Qualitative modeling of dynamical systems employing continuous-time recurrent fuzzy systems

Continuous-time recurrent fuzzy systems (CTRFS) allow the representation of knowledge-based dynamic processes that can be stated in the form of “if … , then … ” rules. In this article we show how a CTRFS can not only be modeled by linguistically given knowledge but also by measured data. Furthermore, a unified approach for both structure and parameter identification of continuous-time recurrent fuzzy systems will be presented, resulting in a linguistically interpretable model of the considered dynamic process. The capability of the approach is shown by modeling of a biotechnological process.