Digital model for rapid prediction and autonomous control of die forging force for aluminum alloy aviation components

Abstract

Digital modeling and autonomous control of the die forging process are significant challenges in realizing high-quality intelligent forging of components. Using the die forging of AA2014 aluminum alloy as a case study, a machine-learning-assisted method for digital modeling of the forging force and autonomous control in response to forging parameter disturbances was proposed. First, finite element simulations of the forging processes were conducted under varying friction factors, die temperatures, billet temperatures, and forging velocities, and the sample data, including process parameters and forging force under different forging strokes, were gathered. Prediction models for the forging force were established using the support vector regression algorithm. The prediction error of F_f, that is, the forging force required to fill the die cavity fully, was as low as 4.1%. To further improve the prediction accuracy of the model for the actual F_f, two rounds of iterative forging experiments were conducted using the Bayesian optimization algorithm, and the prediction error of F_f in the forging experiments was reduced from 6.0% to 1.5%. Finally, the prediction model of F_f combined with a genetic algorithm was used to establish an autonomous optimization strategy for the forging velocity at each stage of the forging stroke, when the billet and die temperatures were disturbed, which realized the autonomous control in response to disturbances. In cases of −20 or −40°C reductions in the die and billet temperatures, forging experiments conducted with the autonomous optimization strategy maintained the measured F_f around the target value of 180 t, with the relative error ranging from −1.3% to +3.1%. This work provides a reference for the study of digital modeling and autonomous optimization control of quality factors in the forging process.

Keywords

aluminum alloy / forging force / prediction model / machine learning / intelligent control

References

[1] DursunT, SoutisC. Recent developments in advanced aircraft aluminium alloys. Mater. Des., 2014, 56862.

[2] HeinzA, HaszlerA, KeidelC, MoldenhauerS, BenedictusR, MillerWS. Recent development in aluminium alloys for aerospace applications. Mater. Sci. Eng. A, 2000, 2801102.

[3] GronostajskiZ, PaterZ, MadejL, et al.. Recent development trends in metal forming. Arch. Civ. Mech. Eng., 2019, 193898.

[4] ParkJJ, HwangHS. Preform design for precision forging of an asymmetric rib-web type component. J. Mater. Process. Technol., 2007, 187–188595.

[5] GaoPF, YanXG, FeiMY, ZhanM, LiYK. Formation mechanisms and rules of typical types of folding defects during die forging. Int. J. Adv. Manuf. Technol., 2019, 1041–41603.

[6] ZhangYQ, JiangSY, ZhaoYN, ShanDB. Isothermal precision forging of aluminum alloy ring seats with different preforms using FEM and experimental investigation. Int. J. Adv. Manuf. Technol., 2014, 729–121693.

[7] ChanWL, FuMW, LuJ, ChanLC. Simulation-enabled study of folding defect formation and avoidance in axisymmetrical flanged components. J. Mater. Process. Technol., 2009, 209115077.

[8] GuoJ, LiuLG, SunYL, LiQ, RenXJ, YangQX. Parameter optimization during forging process of a novel highspeed-steel cold work roll. J. Mater. Eng. Perform., 2016, 251188.

[9] J.H. Zhao, Y.L. Deng, J. Zhang, and J.G. Tang, Effect of forging speed on the formability, microstructure and mechanical properties of isothermal precision forged of Al–Zn–Mg–Cu alloy, Mater. Sci. Eng. A, 767(2019), art. No. 138366.

[10] HeHL, HuangSQ, YiYP, GuoWF. Simulation and experimental research on isothermal forging with semi-closed die and multi-stage-change speed of large AZ80 magnesium alloy support beam. J. Mater. Process. Technol., 2017, 246198.

[11] ZhangQ, FelderE, BruschiS. Evaluation of friction condition in cold forging by using T-shape compression test. J. Mater. Process. Technol., 2009, 209175720.

[12] XuWJ, LiWH, WangYS. Experimental and theoretical analysis of wear mechanism in hot-forging die and optimal design of die geometry. Wear, 2014, 3181–278.

[13] J.X. Xie, Prospects of materials genome engineering frontiers, Mater. Genome Eng. Adv., 1(2023), No. 2, art. No. e17.

[14] J.X. Xie, Materials Genome Engineering Advances: A new journal dedicated to digital and intelligent materials research and development, Mater. Genome Eng. Adv., 1(2023), No. 1, art. No. e9.

[15] LiDY, PengYH, YinJL. Optimization of metal-forming process via a hybrid intelligent optimization technique. Struct. Multidiscip. Optim., 2007, 343229.

[16] AzariA, PoursinaM, PoursinaD. Radial forging force prediction through MR, ANN, and ANFIS models. Neural Comput. Appl., 2014, 253–4849.

[17] KampenD, RichterJ, BlohmT, et al.. Design of a genetic algorithm to preform optimization for hot forging processes. Int. J. Mater. Form., 2020, 13177.

[18] ChenDD, LinYC. Online optimizing hot forming parameters for alloy parts based on action-dependent heuristic dynamic programming. Int. J. Adv. Manuf. Technol., 2019, 1049–123745.

[19] L. Jiang, Z.H. Zhang, H. Hu, X.Q. He, H.D. Fu, and J.X. Xie, A rapid and effective method for alloy materials design via sample data transfer machine learning, NPJ Comput. Mater., 9(2023), No. 1, art. No. 26.

[20] CecenA, DaiHJ, YabansuYC, KalidindiSR, SongL. Material structure–property linkages using three-dimensional convolutional neural networks. Acta Mater., 2018, 14676.

[21] YangZJ, YabansuYC, JhaD, et al.. Establishing structure-property localization linkages for elastic deformation of three-dimensional high contrast composites using deep learning approaches. Acta Mater., 2019, 166335.

[22] RenYM, ZhangYC, DingYY, et al.. Finite element modeling of direct metal laser solidification process: Sensor data replication and use in defect detection and data reduction via machine learning. Chem. Eng. Res. Des., 2021, 171254.

[23] CaiHR, XiaoWC, ZhengKL. The prediction of part thickness using machine learning in aluminum hot stamping process with partition temperature control. Int. J. Adv. Manuf. Technol., 2022, 1195–63891.

[24] D.Z. Xue, P.V. Balachandran, J. Hogden, J. Theiler, D.Q. Xue, and T. Lookman, Accelerated search for materials with targeted properties by adaptive design, Nat. Commun., 7(2016), art. No. 11241.

[25] XueDZ, XueDQ, YuanRH, et al.. An informatics approach to transformation temperatures of NiTi-based shape memory alloys. Acta Mater., 2017, 125532.

[26] LiuYW, WangLY, ZhangH, et al.. Accelerated development of high-strength magnesium alloys by machine learning. Metall. Mater. Trans. A, 2021, 523943.

[27] WenC, ZhangY, WangCX, et al.. Machine learning assisted design of high entropy alloys with desired property. Acta Mater., 2019, 170109.

[28] H.T. Zhang, H.D. Fu, S.C. Zhu, W. Yong, and J.X. Xie, Machine learning assisted composition effective design for precipitation strengthened copper alloys, Acta Mater., 215(2021), art. No. 117118.

[29] ZhangHT, FuHD, ShenYH, XieJX. Rapid design of secondary deformation-aging parameters for ultra-low Co content Cu–Ni–Co–Si–X alloy via Bayesian optimization machine learning. Int. J. Miner. Metall. Mater., 2022, 2961197.

[30] PrabhuTR. Simulations and experiments of hot forging design and evaluation of the aircraft landing gear barrel Al alloy structure. J. Mater. Eng. Perform., 2016, 2541257.

[31] LangLH, XuAJ, LiF. Precision forging technological optimization for 7075 aluminum alloy complex component with limbs. JOM, 2012, 642309.

[32] SánchezVDA. Advanced support vector machines and kernel methods. Neurocomputing, 2003, 551–25.

[33] ZhangHT, FuHD, HeXQ, et al.. Dramatically enhanced combination of ultimate tensile strength and electric conductivity of alloys via machine learning screening. Acta Mater., 2020, 200803.

[34] W. Yong, H.T. Zhang, H.D. Fu, Y.L. Zhu, J. He, and J.X. Xie, Improving prediction accuracy of high-performance materials via modified machine learning strategy, Comput. Mater. Sci., 204(2022), art. No. 111181.

[35] GuoZD, OngYS, LiuHT. Calibrated and recalibrated expected improvements for Bayesian optimization. Struct. Multidiscip. Optim., 2021, 6463549.

[36] LuXJ, HuangMH. Two-level modeling based intelligent integration control for time-varying forging processes. Ind. Eng. Chem Res., 2015, 54215690.

[37] GaratV, BernhartG, HervyL. Influence of design and process parameters on service life of nut hot forging die. J. Mater. Process. Technol., 2004, 1473359.

[38] LiuDH. Mathematical modeling analysis of genetic algorithms under schema theorem. J. Comput. Methods Sci. Eng., 2019, 19S1S131

[39] D.M. Rocke, Genetic algorithms + data structures = evolution programs, J. Am. Stat. Assoc., 95(2000), No. 449, art. No. 347.

[40] MaleAT, CockcroftMG. A method for the determination of the coefficient of friction of metals under conditions of bulk plastic deformation. J. Inst. Met., 1964, 93238

[41] LuoSY, YaoJN, LiJ, DuH, LiuHY, YuFP. Influence of forging velocity on temperature and phases of forged Ti–6Al–4V turbine blade. J. Mater. Res. Technol., 2020, 9612043.

RIGHTS & PERMISSIONS

University of Science and Technology Beijing