Mode:ling of angle tracking systems in the presence of actuator Iron-l
inearity such as angle, position and rate limits is a very significant
and difficult task in the design and implementation of aircraft, targ
et-tracking, and missile guided systems. A new recurrent neural networ
k with time-delayed inputs and output feedback is used for the modelin
g of angle tracking systems, with emphasis on the neural network archi
tecture, principles and algorithms. The neural network controller with
modeling units for angle tracking is designed by using TMS320C25 proc
essors. For time and size requirements, limited precision technology a
nd look-up table technology are used in the design of the hardware and
software systems. Given a set of input commands, the network is train
ed to control the system within the constraints imposed by actuators.
The results show that the proposed networks are able to model the angl
e tracking system through learning without separate consideration of t
he non-linearity of actuators.