Predication of roll force and roll torque in hot strip rolling process using artificial neural networks and finite element method

Author

Abstract

This paper introduces an artificial neural network (ANN) application to a hot strip mill to improve the model’s prediction ability for rolling force and rolling torque, as a function of various process parameters. To obtain a data basis for training and validation of the neural network, numerous three dimensional finite element simulations were carried out for different sets of process variables. Experimental data were compared with the finite element predictions to verify the model accuracy. Thus the ABAQUS and MATLAB soft wares are used to simulate the finite element method and an artificial neural network, respectively. The back-propagation algorithm and Levenberg–Marquardt Training function were used in the artificial neural network. The input variables are selected to be, initial temperature of the strip, interface heat-transfer coefficient between strip and work roll, percentage of thickness reduction, initial thickness and rolling speed. The resulted ANN model is feasible for on-line control and rolling schedule optimization and can be easily and rapidly predicted the roll force and roll torque.

Keywords

Main Subjects

References

[1] Orowan E (1943) The calculation of roll pressure in hot and cold flat rolling. Proce Institu Mech Eng 150: 140-167.
[2] Sims RB (1954)  The calculation of roll force and torque in hot rolling mills. Proce Institu Mech Eng 168: 191-200.
[3] Ford H, Alexander JM (1964) Simplified hot rolling calculations. J Inst Metals (92): 397-404.
[4] Hwang SM, Joun M.S (1992) Analysis of hot-strip rolling by a penalty rigid-viscoplastic finite   element method. Int  J Mech  Sci (34): 971-984.
[5] Shangwu X, Rodrigues JMC, Martins PAF (1999)  Three-dimensional simulation of flat rolling through a combined finite element-boundary element approach. Finite Element Anal Des (32): 221-233.
[6] Kwak WJ, Kim YH, Park HD, Lee JH, Hwang SM (2000) FE-based on-line model for the prediction of roll force and roll power in hot strip rolling. ISIJ Int 40:1013-1018.
[7] Duan X, Sheppard T (2002) Three dimensional thermal mechanical coupled simulation during hot rolling of aluminum alloy 3003. Int J Mech  Sci 44: 2155-2172.
[8] Wang X, Peng Y, Xu L, Liu H (2010) A 3-D differential method for solving rolling force of PC hot strip mill. J Iron Steel Res 17: 36-39.
[9] Zhang J, Cui Z (2011) Continuous FEM simulation of multi-pass plate hot rolling suitable for plate shape analysis. J Cent South Univ Technol 18:16-22.
 [10] Dadgar Asl Y, Tajdari M, Moslemi Naeini H, Davoodi B, Azizi Tafti R, Panahizadeh V (2015) Prediction of Required Torque in Cold Roll Forming Process of Channel Section Using Artificial Neural Networks. Modares Mech Eng 15(7): 209-214. (In Persian)
[11] Moharrami R, Soleymani MR (2015) Process parameters selection of cold rolling process for obtaining of certain residual stresses distribution on cylindrical aluminum. Aero Mech J 11(2):1-11. (In Persian)
[12] Portmann NF, Lindhoff D, Sorgel G, Gramckow O (1995) Application of neural networks in rolling mill automation. Iron Steel Eng 72: 33-36.
[13] Chun MS, Biglou J, Lenard JG, Kim JG (1999)  Using neural networks to predict parameters in the hot working of aluminum alloys. J Mat Proc Tech 86: 245-251.
[14] Jeon EC, Kim SK (2000) A study on the texturing of work roll for temper rolling. J Korean Soc Mach Tool Eng 9:7–16.
[15] Yang YY, Linkens DA, Talamantes-Silva J, Howard IC (2003) Roll force and torque prediction using neural network and finite element modeling. ISIJ Int 43:1957-1966.
[16] Yang YY, Linkens DA, Talamantes-Silva J (2004) Roll load prediction-data collection, analysis and neural network modeling. J Mat Proc Tech 152:304-315.
[17] 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 Mat Proc Tech 209: 1920-1935.
[18] 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.
[19] Serajzadeh S, Karimi Taheri A, Nejati M, Izadi J, Fattahi M (2002) An investigation on strain in homogeneity in hot strip rolling process. J Mater Process Technol 128: 88-99.
[20] Fletcher JD, Beynon JH (1996) Heat transfer in roll gap in hot strip rolling, Ironmak Steel mak     23: 52-57.
[21] Rezaei Ashtiani HR, Bisadi H, Parsa MH(2011) In homogeneity of temperature distribution through thickness of the aluminum strip during hot rolling. Proce Institu Mech Eng Part C: J Mech Eng Sci  225: 2938-2952.
[22] Hum B, Colquhoun HW, Lenard JG (1996) Measurements of friction during hot rolling of aluminum strips. J Mat Proc Tech 60: 331-338.
[23] Deng J, Gu D, Li X, Yue ZQ (2005) Structural reliability analysis for implicit performance functions using artificial neural network, Struct Saf 27: 25-48.
Journal of Solid and Fluid Mechanics
Volume 6, Issue 3
September and October 2016
Pages 149-162

Files

Share

How to cite

Statistics