Multiple Models Fuzzy Control: A Redistributed Fixed Models Based Approach
Nikolaos A. Sofianos, Yiannis S. Boutalis · Intelligent Automation & Soft Computing · 2014
A new fuzzy control architecture for unknown nonlinear systems in the framework of multiple models control is proposed in this paper. The architecture incorporates different kinds of identification models and controllers offering enhanced overall performance. More specifically, the fixed models which are widely used in multiple models control are becoming more flexible and they end up to be semi-fixed models. When semi-fixed models are combined with a free adaptive model and a reinitialized adaptive model, the result is very promising and offers many advantages in comparison with former control methods. All these models are represented by using the Takagi-Sugeno (T-S) method which is very useful for representing unknown or partially unknown nonlinear systems. The identification T-S models define the control signal at every time instant by updating their own state feedback fuzzy controllers and using the certainty equivalence approach. A performance index and an appropriate switching rule are used to deter...