Internal model control based on RBF neural network inverse system decoupling in a 3-DOf helicopter system

Abstract

3-DOF helicopter is a typical multi-input multi-output (MIMO) system with high-order and strong channel coupling and nonlinearity. In this paper, an internal control strategy based on RBF neural network inverse system decoupling for helicopter process is proposed. First the mathematical model of helicopter system is obtained and the reversibility of system is testified, then the neural network inverse system of helicopter is established by neural network online identification, and the inverse model as controller model and helicopter in series, which forms a dynamic pseudo linear system. The MIMO helicopter system with strong coupling is converted into isolated dynamic decoupling pseudo linear system. Finally, a linear close-loop internal model controller is designed. The simulation shows that this strategy is very validity in tracking control of the 3-DOF helicopter system.