基于数据特征的模糊模型辨识与模糊控制器设计方法  

Fuzzy model identification and fuzzy controller design based on data characteristic

作　　者：朱文彪[1] 孙增圻[2] 

机构地区：[1]北京航天自动控制研究所宇航智能控制技术国防科技重点实验室,北京100854 [2]清华大学计算机科学与技术系,北京100084

出　　处：《东南大学学报（自然科学版）》2009年第S1期53-56,共4页Journal of Southeast University：Natural Science Edition

摘　　要：针对难于建立精确数学模型的复杂过程,提出了一种基于数据特征的模糊模型辨识方法.该方法首先按过程输出随输入变量变化的剧烈程度对输入变量论域进行划分,然后在此划分的基础上确定出模糊模型的规则总数和前件参数,最后由于要建立的模糊模型可以表示为一个前馈模糊神经网络,因此利用BP学习算法求得过程模糊模型的后件参数.基于所提出的模糊模型辨识方法进行了柔性连杆机器人模糊控制器设计,并进行了柔性连杆机器人模糊控制实验.实验表明,通过所提出的模糊模型辨识和模糊控制方法可以得到满意的控制性能.A fuzzy model identification method based on data characteristic is presented for complex processes which are difficult to be mathematically modeled.First,the domain of discourse of input variables is divided according to the changing degree of the process output while the input variables change.Then,the total number and the premise parameters of the fuzzy rules are determined based on the division.Finally,the fuzzy model can be expressed as a feedfoward fuzzy neural network,so the BP algorithm is applied to obtain the consequent parameters of the fuzzy rules.The fuzzy controller of a flexible link robot is designed based on the presented fuzzy model identification method,and the corresponding fuzzy control experiment is performed.The experimental results show that the satisfactory performance is achieved by using the presented fuzzy model identification and fuzzy control method.

关 键 词：复杂过程 模糊模型 辨识 模糊神经网络 模糊控制 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]