Prediction about residual stress and microhardness of material subjected to multiple overlap laser shock processing using artificial neural network

Abstract

In this work, the nickel-based powder metallurgy superalloy FGH95 was selected as experimental material, and the experimental parameters in multiple overlap laser shock processing (LSP) treatment were selected based on orthogonal experimental design. The experimental data of residual stress and microhardness were measured in the same depth. The residual stress and microhardness laws were investigated and analyzed. Artificial neural network (ANN) with four layers (4-N-(N-1)-2) was applied to predict the residual stress and microhardness of FGH95 subjected to multiple overlap LSP. The experimental data were divided as training-testing sets in pairs. Laser energy, overlap rate, shocked times and depth were set as inputs, while residual stress and microhardness were set as outputs. The prediction performances with different network configuration of developed ANN models were compared and analyzed. The developed ANN model with network configuration of 4-7-6-2 showed the best predict performance. The predicted values showed a good agreement with the experimental values. In addition, the correlation coefficients among all the parameters and the effect of LSP parameters on materials response were studied. It can be concluded that ANN is a useful method to predict residual stress and microhardness of material subjected to LSP when with limited experimental data.

Keywords

laser shock processing / residual stress / microhardness / artificial neural network

References

[1] SembiringJ P B A, AmanovA, PyunY S. Artificial neural network-based prediction model of residual stress and hardness of nickel-based alloys for UNSM parameters optimization [J]. Materials Today Communications, 2020, 25: 101391

[2] ShenX, ShuklaP, SubramaniyanA K, et al. . Residual stresses induced by laser shock peening in orthopaedic Ti-6Al-7Nb alloy [J]. Optics & Laser Technology, 2020, 131106446

[3] LuG, SokolD W, ZhangY, et al. . Nanosecond pulsed laser-generated stress effect inducing macro-micro-nano structures and surface topography evolution [J]. Applied Materials Today, 2019, 15171-184

[4] SadeghiH, AlitavoliM, DarvizehA, et al. . Dynamic plastic behaviour of strain rate sensitive tubes under axial impact [J]. Thin-Walled Structures, 2019, 143: 106220

[5] AlikhaniA, BeygiR, ZarezadehM M, et al. . Effect of Mg and Si on intermetallic formation and fracture behavior of pure aluminum-galvanized carbon-steel joints made by weld-brazing [J]. Journal of Central South University, 2021, 28(11): 3626-3638

[6] ZhuZ, WuJ, WuZ, et al. . Femtosecond laser micro/nano fabrication for bioinspired superhydrophobic or underwater superoleophobic surfaces [J]. Journal of Central South University, 2021, 28(12): 3882-3906

[7] PaekU C, GaglianoF. Thermal analysis of laser drilling processes [J]. IEEE Journal of Quantum Electronics, 1972, 8(2): 112-119

[8] ChuJ P, RigsbeeJ M, BanaśG, et al. . Laser-shock processing effects on surface microstructure and mechanical properties of low carbon steel [J]. Materials Science and Engineering A, 1999, 260(1–2): 260-268

[9] ArifA F M. Numerical prediction of plastic deformation and residual stresses induced by laser shock processing [J]. Journal of Materials Processing Technology, 2003, 136(1–3): 120-138

[10] NilssonN J. Artificial intelligence: A modern approach [J]. Artificial Intelligence, 1996, 82(1–2): 369-380

[11] ChenL, YinY, LiY, et al. . Multifunctional inverse sensing by spatial distribution characterization of scattering photons [J]. Opto-Electronic Advances, 2019, 2(9): 19001901-19001908

[12] ArtrithN, UrbanA. An implementation of artificial neural-network potentials for atomistic materials simulations: Performance for TiO₂ [J]. Computational Materials Science, 2016, 114135-150

[13] HuangZ, WuJ, XieF. Automatic recognition of surface defects for hot-rolled steel strip based on deep attention residual convolutional neural network [J]. Materials Letters, 2021, 293: 129707

[14] WangY, LouieD C, CaiJ, et al. . Deep learning enhances polarization speckle for in vivo skin cancer detection [J]. Optics & Laser Technology, 2021, 140107006

[15] MathewJ, KshirsagarR, ZabeenS, et al. . Machine learning-based prediction and optimisation system for laser shock peening [J]. Applied Sciences, 2021, 11(7): 2888

[16] WuJ, LiY, ZhaoJ, et al. . Prediction of residual stress induced by laser shock processing based on artificial neural networks for FGH4095 superalloy [J]. Materials Letters, 2021, 286129269

[17] ZhouL, LiY, HeW, et al. . Deforming TC6 titanium alloys at ultrahigh strain rates during multiple laser shock peening [J]. Materials Science and Engineering A, 2013, 578181-186

[18] Academic Committee of the Superalloys (CSM)China superalloys handbook [M], 2012, Beijing, China, Standards Press of China(in Chinese)

[19] TangZ, WangK, GengY, et al. . An investigation of the effect of warm laser shock peening on the surface modifications of [001]-oriented DD6 superalloy [J]. The International Journal of Advanced Manufacturing Technology, 2021, 113(7–8): 1973-1988

[20] VildA, TeixeiraS, KühnK, et al. . Orthogonal experimental design of titanium dioxide—Poly(methyl methacrylate) electrospun nanocomposite membranes for photocatalytic applications [J]. Journal of Environmental Chemical Engineering, 2016, 4(3): 3151-3158

[21] DhakalB, SwaroopS. Effect of laser shock peening on mechanical and microstructural aspects of 6061-T6 aluminum alloy [J]. Journal of Materials Processing Technology, 2020, 282116640

[22] SchalkoffR-JArtificial neural networks [M], 1997, New York, McGraw-Hill

[23] YinYStudy of flow law, microstructure and mechanical properties of 316L stainless steel by selective laser melting [D], 2019, Beijing, University of Science and Technology Beijing(in Chinese)

[24] WuJ, ZhaoJ, QiaoH, et al. . A method to determine the material constitutive model parameters of FGH4095 alloy treated by laser shock processing [J]. Applied Surface Science Advances, 2020, 1100029

[25] WangC, LiW, WangY, et al. . Study of electrochemical corrosion on Q235A steel under stray current excitation using combined analysis by electrochemical impedance spectroscopy and artificial neural network [J]. Construction and Building Materials, 2020, 247118562

[26] GuoW, SunR, SongB, et al. . Laser shock peening of laser additive manufactured Ti6Al4V titanium alloy [J]. Surface and Coatings Technology, 2018, 349503-510

[27] GillA, TelangA, MannavaS R, et al. . Comparison of mechanisms of advanced mechanical surface treatments in nickel-based superalloy [J]. Materials Science and Engineering A, 2013, 576: 346-355

[28] QiaoH, ZhaoJ, GaoY. Experimental investigation of laser peening on TiAl alloy microstructure and properties [J]. Chinese Journal of Aeronautics, 2015, 28(2): 609-616

[29] SungA H. Ranking importance of input parameters of neural networks [J]. Expert Systems with Applications, 1998, 15(3–4): 405-411

[30] LuG X, LiuJ D, QiaoH C, et al. . Microscopic surface topography of a wrought superalloy processed by laser shock peening [J]. Vacuum, 2016, 130: 25-33