REAL TIME NEURO CONTROL TECHNIQUE OF A TWIN ROTOR SYSTEM

Abstract

This paper describes the development of neural network controller of twin rotor multi input multi output system (TRMS) in real time. The TRMS is the aerodynamic test rig representing the control challenges of modern aircraft. As TRMS resemble the helicopter’s behavior in certain aspect, it becomes the best laboratory platform for this topic. The mathematical modeling for pitch channel required for this topic can be derived based on TRMS model. System Identification technique is suggested to be use to get the proper TRMS modeling for better result. Based on the mathematical modeling, the behavior of the system can be predicted and the control will be train to compensate the error to enhance the robustness and stability of the system. In this topic neural network control technique is apply for adaptive controller to get desired performance.