Adaptive neural network control for time-varying state constrained nonlinear stochastic systems with input saturation

This paper investigates the tracking control issue of nonlinear stochastic systems subject to time-varying full state constraints and input saturation. By employing both neural network-based approximator and backstepping technique, an adaptive neural network (NN) control approach is presented on the basis of the time-varying barrier Lyapunov function. To surmount the influence of saturation nonlinearity, a Gaussian error function-based continuous differentiable saturation model is introduced such that the actual control in the final backstepping step can be achieved. The designed controller can not only achieve the tracking control objective, but also surmount the impact of input saturation to stochastic system performance. Meanwhile, the norm of NN weight vector is taken as estimated parameter, and it can alleviate computation burden. The presented controller can ensure that all the signals in the closed-loop system are bounded in probability and all state variables are restricted the predefined regions. Finally, simulation results are given to illustrate the effectiveness of the established controller. (C) 2020 Elsevier Inc. All rights reserved.