|
DYNAMIC MODELLING USING GENETIC PROGRAMMING
Mark Hinchliffe and Mark Willis
m.p.hinchliffe@ncl.ac.uk, mark.willis@ncl.ac.uk
Advanced Control Group, Department of Chemical and Process Engineering
University of Newcastle, Newcastle upon Tyne NE1 7RU, UK
In this contribution we demonstrate how a Single Objective Genetic Programming (SOGP) and a Multi-Objective Genetic Programming (MOGP) algorithm can be used to evolve accurate input-output models of dynamic processes. Having described the algorithms, two case studies are used to compare their performance with that of Filter-Based Neural Networks (FBNNs). For the examples given, the models generated using GP have comparable prediction performance to the FBNN. However, performance with respect to additional modelling criteria can be improved using the MOGP algorithm.
Keywords: Genetic algorithms, dynamic modelling, multi-objective optimisation
Session slot T-Tu-E01: Soft Computing and Wavelets in Identification/Area code 3a : Modelling, Identification and Signal Processing
 | 