Neural Network-Based Adaptive Tracking Control for Nonlinear Systems with Multi-actuator Constraints
摘要
In real physical systems, too large control inputs can easily cause serious accidents, Therefore, a new controller design method is suggested for nonlinear systems with dead zones and saturation. Adaptive neural network-based tracking control applied to nonlinear systems subject to multiple actuator constraints is studied based on backstepping method is designed on the basis of finite time stability theory. By introducing a second-order command filter, Complexity Blasting in Conventional Inversion Methods for designing controllers is solved. The designed control algorithm ensures good tracking controlled system the corresponding saturation and dead zone input environments. With the neural network command filtering control scheme, In a controlled system, all variables are bounded, and the results show there is tracking error near the equilibrium point. Finally, simulation results show that the proposed method is feasible.