A Novel Neural Network Based Adaptive Control for a Class of Uncertain Strict-Feedback Nonlinear Systems

In this paper, a novel robust adaptive tracking control approach is presented for a class of strict-feedback single input single output nonlinear systems. In the controller design process, all unknown functions at intermediate steps are passed down, and only one neural network is used to approximate the lumped unknown function of the system at the last step. Although some similar design themes have been proposed, the approach presented in this paper is more reasonable and simpler. The most contribution in this paper is that a new concept named "filter technique" is proposed for how to avoid generating new unknown functions when derivation of virtual control law in the backstepping based control methods. So the neural network is just used to approximate the finite or less unknown functions and the good capabilities in function approximation of neural network are guaranteed. Stability analysis shows that the uniform ultimate boundedness of all the signals in the closed-loop system can be guaranteed, and the steady state tracking error can be made arbitrarily small by appropriately choosing control parameters. Simulation results demonstrate the effectiveness of the proposed scheme.