Universität Karlsruhe
Fynesse: A hybrid architecture for selflearning control


[1]Martin Riedmiller, Martin Spott, Joachim Weisbrod, Fynesse: A hybrid architecture for selflearning control, I. Cloete, J. Zurada (Ed.), MIT Press, Feb 2000.


The chapter presents a novel controller design method that exploits principles of knowledge-based neurocomputing to realize a hybrid controller architecture that is able to autonomously learn to control a priori unknown nonlinear dynamical systems. It allows the user to interpret, examine and correct the acquired control strategy in every stage of learning. Based on five requirements that are essential for a widely applicable learning controller the hybrid control architecture Fynesse is derived: The control strategy is represented by a fuzzy relation that can be interpreted and contain a priori knowledge, whereas the more complex part of learning is solved by a neural network that is trained by dynamic programming methods. The advantages of both paradigms - learning capability of neural networks and interpretability of fuzzy systems - are preserved since the two modules are strictly separated. The application of the Fynesse controller to a chemical plant demonstrates the high quality of autonomously learned control. Furthermore it shows the benefits of the integration of a priori knowledge and the interpretation of the controller in terms of fuzzy rules.

[Erzeuge bibTeX Eintrag]


Dr. Martin Spott
Dr. Joachim Weisbrod
Dr. Martin Riedmiller