A novel online hybrid direct/indirect adaptive Petri fuzzy neural network (PFNN) controller with stare observer for a class of multi-input multi-output (MIMO) uncertain nonlinear systems is developed in the paper. By using the Lyapunov synthesis approach, the online observer-based tracking control law and the weight-update law of the adaptive hybrid intelligent controller are derived. According to the importance and viability of plant knowledge and control knowledge, a weighting factor is utilized to sum together the direct and indirect adaptive PFNN controllers. In this paper, we prove that the proposed online observer-based hybrid PFNN controller can guarantee that all signals involved are bounded and that the system outputs of the closed-loop system can track asymptotically the desired output trajectories. An example including four cases is illustrated to show the effectiveness of this approach.
Proceedings of the 2012 International Conference on Advanced Mechatronic Systems, pp.621-625