Integrating method based on KICA and LSSVM for steel temperature prediction of heating furnace

The purpose of this paper is to develop an intelligent algorithm by integrating the Kernel Independent Component Analysis (KICA) and the Support Vector Machines (SVM) for forecasting the steel temperature. Characterized by nonlinearity, multivariable, coupling of the heating furnace, it is necessary to feature extraction. Thus, this study proposes the application of KICA to extract the hidden information of process before conducting LSSVM. An application study is carried out on the real production data acquired from a steel-making plant. Results demonstrate that the proposed method possesses superior accuracy when compared to conventional methods, including SVM, KICA-SVM and KICA-LSSVM.