Advertisement

Springer Nature is making Coronavirus research free. View research | View latest news | Sign up for updates

Neural networks for parameters prediction of an electromagnetic forming process of FeP04 steel sheets

  • 186 Accesses

  • 2 Citations

Abstract

An electromagnetic forming process of FeP04 steel sheets is studied over a wide range of variation of technological parameters aiming at finding optimal values providing maximum deformation of the part. The process parameters considered in this paper are deformed part diameter (d), thickness of specimen (t), distance coil–specimen (D), number of coil turns (N), capacitance of capacitor bank (C), and the charging voltage (V). Each specimen was freely deformed on a die of ring type through a unique combination of input parameters included in the study, and the maximum depth of the deformed parts center (h) was considered output parameter. Radial basis function neural networks are used for modeling the functional dependence between technological parameters and the resulting deformation of the material. Modeling results indicate an average mean square error around 4 % and a correlation between experimental data and neural model output exceeding 0.99. Sensitivity analysis reveals significant input parameters that decisively influence the output of the model. Simulation results are in good agreement with the experimental data, suggesting that neural networks can be considered a viable modeling alternative to existing approaches.

This is a preview of subscription content, log in to check access.

References

  1. 1.

    Oliveira DA, Worswick MJ, Finn M, Newman D (2005) Electromagnetic forming of aluminum alloy sheet: free-form and cavity fill experiments and model. J Mater Process Technol 170:350–362

  2. 2.

    Karimi A, Niayesh K, Bahmani MA (2010) Magnetic field enhancement in electromagnetic forming systems using anisotropic materials. Int J Mater Form 3:205–208

  3. 3.

    Andersson R, Syk M (2008) Electromagnetic pulse forming of carbon steel sheet metal. 3rd International Conference on High Speed Forming. Dortmund :233–244

  4. 4.

    Imbert J, Worswick M (2011) Electromagnetic reduction of a pre-formed radius on AA5754 sheet. J Mater Process Technol 211:896–908

  5. 5.

    Bagheripoor M, Bisadi H (2013) Application of artificial neural networks for the prediction of roll force and roll torque in hot strip rolling process. Appl Math Model 37:4593–4607

  6. 6.

    Chen J, Chandrashekhara K, Mahimkar C, Lekakh SN, Richards VL (2011) Void closure prediction in cold rolling using finite element analysis and neural network. J Mater Process Technol 211:245–255

  7. 7.

    Gudur PP, Dixit US (2008) A neural network-assisted finite element analysis of cold flat rolling. Eng Appl Artif Intel 21:43–52

  8. 8.

    Shahani AR, Setayeshi S, Nodamaie SA, Asadi MA, Rezaie S (2009) Prediction of influence parameters on the hot rolling process using finite element method and neural network. J Mater Process Technol 209:1920–1935

  9. 9.

    Hambli R (2009) Statistical damage analysis of extrusion processes using finite element method and neural networks simulation. Finite Elem Anal Des 45:640–649

  10. 10.

    Zhichao S, He Y, Ze T (2010) Microstructural evolution model of TA15 titanium alloy based on BP neural network method and application in isothermal deformation. Comput Mater Sci 50:308–318

  11. 11.

    Abbassi F, Belhadj T, Mistou S, Zghal A (2013) Parameter identification of a mechanical ductile damage using artificial neural networks in sheet metal forming. Mater Des 45:605–615

  12. 12.

    Jamli MR, Ariffin AK, Wahab DA (2014) Integration of feedforward neural network and finite element in the draw-bend springback prediction. Expert Syst Appl 41:3662–3670

  13. 13.

    Esmailzadeh M, Aghaie-Khafri M (2012) Finite element and artificial neural network analysis of ECAP. Comput Mater Sci 63:127–133

  14. 14.

    Hsiang S-H, Ho H-L (2004) Application of finite element method and artificial neural network to the die design of radial forging processes. Int J Adv Manuf Technol 24:700–707

  15. 15.

    Aguir H, BelHadjSalah H, Hambli R (2011) Parameter identification of an elasto-plastic behaviour using artificial neural networks-genetic algorithm method. Mater Des 32:48–53

  16. 16.

    Mousavi Anijdan SH, Madaah-Hosseini HR, Bahrami A (2007) Flow stress optimization for 304 stainless steel under cold and warm compression by artificial neural network and genetic algorithm. Mater Des 28:609–615

  17. 17.

    Mandal S, Sivaprasad PV, Venugopal S, Murthy KPN (2009) Artificial neural network modeling to evaluate and predict the deformation behavior of stainless steel type AISI 304L during hot torsion. Appl Soft Comput 9:237–244

  18. 18.

    Gupta AK, Singh SK, Reddy S, Hariharan G (2012) Prediction of flow stress in dynamic strain aging regime of austenitic stainless steel 316 using artificial neural network. Mater Des 35:589–595

  19. 19.

    Han Y, Zeng W, Zhao Y, Qi YL, Sun Y (2011) An ANFIS model for the prediction of flow stress of Ti600 alloy during hot deformation process. Comput Mater Sci 50:2273–2279

  20. 20.

    Ji G, Li F, Li Q, Li H, Li Z (2010) Prediction of the hot deformation behavior for Aermet100 steel using an artificial neural network. Comput Mater Sci 48:626–632

  21. 21.

    Ji G, Li F, Li Q, Li H, Li Z (2011) A comparative study on Arrhenius-type constitutive model and artificial neural network model to predict high-temperature deformation behaviour in Aermet100 steel. Mater Sci Eng A 528:4774–4782

  22. 22.

    Li H-Y, Wei D-D, Li Y-H, Wang X-F (2012) Application of artificial neural network and constitutive equations to describe the hot compressive behavior of 28CrMnMoV steel. Mater Des 35:557–562

  23. 23.

    Li H-Y, Hu J-D, Wei D-D, Wang X-F, Li Y-H (2012) Artificial neural network and constitutive equations to predict the hot deformation behavior of modified 2.25Cr-1Mo steel. Mater Des 42:192–197

  24. 24.

    Toros S, Ozturk F (2011) Flow curve prediction of Al-Mg alloys under warm forming conditions at various strain rates by ANN. Appl Soft Comput 11:1891–1898

  25. 25.

    Yassar RS, AbuOmar O, Hansen E, Horstemeyer MF (2010) On dislocation-based artificial neural network modeling of flow stress. Mater Des 31:3683–3689

  26. 26.

    Sabokpa O, Zarei-Hanzaki A, Abedi HR, Haghdadi N (2012) Artificial neural network modeling to predict the high temperature flow behavior of an AZ81 magnesium alloy. Mater Des 39:390–396

  27. 27.

    Yu H, Yu H-S, Kim Y-M, You B-S, Min G-H (2013) Hot deformation behavior and processing maps of Mg-Zn-Cu-Zr magnesium alloy. Trans Nonferrous Met Soc China 23:756–764

  28. 28.

    Peng W, Zeng W, Wang Q, Yu H (2013) Comparative study on constitutive relationship of as-cast Ti60 titanium alloy during hot deformation based on Arrhenius-type and artificial neural network models. Mater Des 51:95–104

  29. 29.

    Chen C, Yin H, Humail I-S, Wang Y, Qu X (2007) A comparative study of a back propagation artificial neural network and a Zerilli-Armstrong model for pure molybdenum during hot deformation. Int J Refract Met Hard Mater 25:411–416

  30. 30.

    Poshal G, Ganesan P (2008) An analysis of formability of aluminium preforms using neural network. J Mater Process Technol 205:272–282

  31. 31.

    Kim YH, Choi JC, Yoon JM, Park JH (2002) A study of the optimum reheating process for A356 alloy in semi-solid forging. Int J Adv Manuf Technol 20:277–283

  32. 32.

    Costanza G, Tata ME, Ucciardello N (2006) Superplasticity in PbSn60: experimental and neural network implementation. Comput Mater Sci 37:226–233

  33. 33.

    Datta S, Pettersson F, Ganguly S, Saxén H, Chakraborti N (2008) Identification of factors governing mechanical properties of TRIP-aided steel using genetic algorithms and neural networks. Mater Manuf Proc 23:130–137

  34. 34.

    Sinha A, Sikdar (Dey) S, Chattopadhyay PP, Datta S (2013) Optimization of mechanical property and shape recovery behavior of Ti-(_49 at.%) Ni alloy using artificial neural network and genetic algorithm. Mater Des 46:227–234

  35. 35.

    Kmet S, Sincak P, Stehlik P (2011) Artificial neural network for creep behaviour predictions of a parallel-lay aramid rope under varying stresses. Strain 47:121–128

  36. 36.

    Lin YC, Fang X, Wang YP (2008) Prediction of metadynamic softening in a multi-pass hot deformed low alloy steel using artificial neural network. J Mater Sci 43:5508–5515

  37. 37.

    Tanasa DE, Piuleac CG, Curteanu S, Popovici E (2013) Photodegradation process of Eosin Y using ZnO/SnO2 nanocomposites as photocatalysts: experimental study and neural network modeling. J Mater Sci 48:8029–8040

  38. 38.

    Piuleac CG, Rodrigo MA, Canizares P, Curteanu S, Saez C (2010) Ten steps modeling of electrolysis processes by using neural networks. Environ Model Soft 25:74–81

  39. 39.

    Man H, Prusty G (2011) Neural network modelling for damage behaviour of composites using full-field strain measurements. Compos Struct 93:383–391

  40. 40.

    Cavaliere P (2007) Flow curve prediction of an Al-MMC under hot working conditions using neural networks. Comput Mater Sci 38:722–726

  41. 41.

    Spliid H (2002) Design and analysis of experiments with k factors having p levels. Lecture notes, Technical University of Denmark, Lyngby, Denmark; 2002. http://www2.imm.dtu.dk/courses/02411/engnote.pdf

  42. 42.

    Luca D (2010) Statistical mathematical modelling of the manufacturing process of parts obtained by electromagnetic forming. Proceedings of the 21st International DAAAM Symposium. Vienna, 21:1437–1438

  43. 43.

    Broomhead DS, Lowe D (1988) Multivariable functional interpolation and adaptive networks. Comp Syst 2:321–355

  44. 44.

    Moody J, Darken CJ (1989) Fast learning in networks of locally-tuned processing units. Neural Comput 1:281–294

  45. 45.

    Gevrey M, Domopoulos I, Lek S (2003) Review and comparison of methods to study the contribution of variables in artificial neural network models. Ecol Model 160:249–264

  46. 46.

    Olden JD, Joy MK, Death RG (2004) An accurate comparison of methods for quantifying variable importance in artificial neural networks using simulated data. Ecol Model 178:389–397

  47. 47.

    Luca D (2012) A numerical modelling: opened perspectives to increase the performance of the electromagnetic forming processes. Int J Numer Model 25:15–23

Download references

Author information

Correspondence to Dorin Luca.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Luca, D. Neural networks for parameters prediction of an electromagnetic forming process of FeP04 steel sheets. Int J Adv Manuf Technol 80, 689–697 (2015). https://doi.org/10.1007/s00170-015-7006-5

Download citation

Keywords

  • Neural networks
  • Modeling
  • Optimization
  • Electromagnetic forming process
  • Steel sheet forming