Cross-domain fault diagnosis of rolling bearing using similar features-based transfer approach

For cross-domain fault diagnosis of rolling bearing, the method of how to find and select similar features between the source and target domains is still a key problem. Toward this end, this study proposes a novel cross-domain fault diagnosis method using similar features-based transfer. Specifically, modified composite multi-scale fuzzy entropies are firstly extracted from the source domain and target domain respectively. Subsequently, minimum redundancy maximum relevance is used to select the discriminative features from the source domain. Based on these discriminative features, the Kullback-Liebler divergence is applied to search the useful features in the target domain. Finally, the K nearest neighbor classifier is used to learn the discriminative features from the source domain and classify the unlabeled samples in the target domain. Experimental results demonstrated that the proposed method can successfully achieve cross-domain fault diagnosis for the rolling bearing under different speed conditions or with different types of damages.