Refined composite hierarchical bidirectional diversity entropy and its application in fault type diagnosis and fault degree diagnosis of diesel engine fuel injectors

The performance of a diesel engine is closely related to the injector, and the fuel pressure shock signal for monitoring the state of the injector always contains multiple natural oscillation modes at different levels. Therefore, it is very necessary to detect the dynamic changes of the injector signal from multiple levels. Multi-scale Diversity Entropy (MDE) is a recent commonly used method of information entropy. However, due to its inherent defects, it limits the wide application of MDE in fault feature extraction. Therefore, this paper proposes a new nonlinear dynamics method, called the Refined Composite Hierarchical Bidirectional Diversity Entropy (RCHBDE). The ability of RCHBDE to extract signal complexity changes was verified through simulation signals, which is superior to MDE and multi-scale bidirectional diversity entropy (MBDE). On this basis, this article proposes a diagnostic framework for fuel injector fault type and degree based on RCHBDE and Seagull optimized Support Vector Machine. We apply the proposed method to the injector failure test data. The results show that RCHBDE can better reflect the dynamic change process of the injector fault signal than MDE and MBDE. Moreover, compared with existing methods, the proposed method in this paper improves the accuracy and efficiency of fault diagnosis.