IJE TRANSACTIONS B: Applications Vol. 31, No. 2 (February 2018) 343-354    Article in Press

PDF URL: http://www.ije.ir/Vol31/No2/B/19.pdf  
downloaded Downloaded: 0   viewed Viewed: 102

E. Maleki and G. H. Farrahi
( Received: June 10, 2017 – Accepted: September 08, 2017 )

Abstract    Shot peening (SP), as one of the severe plastic deformation (SPD) methods is employed for surface modification of the engineering components by improving the metallurgical and mechanical properties. Furthermore artificial neural network (ANN) has been widely used in different science and engineering problems for predicting and optimizing in the last decade. In the present study, effects of conventional shot peening (CSP) and severe shot peening (SSP) on properties of AISI 1060 high carbon steel were modelled and compared via ANN. In order to networks training, the back propagation (BP) error algorithm is developed and data of experimental test results are employed. Experimental data illustrates that SSP has superior influence than CSP to improve the properties. Different networks with different structures are trained with try and error process and the one which had the best performance is selected for modeling. Testing of the ANN is carried out using experimental data which they were not used during networks training. Distance from the surface (depth), SP intensity and coverage are regarded as inputs and microhardness, residual stress and grain size are gathered as outputs of the networks. Comparison of predicted and experimental values indicates that the networks are tuned finely and adjusted carefully; therefore, they have good agreement.


Keywords    artificial neural network, severe shot peening, residual stress, coverage, Almen intensity


چکیده    فرایند ساچمه زنی به عنوان یکی از روشهای تغییر شکل دائمی شدید، در بسیاری از قطعات مهندسی به منظور ارتقا خواص مکانیکی و متالورژیکی سطوح استفاده می شود. از طرفی دیگر، در دهه گذشته شبکه های عصبی مصنوعی به میزان قابل توجهی برای پیش بینی و بهینه سازی در مسائل مختلف علوم و مهندسی مورد استفاده قرار گرفته اند. در این مقاله اثرات ساچمه زنی های معمولی و شدید بر روی خواص فولاد پرکربن AISI 1060 با استفاده از شبکه عصبی مصنوعی مدلسازی شده و مورد مقایسه قرار گرفته. برای آموزش شبکه الگوریتم خطای انتشار بازگشتی به همراه داده های تجربی-آزمایشگاهی به دست امده استفاده شده اند. نتایج آزمایشگاهی نشان می دهند که ساچمه زنی شدید اثراتی به مراتب بیشتر و بهتر نسبت به ساچمه زنی معمولی داشته. شبکه های گوناگونی با استفاده از آزمون و خطا برای یافتن ساختار بهینه ی شبکه آموزش داده شدند و ارزیابی شبکه توسط داده هایی که در فرآیند اموزش مورد استفاده قرار نگرفته بودند صورت گرفت. عمق، میزان شدت و میزان پوشش دهی به عنوان ورودی و سختی، تنش پسماند و اندازه دانه ها به عنوان خروجی شبکه در نظر گرفته شدند. مقایسه نتایج پیش بینی شده و نتیایج ازمایشگاهی تطابق قابل ملاحظه و قابل قبولی را در فرایند مدلسازی نشان می دهند.

References      [1]  S. M. H. Gangaraj, G. H. Farrahi, Side effects of shot peening on fatigue crack initiation life, International Journal of Engineering 24 (2011) 275-280. [2]  E. Maleki, A. Zabihollah, Modeling of shot-peening effects on the surface properties of a (TiB + TiC)/Ti–6Al–4V composite employing artificial neural networks, Materiali in tehnologije 50 (2016) 6, 851–860. [3]  Y.-S. Nam, U. Jeon, H.-K. Yoon, B.-C. Shin, J.-H. Byun, International Journal of Advanced Manufacturing Technology 87 (2016) 2967-2081. [4]  G. H. Farrahi, J. L. Lebrun, D. Courtain, Effect of shot peening on residual stress and fatigue life of a spring steel, Fatigue Frac. Eng. Mat. Struct. 18 (1995) 211-220.[5]  S. Bagherifard, M. Guagliano, Fatigue behavior of a low-alloy steel with nanostructured surface obtained by severe shot peening, Eng. Frac. Mech. 81 (2012) 56-68. [6]  S. Bagherifard, I. Fernandez-Pariente, R. Ghelichi, M. Guagliano, Effect of severe shot peening on microstructure and fatigue strength of cast iron, Int. J. Fatigue 65 (2013) 64-70. [7]  S. Bagherifard, S. Slawik, I. Fernández-Pariente, C. Pauly, F.Mücklich and M. Guagliano, Nanoscale surfacemodificationof AISI 316L stainless steel by severe shot peening, Mater. Des.102 (2016) 68–77. [8]  O. Unal, R. Varol, Almen intensity effect on microstructure and mechanical properties of low carbon steel subjected to severe shot peening, Appl. Surf. Sci. 290 (2014) 40–47. [9]  O. Unal, R. Varol, Surface severe plastic deformation of AISI 304 via conventional shot peening, severe shot peening and repeening, Appl. Surf. Sci. 351 (2015) 289-295. [10]                    S.M. Hassani-Gangaraj, A. Moridi, M. Guagliano, A. Ghidini, M. Boniardi, effect of nitriding, severe shot peening and their combination on the fatigue behavior and micro-structure of a low-alloy steel, Int. J. Fatigue 62 (2014) 67–76. [11]                    A.J Skinner and J Q Broughton, Neural networks in computational materials science: training algorithms, Modelling Simul. Mater. Sci. Eng. 3 (1995) 371- 390. [12]                   X. Xiao, G.Q. Liu, B.F. Hu, X. Zheng, L.N. Wang, S.J. Chen, A. Ullah, A comparative study on Arrhenius-type constitutive equations and artificial neural network model to predict high-temperature deformation behavior in 12Cr3WV steel, Computational Materials Science 62 (2012) 227–234 13]                   S. E. Restrepo, S. T. Giraldo, B. J. Thijsse, Using artificial neural networks to predict grain boundary energies, Computational Materials Science 86 (2014) 170–173 [14]                   G. Sidhu, S.D. Bhole, D.L. Chen, E. Essadiqi, Determination of volume fraction of bainite in low carbon steels using artificial neural networks, Computational Materials Science 50 (2011) 3377–3384 [15]                   Y. Han, G. Qiao, J. Sun, D. Zou, A comparative study on constitutive relationship of as-cast 904L austenitic stainless steel during hot deformation based on Arrhenius-type and artificial neural network models, Computational Materials Science 67 (2013) 93–103 [16]                   H. Akbarpour, M. Mohajeri, M. Moradi, Investigation on the synthesis conditions at the interpore distance of nanoporous anodic aluminum oxide: A comparison of experimental study, artificial neural network, and multiple linear regressions, Computational Materials Science 79 (2013) 75–81 [17]                   J. F. Velez and G. W. Powell, Some metallographic observations on the spalling of aisi 1060 steel by the formation of adiabatic shear bands, Wear 66 (1981) 367 – 378. [18]                   H. Roy, N. Parida, S. Sivaprasad, S. Tarafder, K.K. Ray, Acoustic emissions during fracture toughness tests of steels exhibiting varying ductility, Mater. Sci. Eng.A 486 (2008) 562–571. [19]                   SAE J443 procedures for using standard shot peening Almen test strip. [20]                   Y. Sun, W. Zeng, Y. Han, X. Ma, Y. Zhao, P. Guo, G. Wang, M. S. Dargusch, Determination of the influence of processing parameters on the mechanical properties of the Ti–6Al–4V alloy using an artificial neural network, Computational Materials Science 60 (2012) 239–244 [21]                   E. Maleki, N. Maleki, artificial neural network modeling of pt/c cathode degradation in PEM fuel cell, Journal of Electronic Materials 45 (2016) 3822–3834. 22]                   M. Jahanshahi, E. Maleki and A. Ghiami, On the efficiency of artificial neural networks for plastic analysis of planar frames in comparison with genetic algorithms and ant colony systems, Neural Computing and Applications (2016) in press. doi: 10.1007/s00521-016-2228-5 [23]                   J. Zhao, H. Ding, W. Zhao, M. Huang, D. Wei, Z. Jiang, Modelling of the hot deformation behaviour of a titanium alloy using constitutive equations and artificial neural network, Computational Materials Science 92 (2014) 47–56 [24]                   M. Esmailzadeh, M. Aghaie-Khafri, Finite element and artificial neural network analysis of ECAP, Computational Materials Science 63 (2012) 127–133 [25]                   K. Benyelloul, H. Aourag, Elastic constants of austenitic stainless steel: Investigation by the first-principles calculations and the artificial neural network approach, Computational Materials Science 67 (2013) 353–358 [26]                   N. Artrith, A. Urban, An implementation of artificial neural-network potentials for atomistic materials simulations: Performance for TiO2, Computational Materials Science 114 (2016) 135–150 [27]                   M. Abendroth, M. Kuna, Determination of deformation and failure properties of ductile materials by means of the small punch test and neural networks, Computational Materials Science 28 (2003) 633–644 [28]                   N. Castin, J.R. Fernández, R.C. Pasianot, Predicting vacancy migration energies in lattice-free environments using artificial neural networks, Computational Materials Science 84 (2014) 217–225 [29]                   K. Elangovan, C. S. Narayanan, R. Narayanasamy, Modelling of forming limit diagram of perforated commercial pure aluminium sheets using artificial neural network, Computational Materials Science 47 (2010) 1072–1078 [30]                   E. Maleki, Artificial neural networks application for modeling of friction stir welding effects on mechanical properties of 7075-T6 aluminum alloy, IOP Conference Series: Materials Science and Engineering 103 (2015) 012034. doi:10.1088/1757-899X/103/1/012034 [31]                   E. Maleki, G.H. Farrahi, K. Sherafatnia, , Application of Artificial Neural Network to Predict the Effects of Severe Shot Peening on Properties of Low Carbon Steel, in: A. Öchsner and H. Altenbach (Eds.), Machining, Joining and Modifications of Advanced Materials, Springer, Singapore, 2016, pp. 45-60 [32]                   H. Saitoh, T. Ochi and M. Kubota, Formation of surface nanocrystalline structure in steels by air blast shot peening, In: Proceedings of the 10th international conference on shot peening, Japan, 2008. pp. 488–93. [33]                   Y.M. Wang and E. Ma, Three strategies to achieve uniform tensile deformation in a nanostructured metal, Acta Mater. 52 (2004) 1699–1709 

Download PDF 

International Journal of Engineering
E-mail: office@ije.ir
Web Site: http://www.ije.ir