A locally recurrent neural network is described as a key component of
a control system able to rule an artificial satellite whose attitude m
ust be kept close to zero-angle with respect to an inertial reference
system earth centred. The main idea is to join a simple linear adaptiv
e controller with a neural network trained to compensate the inadequac
y of the former. The control signal is the sum of the signal computed
by the two devices; the feedback for training the neural network comes
from the attitude error w.r.t. a reference trajectory and is computed
by means of a linear inversion of the satellite dynamics. Thanks to s
uch co-operation, the resulting system is easily trainable and perform
s efficiently. In fact, the whole system acts as a MRAC controller who
se accuracy has been tested on numerical simulations of an Olympus cla
ss spacecraft, Considerations on stability, reactions to unexpected so
licitations, extension to non-geocentric missions and power consumptio
n are included as well.