A novel transfer learning fault diagnosis method for rolling bearing based on feature correlation matching

Abstract

Abstract As one of the mainstream transfer learning methods, correlation alignment (CORAL) has been widely applied in fault diagnosis field and has achieved certain achievements. However, CORAL ignores the differences between domains in the matching process, which makes it difficult to measure the discrepancies between domains accurately. To compensate the shortcomings of the CORAL, this paper proposes a new feature correlation matching (FCM) method, and further it is applied as the objective function to propose a deep feature correlation matching network (DFCMN). The FCM method focuses on both first-order feature correlation and second-order feature correlation of the source and target domains, which measures the discrepancies between different domains more comprehensively and accurately. With the powerful feature mapping capability of neural network, the DFCMN can improve the feature similarity in different domain centers while reducing the discrepancies of feature distribution between different domains, so as to obtain more reliable shared features and improve the cross-work-conditions diagnosis accuracy. The effectiveness of the proposed method is verified through multiple transfer tasks utilizing public rolling bearing data sets.