Abstract: In a previous study , it was found that the pilot behavior shows obviously nonlinear characters in the multiloop pilot-vehicle system. Therefore , a new method , neural-networks , is focused on the pilot modeling. A real timesimulation is carried out on a simulator , in which the pilot traces the command velocity and pitch angle of aircraft bycontrolling the stick and throttle respectively. The neural network model is identified and its precision expression isfurther proposed. The result obtained verifies the validity of the proposed models compared with the quasi-linearmodel. It is proved that the neural network model is an effective model to describe the nonlinear behavior of pilots.

Key words: man-machine system, pilot models, neural-networks, model building, multi-loop systems