Intelligent modeling and identification of aircraft nonlinear flight

摘要: Abstract In this paper, a new approach has been proposed to identify and model the dynamics of highly maneuverable fighter aircraft through artificial neural networks (ANNs). general, flight is considered as nonlinear coupled system whose modeling ANNs, unlike classical approaches, does not require any aerodynamic or propulsion information few test data seem sufficient. study, for identification dynamics, two known structures internal external recurrent (RNNs) structure called hybrid combined network have used compared. order improve training process, an appropriate evolutionary method applied simultaneously train optimize parameters ANNs. research, it shown that six ANNs each with three inputs one output, trained by data, can dynamic behavior acceptable accuracy without priori knowledge about system.