Modelling hot rolling manufacturing process using soft computing techniques

Steel making industry is becoming more competitive due to the high demand. In order to protect the market share, automation of the manufacturing industrial process is vital and represents a challenge. Empirical mathematical modelling of the process was used to design mill equipment, ensure productivity and service quality. This modelling approach shows many problems associated to complexity and time consumption. Evolutionary computing techniques show significant modelling capabilities on handling complex non-linear systems modelling. In this research, symbolic regression modelling via genetic programming is used to develop relatively simple mathematical models for the hot rolling industrial non-linear process. Three models are proposed for the rolling force, torque and slab temperature. A set of simple mathematical functions which represents the dynamical relationship between the input and output of these models shall be presented. Moreover, the performance of the symbolic regression models is compared to the known empirical models for the hot rolling system. A comparison with experimental data collected from the Ere[gtilde]li Iron and Steel Factory in Turkey is conducted for the verification of the promising model performance. Genetic programming shows better performance results compared to other soft computing approaches, such as neural networks and fuzzy logic.

[1]  Peter Cowling,et al.  A flexible decision support system for steel hot rolling mill scheduling , 2003, Comput. Ind. Eng..

[2]  Yong Hwan Kim,et al.  FE-based On-line Model for the Prediction of Roll Force and Roll Power in Hot Strip Rolling , 2000 .

[3]  Luis E. Zárate,et al.  Qualitative behavior rules for the cold rolling process extracted from trained ANN via the FCANN method , 2009, Eng. Appl. Artif. Intell..

[4]  L. Cser,et al.  Different Kinds of Neural Networks in Control and Monitoring of Hot Rolling Mill , 2001, IEA/AIE.

[5]  Henry Leung,et al.  Data-driven based model for flow prediction of steam system in steel industry , 2012, Inf. Sci..

[6]  Hazim El-Mounayri,et al.  A generic and innovative approach for integrated simulation and optimisation of end milling using solid modelling and neural network , 2010, Int. J. Comput. Integr. Manuf..

[7]  Zhou Wan,et al.  On-line Modeling Method of Rolling Mill Based Least-squares Regression Analysis , 2009 .

[8]  Can Özsoy,et al.  Comparison of empirical and neural network hot-rolling process models , 2009 .

[9]  Surjya K. Pal,et al.  Pseudo-bond graph modelling of temperature distribution in a through-process steel rolling , 2008, Math. Comput. Simul..

[10]  Zhijun Rong,et al.  A BP Neural Network Predictor Model for Desulfurizing Molten Iron , 2005, ADMA.

[11]  T. M. Maccagno,et al.  Mathematical Modelling of Mean Flow Stress during the Hot Strip Rolling of Multiply-alloyed Medium Carbon Steels , 1998 .

[12]  Pranab K. Dan,et al.  Fuzzy ART K-Means Clustering Technique: a hybrid neural network approach to cellularmanufacturing systems , 2011, Int. J. Comput. Integr. Manuf..

[13]  Cai Liu,et al.  Numerical Simulation during Expansion for Hot Rolling Sheet Strip , 2008, First International Workshop on Knowledge Discovery and Data Mining (WKDD 2008).

[14]  A. F. Crawley,et al.  Optimum Scheduling of a Hot Rolling Process by Nonlinear Programming , 1992 .

[15]  Alaa F. Sheta,et al.  Modeling of Hot Rolling Industrial Process Using Fuzzy Logic , 2009, CAINE.

[16]  Mohammad Hossein Fazel Zarandi,et al.  Fuzzy agent-based expert system for steel making process , 2009, Expert Syst. Appl..

[17]  K. Chau,et al.  Neural network and genetic programming for modelling coastal algal blooms , 2006 .

[18]  Inci Batmaz,et al.  A review of data mining applications for quality improvement in manufacturing industry , 2011, Expert Syst. Appl..

[19]  Alberto Cavazos,et al.  Neural, fuzzy and Grey-Box modelling for entry temperature prediction in a hot strip mill , 2012, Expert Syst. Appl..

[20]  T Çakar,et al.  Artificial neural networks for design of manufacturing systems and selection of priority rules , 2004, Int. J. Comput. Integr. Manuf..

[21]  Arthur K. Kordon,et al.  Industrial Strength Genetic Programming , 2003 .

[22]  Farrokh Janabi-Sharifi,et al.  Fuzzy looperless tension control for hot strip rolling , 2009, Fuzzy Sets Syst..

[23]  Sameer Kumar,et al.  A systems approach in examining optimization opportunities and dynamics of the global steel industry , 2008, Inf. Knowl. Syst. Manag..

[24]  Stephan M. Winkler,et al.  Genetic Algorithms and Genetic Programming - Modern Concepts and Practical Applications , 2009 .

[25]  Salah Bouhouche,et al.  Soft sensor - based artificial neural networks and fuzzy logic: application to quality monitoring in hot rolling , 2008 .

[26]  W. Y. Choo,et al.  Application of linear regression analysis in accuracy assessment of rolling force calculations , 1998 .

[27]  Antonio Augusto Gorni,et al.  APPLICATION OF NEURAL NETWORKS IN THE MODELING OF PLATE ROLLING PROCESSES , 1997 .

[28]  Dukman Lee,et al.  Application of neural-network for improving accuracy of roll-force model in hot-rolling mill , 2000 .

[29]  Diego Andina,et al.  Application of Neural Networks , 2007 .