基于最小二乘支持向量机的结晶器液面预测控制

Predictive Control for Mold Level of Continuous Casting Based on Least Square Support Vector Machine

针对连铸过程的结晶器液面控制问题,提出了基于最小二乘支持向量机技术的预测模型的预测控制方法。利用最小二乘支持向量机对非线性过程建立预测模型,采用非线性预测控制方法进行控制。以结晶器液面控制过程为控制对象进行仿真,仿真结果表明,最小二乘支持向量机的建模方法可以有效地建立预测模型并且具有较好的泛化能力,基于这种预测模型的预测控制具有很好的控制性能。

A new predictive control method based on least square support vector machine is proposed in order to control mold level of the continuous casting. The dynamic characteristics of the continuous casting process are described. The simulation result shows that the modeling method is useful to model a nonlinear process and has the good generalized ability. Predictive control based on the predictive model shows satisfactory control performance.