首页 | 官方网站   微博 | 高级检索  
     

多输入多输出非线性系统的最小二乘支持向量机广义逆控制
引用本文:刘国海,张懿,魏海峰,赵文祥.多输入多输出非线性系统的最小二乘支持向量机广义逆控制[J].控制理论与应用,2012,29(4):492-496.
作者姓名:刘国海  张懿  魏海峰  赵文祥
作者单位:1. 江苏大学电气信息工程学院,江苏镇江,212013
2. 江苏科技大学电子信息学院,江苏镇江,212003
基金项目:国家自然科学基金资助项目(60874014, 50907031, 51077066); 江苏省自然科学基金资助项目(BK2010327); 江苏省研究生创新计划资助项目(CX09B 201Z).
摘    要:针对神经网络逆控制存在的不足, 对一类模型未知且某些状态量较难测得的多输入多输出(MIMO)非线性系统, 在状态软测量函数存在的前提下, 提出一种最小二乘支持向量机(LSSVM)广义逆辨识控制策略. 通过广义逆将原被控系统转化为伪线性复合系统, 并可使其极点任意配置, 采用LSSVM代替神经网络拟合广义逆系统中的静态非线性映射. 将系统的状态量辨识与LSSVM逆模型辨识结合, 通过LSSVM训练拟合同时实现软测量功能. 最后以双电机变频调速系统为对象, 采用该控制策略进行仿真研究, 结果验证了本文算法的有效性.

关 键 词:非线性系统    广义逆    辨识    最小二乘支持向量机    双电机变频调速系统
收稿时间:1/5/2011 12:00:00 AM
修稿时间:7/5/2011 12:00:00 AM

Least squares support vector machines generalized inverse control for a class of multi-input and multi-output nonlinear systems
LIU Guo-hai,ZHANG Yi,WEI Hai-feng and ZHAO Wen-xiang.Least squares support vector machines generalized inverse control for a class of multi-input and multi-output nonlinear systems[J].Control Theory & Applications,2012,29(4):492-496.
Authors:LIU Guo-hai  ZHANG Yi  WEI Hai-feng and ZHAO Wen-xiang
Affiliation:School of Electrical and Information Engineering, Jiangsu University,School of Electrical and Information Engineering, Jiangsu University,School of Electrical and Information, Jiangsu University of Science and Technology,School of Electrical and Information Engineering, Jiangsu University
Abstract:Considering the deficiency of neural network inverse control method, for a class of multi-input and multioutput (MIMO) nonlinear systems with unknown model, when soft-sensing functions for immeasurable states are available, we propose a new identification and control strategy based on the generalized inverse control of least squares support vector machines (LSSVM). The generalized inverse converts the controlled nonlinear system into a pseudo linear system with expected pole placement. In place of the neural network, LSSVM is employed to fit the static nonlinear mapping of the generalized inverse system. The identification of state variables is combined with the identification of LSSVM inverse model. Meanwhile, the soft-sensing is implemented through LSSVM training and fitting. Simulation is performed on a two-motor variable-frequency speed-regulating system. Results show that the proposed control strategy is feasible and efficient.
Keywords:nonlinear systems  generalized inverse  identification  least squares support vector machines  two-motor variable-frequency speed-regulating system
本文献已被 CNKI 万方数据 等数据库收录!
点击此处可从《控制理论与应用》浏览原始摘要信息
点击此处可从《控制理论与应用》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司    京ICP备09084417号-23

京公网安备 11010802026262号