Application of finite element method and artificial neural networks to predict the rolling force in hot rolling of Mg alloy plates

��-/%*0* A computational model combining a finite element method (FEM) with an artificial neural network (ANN) was developed to predict the rolling force in the hot rolling of Mg alloy plates. FEM results were compared with experimental data to verify the accuracy of the finite element model. Numerous thermomechanical finite element simulations were carried out to obtain a database for training and validation of the network. The input variables were initial thickness, thickness reduction, initial temperature of the plate, friction coefficient in the contact area, and rolling speed. The optimal ANN model was obtained after repeated training and studying of the samples. The trained network gave satisfactory results when comparing the ANN predictions and FEM simulation results. A comprehensive validation of the prediction model is presented. The resulting ANN model was found to be suitable for online control and rolling schedule optimization in the hot rolling process of Mg alloy plate.

[1]  Mehmet Firat,et al.  Prediction of springback in wipe-bending process of sheet metal using neural network , 2009 .

[2]  Giuseppina Ambrogio,et al.  A hybrid finite element method–artificial neural network approach for predicting residual stresses and the optimal cutting conditions during hard turning of AISI 52100 bearing steel , 2008 .

[3]  A. Mazahery,et al.  FEM and ANN investigation of A356 composites reinforced with B4C particulates , 2012 .

[4]  R. H. Wagoner,et al.  Evolution of the deformation texture and yield locus shape in an AZ31 Mg alloy sheet under uniaxial loading , 2009 .

[5]  I. J. Freshwater.  Simplified theories of flat rollingI. The calculation of roll pressure, roll force and roll torque , 1996 .

[6]  S. Choi,et al.  Simulation of deformation twins and deformation texture in an AZ31 Mg alloy under uniaxial compression , 2007 .

[7]  S. Suwas,et al.  Effect of rolling temperature and reduction in thickness on microstructure and mechanical properties of ZM21 magnesium alloy and its subsequent annealing treatment , 2011 .

[8]  Mahdi Bagheripoor,et al.  Application of artificial neural networks for the prediction of roll force and roll torque in hot strip rolling process , 2013 .

[9]  D. J. Kim,et al.  Application of neural network and FEM for metal forming processes , 2000 .

[10]  Yasuo Yamada,et al.  Mechanical Properties and Blow Forming of Rolled AZ31 Mg Alloy Sheet , 2003 .

[11]  T. Konno,et al.  Effect of differential speed rolling on the anisotropy of mechanical properties and texture evolution of AZ31 Mg alloys , 2010 .

[12]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[13]  M. Aghaie-Khafri,et al.  Finite element and artificial neural network analysis of ECAP , 2012 .

[14]  Guangnan Chen,et al.  Analysis of asymmetrical cold rolling with varying coefficients of friction , 2002 .

[15]  Tetsuo Sakai,et al.  Novel ultra-high straining process for bulk materials—development of the accumulative roll-bonding (ARB) process , 1999 .

[16]  Feng-shan Du,et al.  Nonlinear finite element analysis of thin strip temper rolling process , 2009 .

[17]  Qing Liu,et al.  Effect of initial texture on dynamic recrystallization and deformation mechanisms in AZ31 Mg alloy extruded at 573K , 2013 .

[18]  Xiao-hui Cui,et al.  Springback prediction for incremental sheet forming based on FEM-PSONN technology , 2013 .

[19]  B. Mordike,et al.  Magnesium: Properties — applications — potential , 2001 .

[20]  Mohsen Ostad Shabani,et al.  The ANN application in FEM modeling of mechanical properties of Al–Si alloy , 2011 .

[21]  J. H. Lee,et al.  Effect of grain refinement of magnesium alloy AZ31 by severe plastic deformation on material characteristics , 2008 .

[22]  Saeed Setayeshi,et al.  Prediction of influence parameters on the hot rolling process using finite element method and neural network , 2009 .