Genetic evolving of dynamic neural networks with application to process fault diagnosis

Author

Marcu, T. ; Ferariu, L. ; Frank, P.M.

Author_Institution

FG Mess- und Regelungstech., Univ. - GH - Duisburg, Duisburg, Germany

fYear

1999

fDate

Aug. 31 1999-Sept. 3 1999

Firstpage

4226

Lastpage

4231

Abstract

The robustness issue in model-based diagnosis of process faults is addressed by means of artificial neural networks. The symptoms are generated by using observer schemes with dynamic neural nets. Their design is based on a hierarchical genetic algorithm, extended back-propagation method and multiobjective optimisation. The evolutionary search of genetic type is used to find the optimal architecture of the dynamic networks. Static networks are then used to classify the symptoms. Application to a laboratory process illustrates the approach. It refers to component and instrument fault detection and isolation in a three-tank system.

Keywords

backpropagation; fault diagnosis; genetic algorithms; neural nets; observers; artificial neural networks; dynamic neural networks; extended backpropagation method; fault detection; fault isolation; hierarchical genetic algorithm; model-based diagnosis; multiobjective optimisation; observer schemes; process fault diagnosis; static networks; three-tank system; Artificial neural networks; Biological cells; Genetic algorithms; Genetics; Neurons; Sociology; Statistics; fault diagnosis; genetic algorithms; multiobjective optimisation; neural networks; three-tank system;

fLanguage

English

Publisher

ieee

Conference_Titel

Control Conference (ECC), 1999 European

Conference_Location

Karlsruhe

Print_ISBN

978-3-9524173-5-5

Type

conf

Filename

7099997