Ali ÖZTÜRK, Rifat ŞEHERLİ

A hybrid model for the prediction of aluminum foil output thickness in cold rolling process

This study proposes a hybrid model composed of multiple prediction algorithms and an autoregressive movingaverage (ARMA) module for the thickness prediction. In order to attain higher accuracy, the prediction algorithms wereglobally combined by simple voting to reduce the effect of the inductive bias imposed by each algorithm on the dataset.The global multiexpert combination (GMEC) system included the multilayer perceptron neural network (MLPNN), radialbasis function network (RBFN), multiple linear regression (MLR), and support vector machines (SVM) algorithms. Theproposed hybrid model extends the GMEC system by integrating an ARMA module for the output. On the test dataset,the mean absolute error (MEA) and root mean squared error (RMSE) were better for the hybrid model than the GMECsystem. The GMEC system had approximately twice better performance than the MLPNN, which was the best amongthe learners. The performance was significantly improved via the hybrid model in terms of correlation coefficient (R).The results suggested that the proposed hybrid model can be used for more accurate and precise prediction of aluminumfoil output thickness.

PDF

___

[1] Sun M, Wang T, Zhang W. Research on cascade predictive control in hydraulic AGC of cold rolling mill. In: Proceedings of the 2nd IEEE Conference on Industrial Electronics and Applications; 23–25 May 2007; Harbin, China. New York, NY, USA: IEEE. pp. 2775-2780.
[2] Zarate LE. A predictive thickness control structure and decision about the better control parameter for the cold rolling process through sensitivity factors via neural networks. In: IEEE Mid-Summer Workshop on Soft Computing in Industrial Applications Conference; 28–30 June 2005; Espoo, Finland. New York, NY, USA: IEEE. pp. 17-23.
[3] Liang H, Tong C, Peng K. Data-driven modeling and online algorithm for hot rolling process. In: Proceedings of the 30th Chinese Control Conference; 22–24 July 2011; Yantai, China. New York, NY, USA: IEEE. pp. 1560-1564.
[4] Mei J, Wang H, Xiao J, Shan M. Study on sampling control in hydraulic AGC based on neural network. In: Proceedings of the 6th International Conference on Machine Learning and Cybernetics; 19–22 August 2007; Hong Kong, China. New York, NY, USA: IEEE. pp. 504-508.
[5] Marcellos NS, Denti JF, Saousa GC. Strip thickness estimation in rolling mills from electrical variables in AC drives. Latin American Applied Research 2009; 39: 353-359.
[6] Zheng G, Qu Q. Research on periodical fluctuations identification and compensation control method for export thickness in rolling mill. In: Proceedings of the 8th International Conference on Machine Learning and Cybernetics; 12–15 July 2009; Hebei, China. New York, NY, USA: IEEE. pp. 1972-1977.
[7] Öztürk A, Çınar K. Output thickness prediction of aluminium foil using artificial neural network in cold rolling process. In: ELECO; 27–29 November 2014; Bursa, Turkey. pp. 389-392.
[8] Wang L, Fan L, Lu N, Cui X, Xie Y. Rolling thickness prediction based on extreme learning and clustering. In: International Conference on Computer Science and Mechanical Automation; 23–25 October 2015; Hangzhou, China. New York, NY, USA: IEEE. pp. 30-35.
[9] Wei L, Xiaolan Y, Lei Y, Yue G. Application of SVM regression in HAGC system. In: 27th Chinese Control and Decision Conference; 23–25 May 2015; Qingdao, China. New York, NY, USA: IEEE. pp. 3490-3494.
[10] Varol T, Çanakçı A, Özşahin S, Erdemir F, Özkaya S. Artificial neural network-based prediction technique for coating thickness in Fe-Al coatings fabricated by mechanical milling. Particulate Science and Technology 2018; 36: 742-750.
[11] Öztürk A, Şeherli R. Short-term prediction of aluminium strip thickness via support vector machines. In: IEEE 23rd Signal Processing and Communications Applications Conference; 16–19 May 2015; Malatya, Turkey. New York, NY, USA: IEEE. pp. 208-211.
[12] Öztürk A, Şeherli R. Nonlinear short-term prediction of aluminum foil thickness via global regressor combination. Applied Artificial Intelligence 2017; 31: 568-592.
[13] Huang Q, Liang A. High-precision Rolling Technologies. Beijing, China: Metallurgy Industry Press, 2004.
[14] Beddoes J, Bibbly MJ. Principles of Metal Manufacturing Process. Burlington, MA, USA: Elsevier ButterworthHeinemann, 2003.
[15] Alpaydın E. Introduction to Machine Learning. 2nd ed. Cambridge, MA, USA: MIT Press, 2010.
[16] Hassoun MH. Fundamentals of Artificial Neural Networks. Cambridge, MA, USA: MIT Press, 1995.
[17] Ruppert D, Wand M. Multivariate locally weighted least squares regression. Annual Statistics 1994; 22: 1346–1370.
[18] Witten IH, Frank E. Data Mining: Practical Machine Learning Tools and Techniques with Java Implementations. San Diego, CA, USA: Academic Press, 2000.
[19] Mohandes MA, Halawani TO. Support vector machines for wind speed prediction. Renewable Energy 2004; 29: 939-947.
[20] Osowski S, Garanty K. Forecasting of daily meteorological pollution using wavelets and support vector machine. Engineering Applications of Artificial Intelligence 2007; 20: 745-755.
[21] Üstün B, Melssen WJ, Buydens LMC. Facilitating the application of support vector regression by using a universal Pearson VII function-based kernel. Chemometrics and Intelligent Laboratory Systems 2006; 81: 29-20.
[22] Radhika Y, Shashi M. Atmospheric temperature prediction using support vector machines. International Journal of Computer Theory and Engineering 2009; 1: 1793-8201.
[23] Halıcı U. Artificial Neural Networks – Lecture Notes. Ankara, Turkey: Middle East Technical University, 2004.
[24] Wiener N. Extrapolation, Interpolation, and Smoothing of Stationary Time Series. New York, NY, USA: Wiley, 1949.
[25] Box GEP, Jenkins GM, Reinsel GC. Time Series Analysis: Forecasting and Control. 3rd ed. Upper Saddle River, NJ, USA: Prentice Hall, 1994.
[26] Frank E, Hall MA, Witten IH. The WEKA Workbench Online Appendix for Data Mining: Practical Machine Learning Tools and Techniques. 4th ed. San Francisco, CA, USA: Morgan Kaufmann, 2016.