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

doi:10.19562/j.chinasae.qcgc.2024.07.013

摘要/Abstract

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。

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

Abstract:

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. Finally， 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 measured 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 neural 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.

Key words: electric drive assembly, real-time online temperature prediction, multi-physical field coupling, relational graph convolutional neural network

唐鹏,赵治国,李豪迪,卢万成,杨建煜. 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[J]. 汽车工程, 2024, 46(7): 1259-1272.

Peng Tang,Zhiguo Zhao,Haodi Li,Wancheng Lu,Jianyu Yang. Real-Time Online Prediction of Transient Temperature Field for Electric Drive Assembly with Multi-physics Coupling and Data-Driven Fusion Modeling[J]. Automotive Engineering, 2024, 46(7): 1259-1272.

图/表 21

图1

图2

图3

表1

图4

图5

图6

图7

图8

图9

图10

图11

图12

图13

表2

图14

图15

图16

图17

图18

表3

参考文献 17

1	GRONWALD P O， KERN T A. Traction motor cooling systems， a literature review and comparative study［J］. IEEE Transactions on Transportation Electrification， 2021： 1-1.
2	赵兰萍，江从喜，徐鑫，等. 整车运行环境下油冷对外转子轮毂电机温度特性的影响［J］. 汽车工程， 2019， 41（4）： 373-380.
	ZHAO Lanping， JIANG Congxi， XU Xin， et al. The effects of oil cooling on the temperature field of out-rotor in-wheel motor under vehicle operation environment［J］. Automotive Engineering， 2019， 41（4）： 373-380.
3	吴胜男，郝大全，佟文明. 基于等效热网络法和CFD法高速永磁同步电机热计算研究［J］. 电机与控制学报， 2022， 26（7）：29-36.
	WU Shengnan， HAO Daquan， TONG Wenming. Thermal calculation of high speed permanent magnet synchronous motor based on equivalent thermal network and CFD method［J］. Electric Machines and Control， 2022， 26（7）：29-36.
4	TANG H， DI J， WU Z， et al. Temperature analysis for the asymmetric six-phase permanent magnet synchronous motor in healthy and fault-tolerant modes［J］. IEEE Transactions on Industrial Electronics， 2023， 70（7）： 6482-6493.
5	ZHANG S， WANG C， ZHONG H， et al. Study on the temperature distribution of motor and inverter in an electric scroll compressor for vehicle air conditioning under refrigeration conditions［J］. International Journal of Refrigeration， 2023， 154：111-124.
6	WALLSCHIED O. Thermal monitoring of electric motors： state-of-the-art review and future challenges［J］. IEEE Open Journal of Industry Applications， 2021，2： 204-223.
7	GUO Y， XU R， JIN P. A real-time temperature rise prediction method for PM motor varying working conditions based on the reduced thermal model［J］. Case Studies in Thermal Engineering， 2023， 47：103098.
8	FENG G， LAI C， IYER K， et al. Improved high-frequency voltage injection based permanent magnet temperature estimation for PMSM condition monitoring for electric vehicle （EV） applications［J］. IEEE Transactions on Vehicular Technology， 2018， 67（1）： 216-225.
9	POPOV N， VUKOSAVIC S. Estimator of the rotor temperature of induction machine based on terminal voltages and currents［J］. IEEE Transactions on Energy Conversion， 2017， 32（1）： 155-163.
10	MAPELLI F， TARSITANO D， CHELI F. MRAS rotor resistance estimators for EV vector controlled induction motor traction drive： analysis and experimental results［J］. Electric Power Systems Research， 2017， 146： 298-307.
11	SHIRSAT G， JHALA A. Online rotor resistance evaluation of induction motor using ANN［J］. International Journal of Innovative Research in Science， Engineering and Technology， 2016， 5（1）： 491-498.
12	李兆宗，张硕，张承宁. 基于遗传算法的车用轴向磁通电机温度模型优化［J］. 汽车工程， 2023， 45（4）： 609-618.
	LI Zhaozong， ZHANG Shuo， ZHANG Chengning. Optimization of temperature model in axial flux motor based on genetic algorithm for EVs［J］. Automotive Engineering， 2023， 45（4）： 609-618.
13	KIRCHGAESSNER W， WALLSCHEID O， BCKER J. Thermal neural networks： lumped-parameter thermal modeling with state-space machine learning［J］. Engineering Applications of Artificial Intelligence： The International Journal of Intelligent Real-Time Automation， 2023， 117：105537-105546.
14	肖宗鑫，胡明辉，石力王，等. 电动汽车内置式永磁同步电机转子温度在线估计［J］. 机械工程学报， 2023， 59（24）：209-222.
	XIAO Zongxin， HU Minghui， SHI Liwang， et al. Rotor temperature online estimation of built-in permanent magnet synchronous motor for electric vehicle［J］. Journal of Mechanical Engineering， 2023， 59 （24）： 209-222.
15	YANG Z， DONG H， MAN J， et al. Online deep learning for high-speed train traction motor temperature prediction［J］. IEEE Transactions on Transportation Electrification， 2024， 10 （1）：608-622.
16	CHEN C， YUAN Y， SUN W， et al. Multivariate multi-step time series prediction of induction motor situation based on fused temporal-spatial features［J］. International Journal of Hydrogen Energy， 2024， 50：1386-1394.
17	TANG P， ZHAO Z G， LI H D. Short-term prediction method of transient temperature field variation for PMSM in electric drive gearbox using spatial-temporal relational graph convolutional thermal neural network［J］. IEEE Transactions on Industrial Electronics， 2023， 17（7）： 7839-7852.

参数	数值
永磁体极对数P₂	12
定子槽数S_n	72
定子槽口宽度b₀/mm	4.58
永磁体厚度h_pm/mm	4
永磁体宽度w_pm/mm	22
隔磁桥厚度T_web/mm	22
气隙长度L_gap/mm	1.1
转子轴向长度L_r/mm	94
定子内半径R_sin/mm	203
定子外半径R_sout/mm	266
定子铁芯轴向长度L_s/mm	94
定子槽深d_slot/mm	22.2
定子齿宽w_t/mm	4.15

方法	MAE/℃	l_err/℃	100个周期下平均训练时间/s	平均测试时间/s
OLS-GRU	1.77	6.12	368	0.4
OLS-TGCN	1.32	5.32	497	0.5
OLS-RGCN	1.25	4.40	481	0.45
FEM	1.35	3.49		14 077