Eng-genes: A new genetic modelling approach for nonlinear dynamic systems
| Author: | Li Kang, Queen's University Belfast, United Kingdom |
|---|
| Topic: | 3.2 Cognition and Control ( AI, Fuzzy, Neuro, Evolut.Comp.) |
|---|
| Session: | Intelligent Modelling and Identification I |
|---|
| Keywords: | nonlinear systems, modelling, genetic algorithms, neural networks, chemical process, power plant |
|---|
Abstract
A novel neural modelling method, namely 'eng-genes', is proposed for complex nonlinear dynamic engineering systems. This method performs system modelling by first establishing the ‘eng-genes’ – some fundamental engineering functions from 'a priori' engineering knowledge, which are then constructed and coded into appropriate chromosome representations. Given a suitable fitness function, using evolutionary approaches such as the genetic algorithms, a population of chromosomes evolves for a certain number of generations to finally produce a neural model best-fitting the system data. In this paper, the eng-genes genetic modelling framework is discussed in detail and it is then applied to model two nonlinear engineering systems to confirm the effectiveness.
