Approaches for empirical modeling include regression analysis,
polynomial curve fitting and artificial neural networks [1,2].
These methods involve constructing condenser models from
experimentally obtained input/output data, with no recourse to
any laws concerning the fundamental nature and properties of
the system. In empirical modeling, no a priori knowledge about
the process is necessary, the system is treated like a ‘‘black box,”
and the experimental information gathered from its response to
external stimuli is used to ‘‘identify” what goes on within the