Digital Twin-Driven Graph Convolutional Memory Network for Defect Evolution Assessment of Rolling Bearings

The quantitative diagnosis of rolling bearing defects still mainly relies on the manual analysis of vibration signals and is limited to a specific moment in time, which restricts the intelligent identification of life-cycle defect evolution. In this article, a novel digital twin-driven graph convolutional memory network (GCMN) is proposed for evaluating the defect evolution of rolling bearings throughout the whole life. In the proposed method, a dynamic twin model is constructed to generate the vibration responses that characterize the state of bearings. The twin model is capable of accurately simulating the operational conditions of the bearing and interacting with the actual responses, thereby enhancing the accuracy of the model. In addition, a graph network model GCMN is developed to transfer knowledge from the twin model to the physical entity through domain adaptation, thereby revealing the relationship between vibration responses and defect sizes. It extracts spatial features through nonlinear transformation of graph data and incorporates temporal features via the hidden layer state at the previous moment. The experimental results demonstrate that the proposed method accurately characterizes the local defect extension throughout the bearing entire lifespan.