Support vector machine based predictive functional control design for output temperature of coking furnace
- 作者：Ridong Zhang ; Shuqing Wang
- 关键词：Support vector machine ; Predictive functional control ; Nonlinear process ; Industrial coking equipment
- 刊名：Journal of Process Control
- 出版年：2008
- 期刊代码：106_09591524
- 类别：et
- 出版时间：June 2008
- 卷：18
- 期：5
- 页码：439-448
- 文件大小：633 K
摘要
A new support vector machine based nonlinear predictive functional control design method has been developed and applied to an industrial coking furnace, which leads to the improvement of regulatory capacity for both reference input tracking and load disturbance rejection compared with traditional PFC and PID control strategies. The nonlinear process is first treated into a linear part plus a nonlinear part, then a convergent overall linear predictive functional control law is designed. The method gives a direct and effective multi-step predicting method and uses linear methods to get the control law which avoids the complicated nonlinear optimization. Comparison results and application to the temperature control of the industrial heavy oil coking furnace are presented in the article showing the efficiency of the method.