Fuzzy clustering methods for identifying and modelling of non-linear control strategies

被引:9
作者
Akkizidis, IS [1 ]
Roberts, GN [1 ]
机构
[1] Univ Coll Wales, Mechatron Res Ctr, Newport NP20 5XR, Gwent, Wales
关键词
fuzzy clustering; modelling; identification; control strategies; non-linear systems; underwater vehicles;
D O I
10.1243/0959651011541229
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In this paper an algorithmic methodology for identifying and modelling non-linear control strategies is proposed. The methodology presented is based on choices of different fuzzy clustering algorithms, projection of clusters and merging techniques. The best features of well-known clustering methods such as the Gustafson-Kessel and mountain method are also combined. The latter is used to determine and define the number and the approximate positions of the cluster prototypes, whereas the former is used to define the shapes of the clusters according to the data distribution. The projection of the prototypes and variables of clusters is a recognized approach to extracting the information included in the data clusters into fuzzy sets. Merging these fuzzy sets. based on proposed guidelines. as described in this paper can minimize the number of rules and make the identifying control strategy more transparent. Some improvements to the resulting fuzzy system can be achieved by using optimization methods such as the gradient method. The proposed methodology is based on making the right choice of the right tools and can be described as a universal approximation in terms of identifying and modelling non-linear control strategies. The control strategy of an underwater vehicle for avoiding objects is identified using this methodology. Results are discussed as well as some conclusions about the proposed method.
引用
收藏
页码:437 / 452
页数:16
相关论文
共 22 条
[1]  
[Anonymous], 1998, Fuzzy Modelling for Control
[2]  
[Anonymous], 1998, Fuzzy control
[3]  
[Anonymous], Pattern Recognition With Fuzzy Objective Function Algorithms
[4]  
[Anonymous], 1966, J MATH ANAL APPL
[5]  
BEZDEK CJ, 1999, FUZZY MODELS ALGORIT
[6]   OPTIMAL FUZZY PARTITIONS - HEURISTIC FOR ESTIMATING PARAMETERS IN A MIXTURE OF NORMAL DISTRIBUTIONS [J].
BEZDEK, JC ;
DUNN, JC .
IEEE TRANSACTIONS ON COMPUTERS, 1975, 24 (08) :835-838
[7]  
Chi Z., 1996, Fuzzy Algorithms: With Applications to Image Processing and Pattern Recognition, V10
[8]  
Driankov D., 1993, INTRO FUZZY CONTROL
[9]  
DUNN JC, 1974, CYBERNETICS, V3, P35
[10]  
ESPINOSA J, 1999, SOFT COMPUTING SERIE, V7