Analysis of Automatic Aircraft Landing using Neural Networks and Signal Processor

This paper presents an adaptive neural network, designed to improve the performance of conventional automatic landing systems (ALS). Real-time learning was applied to train the neural network using the gradient-descent of an error function to adaptively update weights. Adaptive learning rates were obtained through the analysis of Lyapunov stability to guarantee the convergence of learning. In addition, we applied a DSP controller using the VisSim/TI C2000 Rapid Prototyper to develop an embedded control system and establish on-line real-time control. Simulations show that the proposed control scheme has superior performance to conventional ALS under conditions of wind disturbance of up to 75 ft/s. Automatic aircraft landing operation, depends upon the proper functioning of various networks related to it. The safe landing of aircraft is very much important. This project deals with the detection of various obstructions related to safe landing. This is achieved by using automatic landing system through neural network, in corporation with embedded system. The sensor is used to sense the real altitude ,altitude rate and command signal. Any one of these signal is fed to the reference trajectory and other signal is fed to ARAN controller from the there the signal is fed to error comparator and other signal for error comparator comes from the reference trajectory, both the signals are compared and the difference in signal is pitch command signal that signal along with disturbance signal is given to aircraft model. If there is any changes found in aircraft model again the signal is fed to real altitude block for further comparison. The ARAN controller is used for varying the weights.