Conflict Measurement Method Based on Improved Evidence Distance

In facing the challenge of extracting difficult data from complex rolling bearings, the uncertainty of data has become a significant issue. Among various approaches, evidence theory stands out as a crucial method. However, in practical applications, traditional evidence theory exhibits certain limitations, especially in its core component—the conflict management mechanism—when dealing with highly conflicting evidence. Accurately quantifying and managing conflicts between pieces of evidence becomes a key issue in enhancing fusion effectiveness during the process of multi-source information fusion. To address this issue, this study introduces an innovative evidence conflict measurement method aimed at improving the capability of traditional evidence theory to handle highly conflicting evidence. This method starts from the perspective of "distance" and conducts a thorough analysis of the properties required by such a distance measurement. By proving these properties, the theoretical rationality and applicability of the proposed conflict measurement method are ensured. Further, through a series of theoretical proofs and numerical calculations, this study demonstrates the accuracy of the method in dealing with completely conflicting and completely non-conflicting evidence. Simultaneously, the method can effectively measure evidence with varying degrees of conflict, showing higher flexibility and broad applicability. This is achieved by applying the new method to classic cases of conflicting evidence and comparing it with existing methods. The comparison not only verifies the effectiveness of the new method on both theoretical and experimental levels but also reveals its significant advantages in handling highly conflicting evidence. The innovation of this research is primarily reflected in the following aspects: Initially, a novel conflict measurement framework is introduced, predicated on an exhaustive analysis and understanding of the "distance" between evidences. Subsequently, the rationality and efficacy of this measurement approach are corroborated through rigorous theoretical validation. Finally, comparative analyses with conventional methodologies underscore the effectiveness of this new approach in addressing highly conflicting evidences in practical applications.