel. Comput. Mater. Sci., 2008, 42(3): 470.

[46] Xu S, Xu XD, Jia WT, Liu WB, Li JL, Li DA. Microstructure–property mapping modeling for AZ31 alloy rolling deformation using improved PSO-BP neural network. J. Mater. Res. Technol., 2023, 25: 2127.

[47] S. Kumar, H. Pradhan, N. Shah, Rahul M R, and G. Phanikumar, Machine learning enabled processing map generation for high-entropy alloy, Scripta Mater., 234(2023), art. No. 115543.

[48] Li H, Tian BH, Zhou M, Ma ZP, Jing K, Liu Y. Hot deformation behavior and hot processing map of Al₂O₃–Cu/25Cr composite. Trans. Mater. Heat Treat., 2024, 45(6): 139

[49] G.Z. Quan, Y. Zhang, S. Lei, and W. Xiong, Characterization of flow behaviors by a PSO-BP integrated model for a medium carbon alloy steel, Materials, 16(2023), No. 8, art. No. 2982.

[50] Prasad YVRK, Seshacharyulu T. Modelling of hot deformation for microstructural control. Int. Mater. Rev., 1998, 43(6): 243.

[51] Prasad YVRK. Author’s reply: Dynamic materials model: Basis and principles. Metall. Mater. Trans. A, 1996, 27(1): 235.

[52] Park SY, Kim WJ. Difference in the hot compressive behavior and processing maps between the as-cast and homogenized Al–Zn–Mg–Cu (7075) alloys. J. Mater. Sci. Technol., 2016, 32(7): 660.

RIGHTS & PERMISSIONS

University of Science and Technology Beijing