摘要
针对复杂非线性动态系统的模糊建模问题,提出了一种基于在线聚类的模糊建模方法。该方法首先采用在线聚类算法辨识T-S模型的前提参数,然后采用递推最小二乘算法辨识结论参数。根据系统过程中新的数据信息,模糊规则可以自动增加、修改和删除,实现了模型结构和参数的在线辨识和更新。最后将提出的方法应用于Box-Jenkin煤气炉建模和二自由度机器人建模两个例子。仿真结果表明,基于该方法辨识的T-S模糊模型具有很高的精度,而且模型结构简单、建模速度快,便于工程应用。
In view of modeling problems of nonlinear dynamic systems, a fuzzy modeling approach based on online fuzzy-clustering algorithm is presented. The structure and consequent parmeters are identified by the online clustering algorithm and recursive least square respectively. The rules can be added, modified and deleted with the new data information automatically. The online identification and update of model structure and parameters is obtained update rapidly and accurately. The simulation results of Box-Jenkin gas furnace and two-DOF robotic show the effectiveness and advantages of this approach.
出处
《控制工程》
CSCD
2007年第4期376-379,共4页
Control Engineering of China
关键词
在线聚类
模糊建模
递推最小二乘
机器人
online clustering
fuzzy modeling
recursive least square
robot
