Analysis and comparison of aircraft landing control using recurrent neural networks and genetic algorithms approaches

This paper presents an intelligent aircraft automatic landing controller that uses recurrent neural networks (RNN) with genetic algorithms (GAs) to improve the performance of conventional automatic landing system (ALS) and guide the aircraft to a safe landing. Real-time recurrent learning (RTRL) is applied to train the RNN that uses gradient-descent of the error function with respect to the weights to perform the weights updates. Convergence analysis of system error is provided. The control scheme utilizes five crossover methods of GAs to search optimal control parameters. Simulations show that the proposed intelligent controller has better performance than the conventional controller.