This paper describes the use of neural networks in a speed control loo
p applied to a DC motor. The proposed technique makes use of the learn
ing capability of neural networks to implement an auto-adaptive contro
l structure. Such capability allows the network to learn the dynamic b
ehavior of the SCR-driven DC motor. This identification network is the
n used to train another network as the process controller, so that the
process output follows the reference signal. An adaptation scheme for
working conditions is also presented. Its performance is verified thr
ough testing of physical parameter variations and noise presence, show
ing the applicability of the system.