Important sources of disturbance torque inputs, which may severely degrade
the seeker tracking accuracy of a guided missile, involve seeker mass imbal
ance, seeker gimbal friction, and seeker head restoring torque. This paper
intends to present a novel approach to treat the disturbance rejection prob
lem for the missile seeker. As the disturbance variables are measurable, we
show that the quality of seeker tracking accuracy can be improved by the a
ddition of feedforward control, A multilayer feedforward neural network is
proposed to realize the nonlinear adaptive feedforward controller. Extensiv
e simulation studies are performed to examine the effect of the proposed co
ntrol scheme. The result shows that the neural controller affords possibili
ties for improving the miss distance performance.