Fault diagnosis method for complex equipment using cased-based reasoning

Rapid and accurate fault detection and diagnosis (FDD) is gaining importance for complex equipments because of the need to increase reliability and to decrease possible loss. In this paper, an intelligent fault diagnosis method is presented by using case-based reasoning (CBR) methodology to infer and classify various failures. Firstly, the case representation and the case base are established according to the characteristics of diagnosis process, and a novel case retrieval approach base on the improved grey relational analysis is presented to solve the matching problems under uncertain cases. Secondly, a new CBR-based Engine fault diagnosis (Engine-FD) system is designed and developed to diagnose four faults of 4135 diesel engine according to eighteen fault features. Finally, the application results show that the proposed fault diagnosis method has a good reliability and engineering practicability, and it can be used to solve other fault diagnosis problems.