Prediction of Rolling Force Based on a Fusion of Extreme Learning Machine and Self Learning Model of Rolling Force
Aiming at the rolling force model of hot strip rolling mill, the forecasting technique based on ELM (extreme learning machine) is presented in this paper. Initially, the variables associated with control rolling are identified by the analysis of the traditional formula of rolling force, in order to ensure the effectiveness of the model, and then apply ELM network to predict models. Production data is applied to train and test the above network, and compare with the modified calculated value of rolling force, which got from the self-learning model of rolling force. The results show that the thickness can be predicted more rapidly and exactly, which can meet the actual demand of production, when this model and the rolling force learning model are integrated.
KeywordsELM Rolling force model Self learning
- 1.Sun, Y.K.: Model of Control Hot Strip Mill, pp. 124–163. Metallurgical Industry Press, Beijng (2002)Google Scholar
- 2.Huang, G.B., Zhu, Q.Y., Siew, C.K.: Extreme learning machine: theory and applications. Neuro-Computing 70, 489–501 (2006)Google Scholar
- 3.Huang, G.B., Zhu, Q.Y., Siew, C.K.: Extreme learning machine: a new learning scheme of feed-forward neural networks. In: Proceedings of International Joint Conference on Neural Networks (IJCNN 2004), pp. 985–990 (2004)Google Scholar
- 4.Lonen, J., Kamarainen, J.-K., Lampinen, J.: Differential evolution training algorithm for feed- forward neural networks. Neural Process. Lett. 7(1), 93–105 (2003)Google Scholar
- 9.Gaemperle, R., Mueller, S.D., Koumoutsakos, P.: A parameter study for differential evolution. In: Grmela, A., Mastorakis, N.E. (eds.) Advances in Intelligent Systems, Fuzzy Systems, Evolutionary Computation, pp. 293–298. WSEAS Press (2002)Google Scholar