Satellite attitude control using multilayer perception neural networks

This work simulates and tests the use of artificial neural networks for satellite attitude dynamics identification and control. In order to exemplify this application, a satellite with a rigid main body, three reaction wheels and three flexible solar panels was chosen (lay-out similar to Brazilian Remote Sensing Satellite). The main objective is to test the neural control and analyze its interaction with the elastic motion and variable geometry of the satellite. Two control schemes are used, the Internal Model Control (IMC) and a modified version of the Fedback Learning Control (FLC). The identification of neural nets parameters is performed by a Kalman filtering algorithm with a local parallelprocessing version in the IMC scheme and by the steepest descent method in the FLC scheme.