Marcu, Teodor; Köppen-Seliger, Birgit; Frank, Paul M.; Ding, Steven X.:
Dynamic Functional-Link Neural Networks Genetically Evolved Applied to Fault Diagnosis
In: Proc. of ECC’03 - Cambridge, UK, 2003
2003book article/chapter in collection
TechnologyFaculty of Engineering » Engineering and Information Technology » Automatic Control and Complex Systems
Title:
Dynamic Functional-Link Neural Networks Genetically Evolved Applied to Fault Diagnosis
Author:
Marcu, TeodorUDE
LSF ID
2884
Other
connected with university
;Köppen-Seliger, BirgitUDE
LSF ID
1496
Other
connected with university
;Frank, Paul M.;Ding, Steven X.UDE
GND
134302427
LSF ID
2347
ORCID
0000-0002-5149-5918ORCID iD
Other
connected with university
Appears in
Proc. of ECC’03
Place of publication:
Cambridge, UK
Year of publication:
2003

Abstract:

The paper addresses the development of neural observer schemes for process fault diagnosis. The design is based on a generalised functional-link neural network with internal dynamics. An evolutionary search of genetic type and multi- objective optimisation in the Pareto-sense is used to determine the optimal architecture of the dynamic network. Symptoms characterising the current state of the process are obtained based on prediction errors. The latter are further evaluated by a static artificial network. Experimental results regarding the detection and isolation of artificial sensor faultsin an evaporation station from a sugar factory illustrate the approach.