Adaptive Neuro-controller based on HMLP network for InnoSAT attitude control

In this paper, an intelligence controller namely Adaptive Neuro-controller (ANC) based on Hybrid Multilayered Perceptron (HMLP) network is developed for the attitude control of a nano-satellite. The objective of this paper is to compare the tracking performance between ANC based on HMLP network and ANC based on standard MLP network for controlling a satellite attitude. Both ANC´s use Model Reference Adaptive Control (MRAC) as a control scheme. The control scheme was used to control a time varying systems where the performance specifications are given in terms of a reference model. Weighted Recursive Least Square (WRLS) algorithm has been used to adjust the controller parameters to minimize the error between the actual output and the reference input. Y-Thompson spin control is adapted to the satellite system as the reference input throughout the simulation. These controllers have been tested using Innovative Satellite (InnoSAT) plant with some variations in operating conditions such as varying gain, noise and disturbance. The simulation results indicated that ANC based on HMLP network is adequate to control satellite attitude and gave better result than the ANC based on MLP network.