基于SVM的PVC汽提过程预测控制方法

Predictive Control Method of PVC Stripper Process Based on SVM

  • 摘要: 针对汽提塔温度控制系统的非线性和参数时变的特性,采用支持向量机对汽提塔温度进行建模,结合非线性模型的实时线性化和广义预测控制隐式算法,提出了基于支持向量预测模型的广义预测控制算法.同时将该算法应用到聚氯乙烯汽提生产过程当中,并将模型在线校正和误差反馈校正相结合,根据实际情况进行了多种情况下的仿真,仿真结果表明了方法的有效性.

     

    Abstract: According to the nonlinear characteristics and time-varying parameters of the stripper temperature control system,support vector machine(SVM) is used to set up a stripper temperature model.Generalized predictive control(GPC) based on SVM predictive model combining the real-time linearization of nonlinear model with the GPC implicit algorithm is proposed.Meantime,the algorithm is applied to the producing process of polyvinyl chloride(PVC) stripper,and the model online regulation is combined with the error feedback regulation.The simulations are made in several circumstances,and the simulation results show the effectiveness of the method.

     

/

返回文章
返回