Data–Model Integration-Driven Temperature Rise Prediction Method for New Energy Electric Drive Bearings

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.