Abstract
This paper presents a refinement of the diagnosis process performed with a fuzzy classifier. The proposed fuzzy classifier demonstrated high accuracy in recognizing faults. In our previous work, when using this classifier, one single category has been considered for each one of the faults under observation. However, 20 levels of fault strength have been considered for each fault, ranging from small and often unnoticeable effects up to large effects. The present work proposes three categories to be considered for each fault, corresponding to small, medium and respectively large faults. Better diagnosis results are obtained. Moreover, the proposed refinement offers a new insight and more information on the behavior of the faults, that improve the final outcome of the diagnosis process.
Original language | English |
---|---|
Title of host publication | Knowledge-Based Intelligent Information and Engineering Systems |
Editors | Mircea Gh. Negoita, Robert J. Howlett, Lakhmi C. Jain |
Place of Publication | Berlin |
Publisher | Springer |
Pages | 373-379 |
Number of pages | 7 |
Volume | 3215 |
ISBN (Electronic) | 978-3-540-30134-9 |
ISBN (Print) | 978-3-540-23205-6 |
DOIs | |
Publication status | Published - 2004 |
Externally published | Yes |
ASJC Scopus subject areas
- Theoretical Computer Science
- General Computer Science