15th Triennial World Congress of the International Federation of Automatic Control
  Barcelona, 21–26 July 2002 
A FUZZY AND ROUGH SETS INTEGRATED APPROACH TO FAULT DIAGNOSIS
Wang, W.H.1, Liu, K.D.2, Zhou, D.H.1, C.H. Wang3
1 Dept. of Automation, Tsinghua University, Beijing 100084, PR. China
Tel: +86-10-62779364, Fax: 62786911, Email: wangwenhui99@mails.tsinghua.edu.cn
2 Dept. Management, Hebei Institute of Construction Science and Technology,
Handan 065038, Hebei Province, PR China
3 Dept. of Information Science, NSFC, Beijing 100085, PR China

This paper proposes a fuzzy and rough sets integrated approach to fault diagnosis. The basic concepts of the rough set theory are firstly introduced, then we describe how the rough sets theory is combined with fuzzy logic to form a new fault diagnostic scheme. An application example, marine diesel engine fault detection and diagnosis system, is presented, and the simulation results with on board real data demonstrate the effectiveness of the proposed approach.
Keywords: Fault detection, fault diagnosis, fuzzy sets, fuzzy logic, decision tables
Session slot T-Th-E10: Fault Diagnosis Application Studies II/Area code 7e : Fault Detection, Supervision and Safety of Technical Processes