Fault diagnosis using rough sets theory

Citation
Lx. Shen et al., Fault diagnosis using rough sets theory, COMPUT IND, 43(1), 2000, pp. 61-72
Citations number
21
Categorie Soggetti
Computer Science & Engineering
Journal title
COMPUTERS IN INDUSTRY
ISSN journal
01663615 → ACNP
Volume
43
Issue
1
Year of publication
2000
Pages
61 - 72
Database
ISI
SICI code
0166-3615(200008)43:1<61:FDURST>2.0.ZU;2-5
Abstract
The fault diagnosis on diesel engine is a difficult problem due to the comp lex structure of the engine and the presence of multi-excite sources. Usual ly, one method of fault diagnosis can only inspect one corresponding fault category. In this paper, a new method, Rough Sets Theory, is used to diagno se the valve fault for a multi-cylinder diesel engine. Through the analysis of the final reducts generated using Rough Sets Theory, it is shown that t his new method is effective for valve fault diagnosis. Rough Sets analysis requires discretizing the fault condition attributes. However, in practice, some of the limits of these attributes are unknown. A new discretization m ethod has been created and the method is found to be suitable for discretiz ing the attributes without a priori knowledge. (C) 2000 Elsevier Science B. V. All rights reserved.