Neuro-fuzzy techniques under MATLAB/SIMULINK applied to a real plant
Andreas Nürnberger, Rudolf Kruse · 2002
The design and optimization process of fuzzy controllers can be supported by learning techniques derived from neural networks. Such approaches are usually called neuro-fuzzy systems. In this paper, we describe the application of an updated version of the neuro-fuzzy model NEFCON to a real plant. The NEFCON model is able to learn and optimize the rule-base of a Mamdani-type fuzzy controller online by a reinforcement learning algorithm that uses a fuzzy error measure. An implementation of this model under MATLAB/SIMULINK is presented. This simulation environment supports the development of real time applications.