This paper presents a novel machine learning model designed to predict residual stress and equivalent plastic deformation in metallic alloys undergoing surface mechanical attrition treatment. The dataset used for training was generated by numerically simulating surface mechanical attrition treatment on various alloys, such as SS316L, NiTi, Ti64, Al7075, and AZ31. The regression analysis of the proposed model exhibits exceptional predictive capabilities, with high R² values of 0.959 for residual stress and 0.911 for average equivalent plastic strain, alongside low root mean square error values of 0.035 and 0.088, respectively. Furthermore, the detailed examination of the correlation between input features and output targets revealed that the increase in values of residual stress and plastic strain in treated samples corresponded with heightened weight functions of processing parameters and material properties, respectively, within the machine learning model. A case study focusing on Al7075 was also provided, demonstrating the model's ability to adjust parameters effectively to achieve specific surface residual stress and plastic strain outcomes. Ultimately, the proposed model not only serves as a reliable predictor for the output targets but also functions as a valuable tool for characterizing the complex input–output relationships, thereby reducing the need for trial and error experimentation in real-world scenarios.
KangLMiXZhangX, et al.Detail characterization on the microstructure evolution of nickel-base alloy 600MA via surface mechanical attrition treatment. Mater Charact2023; 195: 112498.
2.
CuiGBaoCZhangM,et al.Effects of thermal aging on mechanical properties and microstructures of an interstitial high entropy alloy with ultrasonic surface mechanical attrition treatment. Mater Sci Eng A2022; 838: 142755.
3.
GaoPSunZRetraintD. Literature review on the fatigue properties of materials processed by surface mechanical attrition treatment (SMAT). Metals (Basel)2022; 12: 775.
4.
TangGOuZLiuF, et al.Enhancing wear resistance of aluminum alloy by fabricating a Ti-Al modified layer via surface mechanical attrition treatment. Tribol Int2024; 193: 109462.
5.
KazemiAHeidariAAminiK, et al.The effect of surface mechanical attrition treatment time on microstructure and mechanical properties of AZ31 Mg alloy. Prot Met Phys Chem Surfaces2023; 59: 1–8.
6.
YangHChenYFengH, et al.Optimized corrosion resistance in pure copper via surface mechanical attrition treatment and subsequent annealing. Mater Today Commun2023; 35: 105645.
7.
KumbharNKKumarVSinghD,et al.Gradient microstructure and properties of surface mechanical attrition treated AZ91D alloy: an effect of colliding balls velocity. Adv Eng Mater2023; 25.
8.
YangHZhangZShuJ,et al.Gradient nanostructure, enhanced surface integrity and fatigue resistance of Ti-6Al-7Nb alloy processed by surface mechanical attrition treatment. J Mater Sci Technol2024; 188: 252–269.
9.
OlugbadeTOLuJ. Literature review on the mechanical properties of materials after surface mechanical attrition treatment (SMAT). Nano Mater Sci2020; 2: 3–31.
10.
LiYRetraintDGaoP, et al.Effect of surface mechanical attrition treatment on torsional fatigue properties of a 7075 aluminum alloy. Metals (Basel)2022; 12: 785.
11.
GhoshSBibhanshuNSuwasS,et al.Surface mechanical attrition treatment of additively manufactured 316L stainless steel yields gradient nanostructure with superior strength and ductility. Mater Sci Eng A2021; 820: 141540.
12.
LinTChangTXieQ, et al.Surface morphology and gradient microstructural evolutions in pure titanium via surface severe plastic deformation. Mater Charact2022; 191: 112114.
13.
GrosdidierTNovelliM. Recent developments in the application of surface mechanical attrition treatments for improved gradient structures: processing parameters and surface reactivity. Mater Trans2019; 60: 1344–1355.
14.
NingJGaoBYuanX, et al.Strength and ductility improvement in a heterostructured Mg-Gd-Y alloy with inversely-gradient hardness distribution. J Mater Res Technol2024; 28: 3781–3793.
15.
GuoZZhouJSunZ, et al.Modelling mechanical behaviour of a gradient-microstructured material obtained by surface mechanical attrition treatment accounting for residual stresses. Mech Mater2023; 184: 104713. Available at: https://www.sciencedirect.com/science/article/pii/S016766362300159X.
WangCWangCWangL, et al.A dislocation density-based comparative study of grain refinement, residual stresses, and surface roughness induced by shot peening and surface mechanical attrition treatment. Int J Adv Manuf Technol2020; 108: 505–525.
PortellaQChemkhiMRetraintD.Influence of surface mechanical attrition treatment (SMAT) post-treatment on microstructural, mechanical and tensile behaviour of additive manufactured AISI 316L. Mater Charact2020; 167: 110463. Available at: https://www.sciencedirect.com/science/article/pii/S1044580320319343.
RajabiEMiresmaeiliRAliofkhazraeiM. The effect of surface mechanical attrition treatment (SMAT) on plastic deformation mechanisms and mechanical properties of austenitic stainless steel 316L. Mater Res Express2020; 6: 1250g8.
23.
OlugbadeTOOlutomilolaEOOlorunfemiBJ. Review of passivity and electrochemical properties of nanostructured stainless steels obtained by surface mechanical attrition treatment (SMAT): trend and progress. Corros Rev2022; 40: 189–203.
24.
MorganDJacobsR. Opportunities and challenges for machine learning in materials science. Annu Rev Mater Res2020; 50: 71–103.
25.
CusatoNNabavizadehSAEshraghiM. A review of large-scale simulations of microstructural evolution during alloy solidification. Metals (Basel)2023; 13: 1169.
26.
SamavatianMGholamipourRBokovDO, et al.Characterization of nanoscale structural heterogeneity in metallic glasses: a machine learning study. J Non-Cryst Solids2022; 578: 121344.
27.
LiuJZhangYZhangY, et al.Machine learning assisted prediction of mechanical properties of graphene/aluminium nanocomposite based on molecular dynamics simulation. Mater Des2022; 213: 110334.
28.
ShenYZhuS. Machine learning mechanical properties of defect-engineered hexagonal boron nitride. Comput Mater Sci2023; 220: 112030.
29.
JhaPShaikshavaliGShankarMG, et al.A hybrid ensemble learning model for evaluating the surface roughness of AZ91 alloy during the end milling operation. Surf Rev Lett2023: 2340001.
30.
NagendraJSrinathMKShaikshavaliG, et al.Evaluation of surface roughness of novel Al-based MMCs using Box-Cox transformation. Int J Interact Des Manuf2023: 1–14.
31.
YeXSuZDahariM, et al.Hybrid modeling of mechanical properties and hardness of aluminum alloy 5083 and C100 copper with various machine learning algorithms in friction stir welding. Structures2023; 55: 1250–1261.
32.
BhatNBarnardASBirbilisN. Improving the prediction of mechanical properties of aluminium alloy using data-driven class-based regression. Comput Mater Sci2023; 228: 112270.
33.
ZhangZQinRLiG, et al.Deep learning-based monitoring of surface residual stress and efficient sensing of AE for laser shock peening. J Mater Process Technol2022; 303: 117515.
34.
MalekiEUnalOSeyedi SahebariSM,et al.A novel approach for analyzing the effects of almen intensity on the residual stress and hardness of shot-peened (TiB+ TiC)/Ti–6Al–4V composite: deep learning. Materials (Basel)2023; 16: 4693.
35.
RalphBJHartlKSorgerM, et al.Machine learning driven prediction of residual stresses for the shot peening process using a finite element based grey-box model approach. J Manuf Mater Process2021; 5: 39.
36.
AlkurdiAAHAl-MohairHKRodriguesP, et al.Enhancing mechanical behavior assessment in porous thermal barrier coatings using a machine learning fine-tuned with genetic algorithm. J Therm Spray Technol2024; 33: 1–15.
37.
ShaoJWuGHeZ, et al.DEM-FEM coupling analysis of shots’ energy distribution and target’s residual stress of pneumatic shot peening. Mater Res Express2023; 10: 096505.
38.
ZhangYProustGRetraintD, et al.Discrete element simulation of surface mechanical attrition treatment with rough-surface sonotrode. Int J Mech Sci2019; 161: 105060.
GhasemiAHassani-GangarajSMMahmoudiAH, et al.Shot peening coverage effect on residual stress profile by FE random impact analysis. Surf Eng2016; 32: 861–870.
41.
AstaraeeAHMiresmaeiliRBagherifardS, et al.Incorporating the principles of shot peening for a better understanding of surface mechanical attrition treatment (SMAT) by simulations and experiments. Mater Des2017; 116: 365–373.
42.
YararEErturkATKarabayS. Dynamic finite element analysis on single impact plastic deformation behavior induced by SMAT process in 7075-T6 aluminum alloy. Met Mater Int2021; 27: 2600–2613.
43.
LehrenfeldCOlshanskiiMAXuX. A stabilized trace finite element method for partial differential equations on evolving surfaces. SIAM J Numer Anal2018; 56: 1643–1672.
44.
SamavatianVFotuhi-FiruzabadMSamavatianM, et al.Correlation-driven machine learning for accelerated reliability assessment of solder joints in electronics. Sci Rep2020; 10: 14821.
45.
WangAY-TMurdockRJKauweSK, et al.Machine learning for materials scientists: an introductory guide toward best practices. Chem Mater2020; 32: 4954–4965.
46.
DaiDXuTWeiX, et al.Using machine learning and feature engineering to characterize limited material datasets of high-entropy alloys. Comput Mater Sci2020; 175: 109618.
47.
VabalasAGowenEPoliakoffE,et al.Machine learning algorithm validation with a limited sample size. PLoS One2019; 14: e0224365.
48.
YuZYeSSunY, et al.Deep learning method for predicting the mechanical properties of aluminum alloys with small data sets. Mater Today Commun2021; 28: 102570.
LeCunYBoserBDenkerJS, et al.Backpropagation applied to handwritten zip code recognition. Neural Comput1989; 1: 541–551.
51.
KingmaDPBaJ. Adam: A method for stochastic optimization. arXiv Prepr arXiv14126980. 2014.
52.
FengSZhouHDongH. Using deep neural network with small dataset to predict material defects. Mater Des2019; 162: 300–310.
53.
XiaZMaKChengS, et al.Accurate identification and measurement of the precipitate area by two-stage deep neural networks in novel chromium-based alloys. Phys Chem Chem Phys2023; 25: 15970–15987.
54.
HassaninHZweiriYFinetL, et al.Laser powder bed fusion of Ti-6Al-2Sn-4Zr-6Mo alloy and properties prediction using deep learning approaches. Materials (Basel)2021; 14: 2056.
55.
WangXLiuH. Soft sensor based on stacked auto-encoder deep neural network for air preheater rotor deformation prediction. Adv Eng Informatics2018; 36: 112–119.
56.
LinYCYangHChenD-D,et al.Stacked auto-encoder network to predict tensile deformation behavior of a typical nickel-based superalloy considering Portevin–Le Chatelier effects. Met Mater Int2021; 27: 254–261.
57.
BajajKSinghDKAnsariMA. Autoencoders based deep learner for image denoising. Procedia Comput Sci2020; 171: 1535–1541.
58.
LiuBLiHOuJ, et al.Intelligent recognition of milling tool wear status based on variational auto-encoder and extreme learning machine. Int J Adv Manuf Technol2022: 1–15. doi:10.1007/s00170-021-07859-w.
59.
QiangNDongQLiangH, et al.Modeling and augmenting of fMRI data using deep recurrent variational auto-encoder. J Neural Eng2021; 18: 0460b6.
60.
PangG-DLinY-CQiuY-L, et al.Dislocation density-based model and stacked auto-encoder model for Ti-55511 alloy with basket-weave microstructures deformed in α + β region. Adv Eng Mater2021; 23: 2001307.
61.
OpělaPSchindlerIKawulokP, et al.Shallow and deep learning of an artificial neural network model describing a hot flow stress evolution: a comparative study. Mater Des2022; 220: 110880.
62.
ZhangLChenHTaoX, et al.Machine learning reveals the importance of the formation enthalpy and atom-size difference in forming phases of high entropy alloys. Mater Des2020; 193: 108835.
63.
LiuQLiNYonggaA, et al.The evaluation of the corrosion rates of alloys applied to the heating tower heat pump (HTHP) by machine learning. Energies2021; 14: 1972.
64.
WangNSamavatianMSamavatianV,et al.Bayesian machine learning-aided approach bridges between dynamic elasticity and compressive strength in the cement-based mortars. Mater Today Commun2023; 35: 106283. Available at: https://www.sciencedirect.com/science/article/pii/S2352492823009741.
65.
ProbstPWrightMNBoulesteixA. Hyperparameters and tuning strategies for random forest. Wiley Interdiscip Rev Data Min Knowl Discov2019; 9: e1301.
66.
ZhangYLingC. A strategy to apply machine learning to small datasets in materials science. npj Comput Mater2018; 4: 25.
67.
PietersmaDLacroixRLefebvreD,et al.Performance analysis for machine-learning experiments using small data sets. Comput Electron Agric2003; 38: 1–17.
68.
AcharyaSPanickerAGGopalV, et al.Surface mechanical attrition treatment of low modulus Ti-Nb-Ta-O alloy for orthopedic applications. Mater Sci Eng C2020; 110: 110729.
69.
BajdaSRatuszekWKrzyzanowskiM,et al.Inhomogeneity of plastic deformation in austenitic stainless steel after surface mechanical attrition treatment. Surf Coatings Technol2017; 329: 202–211.
70.
CaoSCZhangXLuJ, et al.Predicting surface deformation during mechanical attrition of metallic alloys. npj Comput Mater2019; 5: 36.
71.
YangXPanHZhangJ, et al.Progress in mechanical properties of gradient structured metallic materials induced by surface mechanical attrition treatment. Mater Trans2019; 60: 1543–1552.
72.
JoshiMDKumarVSinghI,et al.Tribological response of mechanical attrition treated surface of AISI 316L steel: the role of velocity of colliding balls. J Tribol2021; 143: 31701.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
