电驱动总成多场耦合数据驱动建模及瞬态温度场实时在线预测  

Real-Time Online Prediction of Transient Temperature Field for Electric Drive Assembly with Multi-physics Coupling and Data-Driven Fusion Modeling

作　　者：唐鹏 赵治国[1] 李豪迪 卢万成 杨建煜 Tang Peng;Zhao Zhiguo;Li Haodi;Lu Wancheng;Yang Jianyu(School of Automotive Studies,Tongji University,Shanghai 201804;United Automotive Electronics Co.,Ltd.,Shanghai 200131)

机构地区：[1]同济大学汽车学院,上海201804 [2]联合汽车电子有限公司,上海200131

出　　处：《汽车工程》2024年第7期1259-1272,共14页Automotive Engineering

基　　金：国家自然科学基金(51675381);上海市科委科技创新项目(21DZ1209700)资助。

摘　　要：开发电驱动总成(EDA)轻量级实时在线温度精确预测方法,对于提前有效监测其未来异常温度状态,确保车辆行驶安全至关重要。基于多物理场耦合与数据驱动融合建模,提出了EDA瞬态温度场在线预测方法。首先,建立EDA电-磁-热-流多物理场耦合有限元模型,并通过台架试验验证该模型准确性;其次,采用有限元模型生成了几种常规工况下的瞬态温度场数据集,以用于后续代理模型的测试验证;然后,结合有限元模型获取简化的热网络拓扑和图卷积神经网络,提出一种模型与数据双轮驱动建模的EDA时空关系图卷积神经网络预测模型;最后,通过不同工况下的离线仿真对比分析和台架在线测试,对所提出的温度预测模型进行有效性和实时性验证。实测离线数据集上的分析结果表明:全局预测误差和平均绝对误差分别为4.4和1.25℃,相较于常规时序图卷积神经网络和门控递归单元方法分别降低17.3%、28.1%和5.3%、29.3%。台架在线预测结果也与真实测量值十分接近,其全局预测误差和平均绝对误差为3.99和0.66℃。总之,所提出的实时在线温度预测方法可以准确预测EDA真实温度变化。It is crucial to develop a lightweight real-time online temperature prediction model for electric drive assembly(EDA)to effectively monitor its future abnormal temperature state in advance and ensure vehicle safety.Based on multi-physics coupling and data-driven fusion modeling,this paper proposes an online prediction method for the transient temperature field of EDA.Firstly,a multi-physical coupling finite element model of EDA electric-magnetic-thermal-flow multi-physics coupling is established,and the accuracy of the model is verified by bench test.Secondly,several transient temperature field datasets under normal working conditions are generated via multi-physical field coupling model for subsequent proxy model verification.Then,combined with the finite element model to obtain the simplified thermal network topology and the graph convolutional neural network,a relational spatial-temporal graph convolutional neural network prediction model driven by model and data is proposed.Final-ly,the effectiveness and real-time performance of the proposed temperature prediction model are verified by offline simulation and online test under different ambient temperatures and working conditions.Analysis results on the mea-sured offline dataset show that the global prediction error and average absolute error are 4.4 and 1.25℃,reduced by 17.3%,28.1%,5.3%and 29.3%,respectively,compared with the conventional temporal graph convolutional neu-ral network and gated recurrent unit.Meanwhile,the online prediction results of the bench are also very close to the real measured values,with the global prediction error and average absolute error of 3.99 and 0.66℃.In conclusion,the proposed real-time on-line temperature prediction method can accurately predict the real temperature change of EDA.

关 键 词：电驱动总成 实时在线温度预测 多物理场耦合 关系图卷积神经网络 

分 类 号：U469.72[机械工程—车辆工程]