A model for steel billet temperature of prediction of heating furnace

The estimate of main guide line of steel billet temperature is all along a puzzle in the industry due to the fact that heating furnace is a multivariable nonlinear system with large inertia, net lag and crossed coupling. This thesis proposes billet predictive model between billet temperature variable and heating process variable with improved ELM method. At last, based on actual data from steel industry, reckon model parameter. Analyzing check and error indicate that this model can forecast the temperature of entrance for billet steel before 10~25 minutes, and the error of prediction can satisfy the demand for industrial application.