A Fault Diagnosis Strategy using Local Models, Fault Intensity and Boundary Models Based on SDG and Data-Driven Approaches

Author

Lee, Chang Jun ; Lee, Gibaek ; Han, Chonghun ; Yoon, En Sup

Author_Institution

Seoul Nat. Univ., Seoul

Volume

4

fYear

2007

fDate

19-22 Aug. 2007

Firstpage

2044

Lastpage

2048

Abstract

In this study, at first a hybrid local fault diagnostic model based on the signed digraph (SDG) which is a kind of model based approaches and a statistical learning model, support vector machine (SVM), would be proposed. And then, the fault intensity model and the fault boundary model were constructed for various fault intensities. Key aspects are the issue of resolving signatures resulting from the same fault but with differing intensities and making the decision tool to decide which a fault occurs.

Keywords

directed graphs; fault diagnosis; learning (artificial intelligence); statistics; support vector machines; data-driven approach; fault boundary; fault diagnosis; fault intensity; signed digraph; statistical learning; support vector machine; Biological system modeling; Chemical engineering; Chemical processes; Cybernetics; Data engineering; Fault detection; Fault diagnosis; Machine learning; Support vector machine classification; Support vector machines; Fault boundary; Fault diagnosis; Fault intensity; Signed digraph; Support vector machine;

fLanguage

English

Publisher

ieee

Conference_Titel

Machine Learning and Cybernetics, 2007 International Conference on

Conference_Location

Hong Kong

Print_ISBN

978-1-4244-0973-0

Electronic_ISBN

978-1-4244-0973-0

Type

conf

DOI

10.1109/ICMLC.2007.4370482

Filename

4370482