Fault diagnosis method of complex equipment based on gray relational analysis with entropy weight

To rapidly and effectively diagnose and remove various complex faults is an important work in current equipment maintenance and support. In this paper, a novel fault diagnosis method was proposed based on gray relational analysis and entropy weight. First, the weight values of all fault features were calculated objectively by the entropy method to avoid the influence of subjective factors. Second, the weight-based gray relational degrees were obtained, and consequently, the fault diagnosis result was obtained by using the max membership degree principle. Finally, the engineering practicability and validity of the proposed method was demonstrated by a 4,135 diesel engine fault diagnosis example. The results show that the proposed method is very simple and can effectively reflect the inherent characteristics of fault diagnosis process.