ELM Based Composite Anti-Disturbance Control of a Class of Nonlinear Systems based on Disturbance Observer

This paper studies the design problem of extreme learning machine (ELM) based composite anti-disturbance control for a class of nonlinear systems with disturbances modeled by nonlinear exogenous system. First, the ELM network is used to approximate the nonlinear functions in the system and the exosystem. To deal with the disturbance of nonlinear exosystem, an ELM disturbance observer is constructed. Then, a composite anti-disturbance controller based on ELM disturbance observer is constructed to compensate the unknown disturbance. The stability of the closed loop system is analyzed. Finally, the effectiveness of the proposed method is verified through the simulation experiment on the dynamic positioning system ship.