Title :
A novel cluster validity criterion for the bilinear models and its application to the T-S fuzzy bilinear model identification
Author :
Ku, Hong-Chi ; Kung, Chung-Chun ; Chen, Wei-Yin
Author_Institution :
Dept. of Electr. Eng., Tatung Univ., Taipei, Taiwan
Abstract :
The objective of this paper is to use the T-S fuzzy bilinear model to describe nonlinear system with high accuracy and with as fewer IF-THEN rules as possible via input/output data which collect from original nonlinear system and fuzzy c-regression models (FCRM) clustering algorithm applied to bilinear models. A novel cluster validity criterion suitable for the bilinear models will be presented. The simulation example is provided to demonstrate the accuracy of the fuzzy bilinear model.
Keywords :
fuzzy set theory; identification; nonlinear control systems; pattern clustering; regression analysis; IF-THEN rules; T-S fuzzy bilinear model identification; bilinear models; fuzzy c-regression models clustering algorithm; input/output data; nonlinear system; novel cluster validity criterion; Autoregressive processes; Clustering algorithms; Data models; Mathematical model; Nonlinear systems; Partitioning algorithms; Vectors; T-S fuzzy bilinear model; cluster validity criterion; fuzzy c-regression models (FCRM);
Conference_Titel :
Fuzzy Systems (FUZZ-IEEE), 2012 IEEE International Conference on
Conference_Location :
Brisbane, QLD
Print_ISBN :
978-1-4673-1507-4
Electronic_ISBN :
1098-7584
DOI :
10.1109/FUZZ-IEEE.2012.6250841
