独立元回归在转炉终点温度预测中的应用

转炉终点温度是决定钢质量的关键因素,在炼钢的恶劣环境中难以检测.建立了基于ICR方法的终点温度的预测模型.该方法将独立元分析(ICA)与回归分析相结合,先利用ICA方法提取输入数据矩阵的独立元矩阵(IC);然后再分别以IC、实值矩阵为自变量和因变量进行训练,求取最小二乘回归(LSR)系数建立预测模型.工业生产数据仿真结果表明,与主元回归(PCR)和偏最小二乘回归(PLSR)方法相比,基于ICR的终点温度预测模型预测精度高,跟踪性能好.该方法可为实际生产中的终点控制提供参考,提高生产效益.

Application of Independent Component Regression in Converter Steel-Making Endpoint Temperature Prediction

Endpoint temperature is the key factor determining the quality of steel and one of the most difficult to control in the process of converter steel-making.A predicting model of endpoint temperature based on independent component regression (ICR) is established in converter steel-making.This method combines the independent component analysis (ICA) and regression analysis,which extracts the independent component matrix (IC) firstly,and then establishes the predicting model by the IC and real matrix.Data simulation results show that compared with the principal component regression (PCR) and partial least squares regression (PLSR),the ICR has a higher regression precision.It can provides reference for endpoint control in actual production to improve production efficiency.