Application of artificial neural networks for the prediction of roll force and roll torque in hot strip rolling process

被引:116
作者
Bagheripoor, Mahdi [1 ]
Bisadi, Hosein [1 ]
机构
[1] Iran Univ Sci & Technol, Dept Mech Engn, Tehran, Iran
关键词
Artificial neural network; Finite element simulation; Hot strip mill; Rolling force; Rolling torque; FINITE-ELEMENT-METHOD; CONSTITUTIVE MODEL; STEEL STRIP; MILL; DEFORMATION; SIMULATION; PARAMETERS; WORKING;
D O I
10.1016/j.apm.2012.09.070
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
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. The input variables are selected to be rolling speed, percentage of thickness reduction, initial temperature of the strip and friction coefficient in the contact area. A comprehensive analysis of the prediction errors of roll force and roll torque made by the ANN is presented. Model responses analysis is also conducted to enhance the understanding of the behavior of the NN model. The resulted ANN model is feasible for on-line control and rolling schedule optimization, and can be easily extended to cover different aluminum grades and strip sizes in a straight-forward way by generating the corresponding training data from a FE model. (C) 2012 Elsevier Inc. All rights reserved.
引用
收藏
页码:4593 / 4607
页数:15
相关论文
共 40 条
[31]  
SHANGWU X, 1999, FINITE ELEM ANAL DES, V32, P221, DOI DOI 10.1016/S0924-0136(99)00342-8
[32]  
Sims R.B., 1954, P I MECH ENG, V168, P191
[33]   A study on on-line learning neural network for prediction for rolling force in hot-rolling mill [J].
Son, JS ;
Lee, DM ;
Kim, IS ;
Choi, SG .
JOURNAL OF MATERIALS PROCESSING TECHNOLOGY, 2005, 164 :1612-1617
[34]   Calculation of thermal stress affecting strip flatness change during run-out table cooling in hot steel strip rolling [J].
Wang, Xiaodong ;
Yang, Quan ;
He, Anrui .
JOURNAL OF MATERIALS PROCESSING TECHNOLOGY, 2008, 207 (1-3) :130-146
[35]   A 3-D Differential method for solving rolling force of PC hot strip mill [J].
Wang X.-S. ;
Peng Y. ;
Xu L.-P. ;
Liu H.-M. .
Journal of Iron and Steel Research International, 2010, 17 (9) :36-39
[36]   30 YEARS OF ADAPTIVE NEURAL NETWORKS - PERCEPTRON, MADALINE, AND BACKPROPAGATION [J].
WIDROW, B ;
LEHR, MA .
PROCEEDINGS OF THE IEEE, 1990, 78 (09) :1415-1442
[37]   Roll load prediction - data collection, analysis and neural network modelling [J].
Yang, YY ;
Linkens, DA ;
Talamantes-Silva, J .
JOURNAL OF MATERIALS PROCESSING TECHNOLOGY, 2004, 152 (03) :304-315
[38]   Roll force and torque prediction using neural network and finite element modelling [J].
Yang, YY ;
Linkens, DA ;
Talamantes-Silva, J ;
Howard, IC .
ISIJ INTERNATIONAL, 2003, 43 (12) :1957-1966
[39]   Continuous FEM simulation of multi-pass plate hot rolling suitable for plate shape analysis [J].
Zhang Jin-ling ;
Cui Zhen-shan .
JOURNAL OF CENTRAL SOUTH UNIVERSITY OF TECHNOLOGY, 2011, 18 (01) :16-22
[40]   Constitutive equations for modelling flow softening due to dynamic recovery and heat generation during plastic deformation [J].
Zhou, M ;
Clode, MP .
MECHANICS OF MATERIALS, 1998, 27 (02) :63-76