Active noise control is one among the most promising applications of the so-called Smart Structures, because
it ensures, or promises, lower weight, lower cost, more effectiveness and all what is desirable in a vehicle design
process, with respect to the current solutions. More and more attention in the research world has been devoting to
this argument, pushed by both political, economical and environmental reasons, the one connected to the others.
Piezoceramic actuators, integrated into the structure, seem to offer the most fashionable and practical solutions
among all the proposed architectures, [1-2]. As sensors, microphones demonstrated to be the most performing,
above all because they give the most suitable representation of the field that has to be cancelled, [3-4]. This
approach is known as Acousto-Structural Active Control, ASAC, .
However, according to Fuller's definition,  , an intelligent controller is needed to ensure the development of an
"Intelligent Structure" . Its main characteristic should be represented by the capability of learning by examples,
of following the structure during its evolution, of being the system "brain" . This peculiarity may be offered by
Artificial Neural Networks (ANN's), [7-8]. They present other important features, like the capability, in principle,
of treating non-linear as well as linear problems, , of identifying dynamic systems, , of properly acting as
a controller. Then, such a net could integrate in itself the function of "system estimator" or "observer" ,and of
interpolator - extrapolator and controller, contemporarily. The authors have been working on such subjects for a
long time, proposing for instance ANN's as time-domain structural parameters estimators on a simple 2D element
( a framed plate), , as noise and vibration controllers in a FF system, [12-13], as materials damping parameters
extractors from experimental data, . All these applications were aimed at noise reduction problems. The
results were very encouraging.