Development of a structuring residuals method for diagnostic by PCA-based genetic algorithms

Author

Najeh, T. ; Nabli, L.

Author_Institution

Unite d´Autom., Traitement de Signal et Image (ATSI), Nat. Eng. Sch. of Monastir, Monastir, Tunisia

fYear

2012

fDate

6-8 Dec. 2012

Firstpage

1

Lastpage

6

Abstract

In this paper we propose a new method of structuring of residuals for detection and fault localization by the PCA (Principal Component Analysis). This method is based on the multi-objective optimization by genetic algorithms. The principle of this approach is to maximize the sensitivity of some residuals at certain defects and simultaneously minimize the sensitivity of the remaining residuals for other defects. Numerical example is simulated to validate the proposed technique.

Keywords

fault diagnosis; fault tolerance; genetic algorithms; principal component analysis; reliability; PCA-based genetic algorithm; fault detection; fault diagnosis; fault localization; multiobjective optimization; principal component analysis; residual sensitivity; structuring residuals method; Equations; Genetic algorithms; Mathematical model; Optimization; Principal component analysis; Sensitivity; Vectors; PCA; fault location; genetic algorithms; model-based fault diagnosis; structuring residuals;

fLanguage

English

Publisher

ieee

Conference_Titel

Communications, Computing and Control Applications (CCCA), 2012 2nd International Conference on

Conference_Location

Marseilles

Print_ISBN

978-1-4673-4694-8

Type

conf

DOI

10.1109/CCCA.2012.6417885

Filename

6417885