In this contribution, a Genetic Programming (GP) algorithm is used to
develop empirical models of chemical process systems. GP performs symb
olic regression, determining both the structure and the complexity of
a model. Initially, steady-state model development using a GP algorith
m is considered, next the methodology is extended to the development o
f dynamic input-output models. The usefulness of the technique is demo
nstrated by the development of inferential estimation models for two t
ypical processes: a vacuum distillation column and a twin screw cookin
g extruder.