| 摘要 |
PURPOSE:To accurately predict lowering of furnace heat without any delaying the prediction, by using ARMA model adopting predicting means having the max. accuracy in few kinds of predicting means always automatically to generalized means. CONSTITUTION:The furnace heat in the blast furnace is predicted by the predicting means having the highest prediction accuracy by providing two or more among the predicting means in the under-mentioned five kinds of variables as the variable introducing to MA term in the ARMA model and by comparing the predicted value gone back in time and molten metal temp. As the above- mentioned the variables, A: average value of solution loss quantity or N content in the top furnace gas component during the prescribed time, B: the max. value in the above C quantity or the min. value in the above N content, C: variable correcting the difference of iron tapping hole, D: jointly use of the above B and D variables, E variable related to the temp. difference of the inner wall measured in every the prescribed time interval, are used. By this method, the accurate lowering of the furnace heat without any delay can be predicted. |
