Leveling and gyrocompassing of stable platforms using neural networks

This paper presents the application of neural networks for the adaptive leveling and gyrocompassing of stable platforms. The stable platform is a three input and two output nonlinear plant, and the control of its error dynamics (leveling) is of vital importance for the proper operation of the inertial navigation systems of aircraft. Also, another important pre-flight step in the inertial navigation system using the stable platform is gyrocompassing. Gyrocompassing provides the navigation system with the wander angle, which is the angle between the Y-axis of the stable platform and true north.
In this paper, neural networks are employed to identify the dynamics of the platform and to level it, based on the identified neural model; gyrocompassing is also performed using an inverse neural identification of the stable platform. In order to show the effectiveness of the proposed neural adaptive controller for platform leveling and gyrocompassing, the results of practical leveling tests performed on an inertial navigation unit of a fighter aircraft and simulation results for gyrocompassing are presented.