ABASTRACT

The control and modeling of flexible maneuvering system, such as helicopter unmanned vehicles has always been a challenging problem due to-linearity, significant cross-coupling between its two, complex aerodynamics force between its two rotors and the of some of its states and outputs for measurements. Helicopter has been widely used in air traffic systems, such as traffic condition assessment, prevention and crime precautions. The twin rotor multiple input multiple output system (TRMS) is a laboratory setup which resemble the behavior of a helicopter in certain aspects due to the complicated nonlinearity and high cross coupling effect between main rotor and tail rotor like helicopter. Some of its inputs and outputs are inaccessible for the measurement. The control effort is to make the beam of TRMS to move quickly and accurately to the desired attitudes both in terms of pitch angle and azimuth angle under decoupling effects between two axes. The project is aimed at devising a model of the non-linear MIMO system by using Neural Networks. This is because of the efficient modeling approach provided by neural networks highly non-non-linear systems. The mathematical modeling of TRMS is done using MATLAB/Simulink. The simulation results are compared with the results of conventional PID controller.
The results of A (MLP & (RBF) show better transient, rise time, overshoot and steady state response as compared to conventional PID controller.