System identification (SI) aims to obtain mathematic models to estimate one or more behaviours from a physical
process whose dynamic equations are unknown.
Classic SI refers to the parametrical literature, which has its origin in the linear system analysis [20].
Nevertheless, the increase of the computation capabilities and the availability of soft computing techniques have widen the researches in SI.
One of the most interesting soft computing paradigms used in SI is the Artificial Neural Networks (ANNs).
In any way, the SI procedure is invariantly the same taking advantage of the modelling technique used.