Design of neural network based sliding mode controller for a class of nonlinear system: an event-triggered framework

This paper investigates the design of robust event-triggered neuro sliding mode controller for a class of single input single output uncertain nonlinear system whose nonlinearities are unknown. In this work, the radial basis function neural network is used to approximate these nonlinearities of the system with an adaptive weight update law. The sliding mode controller is designed with these approximated system dynamics where the traditional periodic sampling and update of control law is avoided. This neuro sliding mode controller (NSMC) is designed with a nonuniform sampling approach called event-based sampling. This control strategy not only relaxes the knowledge of complete system dynamics to implement the control law, guarantees the robustness and at the same time it reduces the computation burden and communication bandwidth without compromising the system stability. A numerical example of nonlinear system is simulated with the proposed event-triggered NSMC to evaluate its performance.