To address the issues of negative transfer and reduced stability in transfer learning models for rolling bearing fault diagnosis under variable working conditions, an unsupervised multi-adversarial transfer learning fault diagnosis algorithm based on bearing dynamics simulation data is proposed. Firstly, the algorithm constructs both a global domain classifier and a subdomain classifier. In the subdomain classifier, the simulated vibration signal, which contains rich bearing fault label information, is generated by constructing dynamic equations to replace the label prediction of target domain data, thereby achieving alignment of marginal and conditional distributions. Simultaneously, an improved loss function with embedded maximum mean discrepancy is designed to reduce the feature distribution gap between source and target domain data. Finally, a weight allocation mechanism for source domain and simulation domain samples is developed to promote positive transfer and suppress negative transfer. Experiments were conducted using the Paderborn University dataset and the Huazhong University of Science and Technology dataset, achieving accuracy rates of 89.457% and 96.436%, respectively. The results show that, in comparison with existing unsupervised cross-domain fault diagnosis methods, the proposed method demonstrates significant improvements in diagnostic accuracy and stability, demonstrating its superiority in rolling bearing fault diagnosis under variable operational conditions.

Accurate prediction of the RUL of electric drive bearings over the entire service life cycle for new energy vehicles optimizes maintenance strategies and reduces costs, addressing clear application needs. Full life data of electric drive bearings exhibit long time spans and abrupt degradation, complicating the modeling of time dependent relationships and degradation states; therefore, a piecewise linear degradation model is appropriate. An RUL prediction method is proposed based on degradation assessment and spatiotemporal feature fusion, which extracts strongly time correlated features from bearing vibration data, evaluates sensitive indicators, constructs weighted fused degradation features, and identifies abrupt degradation points. On this basis, a piecewise linear degradation model is constructed that uses a path graph structure to represent temporal dependencies and a temporal observation window to embed temporal features. By incorporating GAT-LSTM, RUL prediction for bearings is performed. The method is validated on the XJTU-SY dataset and on a loaded ball bearing test rig for electric vehicle drive motors, yielding comprehensive vibration measurements for life prediction. The results show that the method captures deep degradation information across the full bearing life cycle and delivers accurate, robust predictions, providing guidance for the health assessment of electric drive bearings in new energy vehicles.

To address the low qualification rate of high-precision rolling bearing products and the need for repeated assembly and selective matching, this paper proposes a digital twin modeling method for rolling bearings oriented toward rotational accuracy prediction. Morphological feature data of the inner and outer raceways are obtained through multi-section measurements using a roundness and waviness measuring instrument. After polar-to-Cartesian transformation and adaptive parameterization, cubic NURBS curves and bicubic NURBS surfaces are used to reconstruct the raceway surface morphology features. A solid model is constructed through isogeometric transformation and geometric post-processing, and a digital twin simulation model for rotational accuracy is established based on ANSYS–ADAMS. Experimental validation is carried out using a B7008AC angular contact ball bearing as the research object. The experimental results show that, compared with the traditional smooth model, the proposed model can effectively improve the prediction accuracy of bearing rotational accuracy, providing a predictive model basis for intelligent grouping of bearing rings based on error complementarity.

Accurate prediction of bearing temperature rise offers essential support for equipment operation and optimized design. However, traditional methods often lack accuracy under the complex operating conditions of new energy electric drive bearings. To address this, we propose a model–data integration-driven approach for predicting the temperature rise in new energy electric drive bearings. First, a data-driven optimization method is employed to integrate mathematical and simulation models, generating highly reliable simulation data. Then, the simulation data and measured data are fused to construct an integrated dataset for bearing temperature rise. Finally, a CNN-LSTM prediction model is established and trained using this dataset. Validation experiments were carried out on the EV6206E-2RZTN/C3 bearing to verify the effectiveness of the proposed method. Results show (1) under constant operating conditions, the MAE during the temperature rise phase is 0.773 °C, and the steady-state phase maximum MAE is 0.686 °C, and (2) under variable operating conditions, the maximum MAE during the temperature rise phase is 0.713 °C, and the steady-state phase maximum MAE is 0.764 °C. The proposed method achieves effective prediction of temperature rise in electric drive bearings and offers a valuable reference for addressing temperature prediction challenges under complex operational conditions.