Multiscale Bidirectional Diversity Entropy for Diesel Injector Fault-Type Diagnosis and Fault Degree Diagnosis

Abstract

The extraction of nonlinear dynamic fault features is a key scientific problem in the condition monitoring and fault diagnosis of diesel fuel injectors. In order to obtain effective fault features and improve fault diagnosis accuracy, this paper proposes a new fault diagnosis method for diesel fuel injectors based on Multiscale Bidirectional Diversity entropy (MBDE). Compared with common information entropy methods, bidirectional diversity entropy has obvious advantages in consistency, robustness, and computational efficiency. Finally, the fuel injector fault diagnosis method is applied to the fault type identification and fault degree identification of diesel fuel injectors. The results show that, compared with the other three commonly used information entropy methods, the method proposed in this paper has the highest recognition accuracy in the identification of fuel injector fault types and fault degrees.