A novel digital twin model for dynamical updating and real-time mapping of local defect extension in rolling bearings

Abstract

The study of bearing local defect extension is of importance for bearing health monitoring and management. However, the local defect sizes of rolling bearings are difficult to monitor in real-time. To tackle this problem, a novel digital twin (DT) model is proposed in this paper for dynamical updating and real-time mapping of local defect extension in rolling bearings. The novel DT model is achieved through combining mechanism models and real-time sensor data, rather than relying solely on measured data as in the traditional DT model. By this means, the full life-cycle defect sizes can be mapped directly utilizing the novel DT model. The XJTU-SY bearing dataset is applied to assess the novel DT model. The result shows that the local defect extension of the full life-cycle in rolling bearings can be characterized accurately in the novel DT model.