铜转炉吹炼过程剩余热组合预测模型及应用

提出了一种吹炼剩余热组合预测模型,以便能根据剩余热准确确定冷料的加入量,提高冷料的使用率;首先,基于吹炼的化学反应过程得到的剩余热计算公式,采用递推最小二乘法,修正剩余热计算公式,建立热量衡算模型;然后,利用递推最小二乘法,修正剩余热计算经验公式;最后采用组合预测算法综合集成两种模型作为剩余热计算的预测模型;实际应用结果表明:利用集成方法建立的预测模型的相对误差控制在10%的波动范围内,具有较高的预测精度.

Combinatorial Forecasting Model of Residual Heat to Copper Matte Converting Process and Its Application

A combinatorial forecasting model of residual heat is presented in order to ensure the additive quantity and improve efficiency of scraps based on the residual heat. Firstly, the method establishes a heat balance model through modifying the parameter of academic reac- tion heat balance expressions using the recursive least square method. Secondly, the method modifies the parameter of traditional experiential expressions using the recursive least square method. Finally, two results are combined by using optimal combination algorithm as general modeling results of the residual heat. Through the analysis of the industrial site modeling experiment, the results show that the relative error of the forecasting model using integrated modeling is between -10% and 10% and the combinatorial forecasting model has higher forecast precision.