Application of an information fusion scheme for rolling element bearing fault diagnosis

Abstract

Abstract This study addresses the high level of misdiagnoses and low reliability of individual rolling element bearing fault diagnosis methods by proposing a fault diagnosis scheme with enhanced diagnosis accuracy that combines the results of two individual diagnosis methods based on an improved information fusion method. The proposed scheme applies variational mode decomposition in conjunction with a support vector machine for conducting fault diagnosis in the frequency domain, which achieves high fault diagnosis precision for learned fault conditions. Meanwhile, good generalization ability is achieved for identifying the operational conditions of bearings in the time domain by integrated mathematical morphology and correlation analysis. Subsequently, conflicts arising between evidences derived from the individual detection results are measured comprehensively using a novel strategy, and the evidences are then combined based on the Dempster–Shafer theory (DST) to enhance the information fusion effect. The effectiveness of the proposed information fusion method is verified by means of a numerical example in comparison with other fusion methods based on DST. The experimental application of the proposed information fusion fault diagnosis scheme demonstrates the complementary advantages of the two individual methods for significantly improving the diagnosis accuracy relative to the accuracies of the individual methods alone.