Concurrent Analysis of Local Structure and Global Temporality: Observable and Controllable Dynamic Graph for RUL Prediction and Evolution Illustration

The accurate prediction of bearing remaining useful life (RUL) is crucial for industrial safety and cost reduction. However, existing deep learning methods often lack interpretability and struggle to integrate local-global and structural-temporal information, limiting their effectiveness. To address this issue, an observable and controllable RUL prediction method is proposed, which visualizes the bearing degradation process through spatio-temporal dynamic graph (STDG), and fully extracts structural information and temporal features to achieve precise RUL prediction. First, canonical variable fluctuation analysis (CVFA) is employed to maximize past-future data correlation, enabling information distillation by analyzing static deviations and dynamic fluctuations. Second, restraint graph attention network (RGAT) is proposed to extract local structural information, generating dynamic factors that feedback into the spatio-temporal static graph (STSG) to construct the STDG for observation and control of experts. Thirdly, to address degradation variability and long sequence dependency, the reversible instance normalization Transformer (RevIN-Former) explores the temporal evolution of the STDG from a global perspective, achieving accurate RUL prediction. Finally, the effectiveness of the proposed method is validated through three accelerated life experiments on bearings, which reduces the RUL prediction error by 88% compared to other methods. Note to Practitioners—Bearings are critical components of rotating machinery. Accurate prediction of their RUL is essential for ensuring industrial safety and reducing costs. Existing deep learning methods face challenges related to incomplete degradation information extraction and poor interpretability. To address these challenges, this paper proposes a deep learning approach that effectively leverages local structural and global temporal information through spatio-temporal dynamic graphs to comprehensively learn and visualize the bearing degradation process. The proposed method has been validated on three public datasets, and the results indicate a significant reduction in prediction error.