论文部分内容阅读
高炉冶炼过程是一个大时滞、强非线性的系统,现有的高炉炉温预测模型不够准确,因此,建立了基于香农熵的广义相关系数时滞分析模型和基于样条变换的非线性偏最小二乘回归(ST-PLS)的反应炉温的参数预测模型,得出影响高炉炉温的主要参数的滞后时间,预测出能够综合反应高炉炉温的4个参数([Si],[S],铁还原速率及铁水温度)。试验证明,模型具有较高的预测精度,当相对误差分别为0.11和0.18时,模型预测[Si]的命中率分别为0.714 3和0.918 4,[S]的命中率分别为0.734 7和0.918 4,铁还原速率的命中率分别为0.612 2和0.816 3,铁水温度的命中率分别为1.000 0和1.000 0。
The blast furnace smelting process is a large time-delay and strong nonlinear system, and the existing blast furnace temperature prediction model is not accurate enough. Therefore, a generalized correlation coefficient time-delay analysis model based on Shannon entropy and a nonlinear model based on spline transformation (S-Si), [S] and [S], which can comprehensively reflect the temperature of the blast furnace, are predicted based on the parameter predictive model of the temperature of the reaction furnace based on the least squares regression (ST-PLS) ], Iron reduction rate and hot metal temperature). Experiments show that the model has high prediction accuracy. When the relative errors are 0.11 and 0.18 respectively, the model predicts the hit rates of [Si] are 0.714 3 and 0.918 4, respectively, and the hit rates of [S] are 0.734 7 and 0.918 4, respectively , The hit rates of iron reduction rate were 0.612 2 and 0.816 3 respectively, and the hits of hot metal temperature were 1.000 0 and 1.000 0 respectively.