A novel method for workpiece deformation prediction by amending initial residual stress based on SVR-GA

Abstract

High-precision manufactured thin-walled pure copper components are widely adopted in precision physics experiments, which require workpieces with extremely high machining accuracy. Double-sided lapping is an ultra-precision machining method for obtaining high-precision surfaces. However, during double-sided lapping, the residual stress of the components tends to cause deformation, which affects the machining accuracy of the workpiece. Therefore, a model to predict workpiece deformation derived from residual stress in actual manufacturing should be established. To improve the accuracy of the prediction model, a novel method for predicting workpiece deformation by amending the initial residual stress slightly based on the support vector regression (SVR) and genetic algorithm (GA) is proposed. Firstly, a finite element method model is established for double-sided lapping to understand the deformation process. Subsequently, the SVR model is utilized to construct the relationship between residual stress and deformation. Next, the GA is used to determine the best residual stress adjustment value based on the actual deformation of the workpiece. Finally, the method is validated via double-sided lapping experiments.

Keywords

Initial residual stress / Double-sided lapping / Support vector regression (SVR) / Genetic algorithm (GA) / Deformation

References

[1] Zhang S (2019) Research on ultra-precision machining of pure copper sheet with large diameter-thickness ratio. Dissertation, Zhejiang University of Technology, Zhejiang

[2] Pan B, Kang RK, Guo J, et al. Precision fabrication of thin copper substrate by double-sided lapping and chemical mechanical polishing. J Manuf Process, 2019, 44: 47-54.

[3] Li BH, Gao HJ, Deng HB, et al. Investigation on the influence of the equivalent bending stiffness of the thin-walled parts on the machining deformation. Int J Adv Manuf Tech, 2019, 101(5/8): 1171-1182.

[4] Li YL, Zhou K, Tan PF, et al. Modeling temperature and residual stress fields in selective laser melting. Int J Mech Sci, 2017, 136: 24-35.

[5] Wang ZJ, Chen WY, Zhang YD, et al. Study on the machining distortion of thin-walled part caused by redistribution of residual stress. Chin J Aeronaut, 2015, 18(2): 175-179.

[6] Richter-Trummer V, Koch D, Witte A, et al. Methodology for prediction of distortion of workpieces manufactured by high speed machining based on an accurate through-the-thickness residual stress determination. Int J Adv Manuf Tech, 2013, 68(9/12): 2271-2281.

[7] Guo H, Zuo DW, Wu HB, et al. Prediction on milling distortion for aero-multi-frame parts. Mat Sci Eng A Struct, 2009, 499(1/2): 230-233.

[8] Gao HJ, Zhang YD, Wu Q, et al. An analytical model for predicting the machining deformation of a plate blank considers biaxial initial residual stress. Int J Adv Manuf Tech, 2017, 93(1/4): 1473-1486.

[9] Cerutti X, Mocellin K. Parallel finite element tool to predict distortion induced by initial residual stress during machining of aeronautical parts. Int J Mater Form, 2015, 8(2): 255-268.

[10] Cerutti X, Arsene S, Mocellin K. Prediction of machining quality due to the initial residual stress redistribution of aerospace structural parts made of low-density aluminium alloy rolled plates. Int J Mater Form, 2016, 9(5): 677-690.

[11] Huang XM, Sun J, Li JF. Finite element simulation and experimental investigation on the residual stress-related monolithic component deformation. Int J Adv Manuf Tech, 2015, 77(5/8): 1035-1041.

[12] Yang Y, Li M, Li KR. Comparison and analysis of main effect elements of machining distortion for aluminum alloy and titanium alloy aircraft monolithic component. Int J Adv Manuf Tech, 2014, 70(9/12): 1803-1811.

[13] Dong HY, Ke YL. Study on machining deformation of aircraft monolithic component by FEM and experiment. Chin J Aeronaut, 2006, 19(3): 247-254.

[14] Righetti VAN, Campos TMB, Robatto LB, et al. Non-destructive surface residual stress profiling by multireflection grazing incidence X-ray diffraction: a 7050 Al alloy study. Exp Mech, 2020, 60(2): 1-6.

[15] Robinson JS, Hossain S, Truman CE, et al. Residual stress in 7449 aluminium alloy forgings. Mater Sci Eng A Struct, 2010, 527(10/11): 2603-2612.

[16] Fu SL, Feng PF, Ma Y, et al. Initial residual stress measurement based on piecewise calculation methods for predicting machining deformation of aeronautical monolithic components. Int J Adv Manuf Tech, 2020, 108(7/8): 2063-2078.

[17] Wang Q, Wang B, Ma DC, et al. Residual stress measurement for ion-implanted NiTi alloy by using moiré interferometry and hole-drilling combined method. Chin J Aeronaut, 2006, S1: 27-30.

[18] Zhang Z, Yang YF, Li L, et al. Assessment of residual stress of 7050–T7452 aluminum alloy forging using the contour method. Mater Sci Eng A Struct, 2015, 644: 61-68.

[19] Korsunsky AM, Sebastiani M, Bemporad E. Residual stress evaluation at the micrometer scale: analysis of thin coatings by FIB milling and digital image correlation. Surf Coat Tech, 2010, 205(7): 2393-2403.

[20] Irastorza-Landa A, Grilli N, Swygenhoven HV. Laue micro-diffraction and crystal plasticity finite element simulations to reveal a vein structure in fatigued Cu. J Mech Phys Solids, 2017, 104(1): 157-171.

[21] Du JX, Yang YF, Zhu JP, et al. Research on aluminum alloy electrolysis process for stress delamination measurement. Tool Tech, 2019, 53(7): 50-55.

[22] Barile C, Casavola C, Pappalettera G et al (2014) Remarks on residual stress measurement by hole-drilling and electronic speckle pattern interferometry. Sci World J 2014:487149. https://doi.org/10.1155/2014/487149

[23] Guo J, Fu HY, Pan B, et al. Recent progress of residual stress measurement methods: a review. Chin J Aeronaut, 2019, 34(2): 54-78.

[24] Na MG, Kim JW, Lim DH, et al. Residual stress prediction of dissimilar metals welding at NPPs using support vector regression. Nucl Eng Des, 2008, 238(7): 1503-1510.

[25] Zhang P, Yin ZY, Jin YF, et al. A novel hybrid surrogate intelligent model for creep index prediction based on particle swarm optimization and random forest. Eng Geol, 2019, 265.

Funding

Key Research and Development Program(2018YFA0702900)

Science Challenge Project http://dx.doi.org/10.13039/501100013287(TZ2016006)

National Natural Science Foundation of China http://dx.doi.org/10.13039/501100001809(51975096)