Derivation of fuzzy hybrid models for real-time fuzzy control design: Application to a furnace

The problem of identification of model parameters often arises when trying to work directly with nonlinear model representations. This problem also appears using fuzzy rule-based models. In this paper an alternative approach is presented. By combining the feasibility of linear, simple models and the flexibility of fuzzy logic a composite, nonlinear model is obtained. Such a hybrid model is both accurate enough and easy to adjust. This model is used for the control system design and debugging, leaving the real system trials for fine adjustment of the obtained controller.