A serial hybrid modeling approach is applied to mechanical systems. Here, h
ybrid means that models are based on combined structural and empirical appr
oaches. The main system behavior is described by a physical model, while co
mplex internal forces are modeled by black box neural networks. For a speci
al class of systems this methodology is extended and a novel approach is pr
esented modeling the whole system behavior by hierarchical neural networks,
that fit the relation between system outputs and internal system variables
. Useful information about the nonlinear system can be extracted from the r
esulting models. The power of hybrid modeling is illustrated with experimen
tal results and some important issues considering the practical implementat
ion are deals with.