LS-SVM Based Adaptive Inverse Control Scheme for Steam Valving Control

摘要：

In this paper, a Least Squares Support Vector Machines(SVM) based adaptive inverse control(AIC) scheme is presented for steam valving control. As a novel function approximation tool with quicker training speed and stronger generalization ability, LSSVM is used in the off line inverse model identification in steam valving control. Then inverse model identified by LS-SVM is acted as the feed-forward controller in the AIC scheme, at the same time, a PI controller is established to compensate control error as well as to serve as reference signal for online adjustment of the feedforward controller. Both the structure and learning algorithms of AIC are presented in detail. Simulation results showed the efficacy of the proposed controller.

作者: Xiaofang Yuan Yaonan Wang

作者单位: College of Electrical Information Engineering Hunan University Changsha, China 410082

会议类型: 国际会议

会议名称: Fourth International Conference on Impulsive and Hybrid Dynamical Systems(ICIHDS 2007)(第四届国际脉冲和混合动力系统学术会议)

会议地点: 南宁

会议语种:英文

在线出版日期: 2007-07-20（万方平台首次上网日期，不代表论文的发表时间）