Robust Control with Disturbance Estimation Using Echo State Networks for the Twin Rotor Aero-Dynamical System Application

Abstract

This paper deals with the application of Echo State Network (ESN) model to robust control of the Twin Rotor Aero-Dynamical System (TRAS) through estimation and cancellation of disturbances. The work describes the modelling process of the plant and control scenarios in which the system is under influence of the unknown disturbances. In such control scenarios the ESN model is used to estimate the disturbances and calculate the input correction in such way to improve the control quality. All data used in experiments are collected from the TRAS through the Matlab/Simulink environment.