Using genetic programming to develop inferential estimation algorithms

Authors:
Ben McKay;Mark Willis;Gary Montague;Geoffrey Barton
Affiliations:
University of Sydney, NSW, Australia;University of Newcastle, Newcastle, UK;University of Newcastle, Newcastle, UK;University of Sydney, NSW, Australia
Venue:
GECCO '96 Proceedings of the 1st annual conference on Genetic and evolutionary computation
Year:
1996

Citing 2
Cited 0

Artificial neural networks in process estimation and control

Automatica (Journal of IFAC)
System Identification using Structured Genetic Algorithms

Proceedings of the 5th International Conference on Genetic Algorithms

Quantified Score

Hi-index	0.00

Visualization

Abstract

Genetic Programming (GP) is used to develop inferential estimation algorithms for two industrial chemical processes. Within this context, dynamic modelling procedures (as opposed to static or steady-state modelling) are often required if accurate inferential models are to be developed. Thus, a simple procedure is suggested so that the GP technique may be used for the development of dynamic process models. Using measurements from a vacuum distillation column and an industrial plasticating extrusion process, it is then demonstrated how the GP methodology can be used to develop reliable 'cost' effective process models. A statistical analysis procedure is used to aid in the assessment of GP algorithm settings and to guide in the selection of the final model structure.