New time-efficient structure for observer-based adaptive fuzzy-neural controllers for nonaffine nonlinear systems

This paper proposes an observer-based adaptive controller with a merged fuzzy-neural network for nonaffine nonlinear systems under the constraint that only the system output is available for measurement. Using a conventional fuzzy-neural network leads to rule explosion which leads to huge computation time. Our proposed merged-FNN does not have this problem, and can take the place of the conventional fuzzy-neural networks under some assumptions while maintaining the property of stability. Moreover, the adaptive scheme using the merged-FNN guarantees that all signals involved are bounded and the output of the closed-loop system asymptotically tracks the desired output trajectory. Finally, this paper gives examples of the proposed controller for nonaffine nonlinear systems, and is shown to provide good effectiveness.