With the increase of motor speed and the deterioration of operating environment, it is more difficult to predict the transient temperature field (TTF). Meanwhile, it is difficult to obtain the temperature test dataset of key nodes under various complete road conditions, so the cost of bench test or real vehicle test is high. Therefore, it is of great significance to establish a high fidelity, lightweight temperature prediction model which can be applied to real vehicle thermal management for ensuring the safe and stable operation of motor. In this paper, a physical model simulating electromagnetic-heat-flow multi-physical coupling of permanent magnet synchronous motor (PMSM) in electric drive gearbox (EDG) is established, and the correctness of the model is verified by the actual EDG bench test. Secondly, combined with the high order lumped parameter thermal network (LPTN) model derived from the multi-physics coupling model, the ten-node thermal network model of PMSM is established by selecting the key temperature nodes. Then, the temperature of the main component is estimated using ordinary least squares (OLS). Considering the thermal network model and the improved graph convolutional neural network (GCN), an OLS-RGCN TTF prediction model based on spatial temporal relationship graph (OLS-RGCN) is constructed. Finally, the OLS-RGCN model, the multi-physics coupling finite element model and the other two proxy models are compared with the self-test dataset obtained from the EDG bench test system. It is found that OLS-RGCN is a regression proxy model with the best comprehensive prediction performance. When the prediction time is 10s, the root mean square error and global maximum prediction error is 1.57 °C and 5.02°C, respectively.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Transient Temperature Field Prediction of PMSM Based on Electromagnetic-Heat-Flow Multi-Physics Coupling and Data-Driven Fusion Modeling


    Weitere Titelangaben:

    Sae Technical Papers


    Beteiligte:
    Li, Haodi (Autor:in) / Tang, Peng (Autor:in) / Zhao, Zhiguo (Autor:in)

    Kongress:

    SAE 2023 Vehicle Powertrain Diversification Technology Forum ; 2023



    Erscheinungsdatum :

    2023-10-30




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Print


    Sprache :

    Englisch





    Urban traffic flow prediction method based on multi-source data fusion

    LIU JIANQI / HE QI / ZENG BI et al. | Europäisches Patentamt | 2020

    Freier Zugriff

    Urban intersection traffic flow prediction method based on multi-source data fusion

    YANG HUICHANG | Europäisches Patentamt | 2021

    Freier Zugriff

    Expressway flow prediction method and system based on multi-source data fusion

    TENG ZHIWEI / XU HUA / YANG JIANGUO et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Digital Twin-Driven Surface Roughness Prediction Based on Multi-sensor Fusion

    Zhang, Xiangyu / Liu, Lilan / Wu, Fang et al. | TIBKAT | 2021