An evolutionary optimizing approach to neural network architecture for improving identification and modeling of aircraft nonlinear dynamics

Abstract

In this paper, modified genetic algorithm has been used as a simultaneous optimizer of recurrent neural network to improve identification and modeling of aircraft nonlinear dynamics. Weighted connections, network architecture, and learning rules are features that play important roles in the quality of neural networks training and their generalizability in order to model nonlinear systems. Therefore, the main focus of this paper is to apply appropriate evolutionary methods in order to simultaneously optimize the parameters of neural networks for the improvement identification and modeling of aircraft nonlinear dynamics. To validate this study, the results have been compared with the recorded data from a fourth generation highly maneuverable fighter aircraft flight test. Furthermore, having been compared to normal genetic algorithm, the results of the present study have showed significant improvement of the neural networks generalization which leads to better identification and modeling of aircraft nonlinear dynamics.