A credibility evaluation method for digital twin based on improved evidence theory

With the rapid development of digital twin technology, the evaluation of its credibility has become a critical issue that needs to be addressed. Existing evaluation methods struggle to effectively cope with the complex and highly dynamic characteristics of digital twins. Therefore, an improved credibility evaluation method based on evidence theory is proposed to enhance the accuracy and reliability of the evaluation results. Firstly, to address the challenge of inconsistent data types across different evaluation metrics in twin models, a cloud model is utilized to generate a unified basic probability assignment, providing a consistent data foundation for the credibility evaluation method. Secondly, to overcome the limitations of traditional evidence theory in handling evidence conflict and uncertainty, an improved evidence theory-based credibility evaluation method is proposed. This method can address conflict resolution and uncertainty expression by incorporating evidence sufficiency and indicator importance. Finally, by effectively integrating multi-source heterogeneous data, this evaluation method enables an accurate evaluation of the credibility of digital twin. Experimental results demonstrate that the proposed method outperforms traditional approaches in handling evidence conflict, providing a more precise evaluation of digital twin credibility, and offering a more reliable basis and evaluation standard for digital twin system design.