某纯电驱动重载车辆能耗预测模型

doi:10.12382/bgxb.2022.1079

摘要/Abstract

摘要：

高精度能耗预测模型是准确预测车辆续驶里程的重要前提。针对载荷大幅度变化且非结构化道路运行的纯电驱动重载车辆,建立其组合能耗模型,该模型由能耗计算基本模型与长短时记忆(Long Short-Term Memory, LSTM)神经网络差值修正两部分组成。基于能量流动过程驱动电机和变速器效率建模,结合汽车行驶动力学建立能耗计算基本模型;采用LSTM神经网络来修正基本模型能耗预测结果与车辆典型工况功率测试值的差值,有效提高了大幅变载荷且低信噪比坡度环境下的车辆能耗预测精度,因此组合能耗模型具有参数简单和模型拟合不需解释能耗规律的优点。经试验测试分析,与VT-Micro能耗模型和径向基(Radial Basis Function, RBF)神经网络能耗模型相比,所提组合能耗模型的功率预测平均误差率分别降低了17.76%和3.35%,能够实现纯电驱动重载车辆复杂工况下能耗的准确实时预测。

关键词: 纯电驱动重载车辆, 组合能耗模型, 长短时记忆神经网络, 行驶动力学, 复杂工况

Abstract:

High-precision energy consumption prediction is an important prerequisite for accurately predicting the running range of vehicle. A combined energy consumption model is established for a heavy-duty purely electric-powered vehicle operating on unstructured roads with significant load changes. The proposed model consists of two parts: a basic model for energy consumption calculation and a long short-term memory (LSTM) neural network for difference correction. Based on the efficiency modeling of drive motor and transmission, the basic model is established in combination with vehicle driving dynamics. Then the LSTM neural network is used to correct the difference between the energy consumption prediction result of the basic model and the power test value of vehicle under typical operating conditions, which effectively improves the prediction accuracy of vehicle energy consumption under significantly variable loads and low signal-to-noise ratio gradient environments. Therefore, the combined energy consumption model has the advantages of simple parameters and model fitting without explaining the energy consumption laws. The real vehicle tests are analyzed. Compared with the VT-Micro model and the Radial basis function (RBF) neural network model for energy consumption, the average error rate of power prediction of the proposed combined model is reduced by 17.76% and 3.35%, respectively, enabling the accurate real-time prediction of energy consumption for the heavy-duty purely electric-powered vehicle under complex operating conditions.

Key words: heavy-duty purely electric-powered vehicle, combined energy consumption model, LSTM neural network, driving dynamics, complex operating condition

中图分类号:

U463.1

王尔烈, 王帅, 皮大伟, 王洪亮, 王显会, 谢伯元. 某纯电驱动重载车辆能耗预测模型[J]. 兵工学报, 2024, 45(4): 1229-1236.

WANG Erlie, WANG Shuai, PI Dawei, WANG Hongliang, WANG Xianhui, XIE Boyuan. Energy Consumption Modeling for a Heavy-duty Purely Electric-powered Vehicle[J]. Acta Armamentarii, 2024, 45(4): 1229-1236.

图/表 13

图1 纯电驱动重载车辆能量流动示意

Fig.1 Energy flow of the electric-powered vehicle

图2 驱动电机效率拟合

Fig.2 Motor efficiency fitting

图3 变速器齿轮传动简图

Fig.3 Transmission structure diagram

图4 变速器一档效率

Fig.4 First gear efficiency of transmission

图5 组合能耗模型框架

Fig.5 Framework of combined energy consumption model

图6 LSTM神经网络修正过程

Fig.6 Schematic diagram of LSTM neural network

图7 典型工况片段车速

Fig.7 Vehicle speed of operating segment

图8 典型工况片段坡度(非结构化道路)

Fig.8 Road slope of operating segment(unstructured road)

图9 典型工况片段装载质量大幅变化

Fig.9 Loading mass of operating segment

表1 车辆基本参数

Table 1 Test vehicle parameters

参数	数值
空载质量/t	35
迎风面积/m²	7.68
车轮半径/m	0.72
电机额定功率/kW	350
电机额定转矩/(N·m)	1800
电机额定转速/(r·min^-1)	1900

图10 组合能耗模型与VT-Micro模型预测结果对比

Fig.10 Comparison of the predicted power consumption results of the proposed combined model and the VT-Micro model

图11 组合能耗模型与RBF神经网络预测结果对比

Fig.11 Comparison of the predicted power consumption results of the proposed combination model and the RBF neural network

表2 功率预测误差对比

Table 2 Comparison of power prediction errors

模型	e_ave/%	S/kW
组合能耗模型	6.67	5.44×10³
VT-Micro能耗模型	24.43	1.72×10⁴
RBF能耗模型	10.02	7.11×10³

参考文献 20

[1]	隗海林, 赖祥翔, 黄朝胜, 等. 基于速度和加速度概率分布的电动汽车能耗计算模型[J]. 吉林大学学报(工学版), 2014, 44(6): 1591-1595.
	KUI H L, LAI X X, HUANG C S, et al. Energy consumption calculation model of electric vehicle based on probability distribution of velocity and acceleration[J]. Journal of Jilin University (Engineering and Technology Edition), 2014, 44(6): 1591-1595. (in Chinese)
[2]	AHN K, RAKHA H, TRANI A, et al. Estimating vehicle fuel consumption and emissions based on instantaneous speed and acceleration levels[J]. Journal of Transportation Engineering, 2002, 128(2): 68-72.
[3]	LI L F, LIU Q. Acceleration curve optimization for electric vehicle based on energy consumption and battery life[J]. Energy, 2019, 169: 1039-1053.
[4]	LUIN B, PETELIN S, Al-MANSOUR F. Microsimulation of electric vehicle energy consumption[J]. Energy, 2019, 174: 24-32. doi: 10.1016/j.energy.2019.02.034
[5]	金辉, 周敏, 李世杰. 基于瞬态修正的车辆燃油消耗模型建模[J]. 北京理工大学学报, 2017, 37(5): 473-477,484.
	JIN H, ZHOU M, LI S J. Vehicle fuel consumption model modeling based on transient correction[J]. Transactions of Beijing Institute of Technology, 2017, 37(5): 473-477, 484. (in Chinese)
[6]	BI J, WANG Y X, SHAO S, et al. Residual range estimation for battery electric vehicle based on radial basis function neural network[J]. Measurement, 2018, 128: 197-203.
[7]	YANG S C, LI M, LIN Y, et al. Electric vehicle's electricity consumption on a road with different slope[J]. Physica A Statistical Mechanics and Its Applications, 2014, 402: 41-48.
[8]	ZHANG R, YAO E J, et al. Mesoscopic model framework for estimating electric vehicles energy consumption[J]. Sustainable Cities and Society, 2019, 47: 101478.
[9]	肖迁, 焦志鹏, 穆云飞, 等. 基于LightGBM的电动汽车行驶工况下电池剩余使用寿命预测[J]. 电工技术学报, 2021, 36(24): 5176-5185.
	XIAO Q, JIAO Z P, MU Y F, et al. Prediction of the remaining service life of batteries under the driving conditions of electric vehicles based on LightGBM[J]. Journal of Electrotechnical Technology, 2021, 36(24): 5176-5185. (in Chinese)
[10]	邹天刚, 闫清东, 盖江涛, 等. 基于扁平电机的轻混式履带车辆综合传动方案[J]. 兵工学报, 2021, 42(10): 2233-2241. doi: 10.3969/j.issn.1000-1093.2021.10.019
	ZOU T G, YAN Q D, GAI J T, et al. Integrated transmission scheme of light hybrid tracked vehicle based on flat motor[J]. Acta Armamentarii, 2021, 42(10): 2233-2241. (in Chinese)
[11]	田乐. 电动汽车用永磁同步电机设计、分析与效率优化[D]. 杭州: 浙江大学, 2019.
	TIAN L. Design analysis and efficiency optimization of permanent magnet synchronous motor for electric vehicles[D]. Hangzhou: Zhejiang University, 2019. (in Chinese)
[12]	王玮琪, 王伟达, 孙晓霞, 等. 重型车辆多挡并联混合动力系统的联合优化控制策略[J]. 兵工学报, 2021, 42(10): 2242-2250. doi: 10.3969/j.issn.1000-1093.2021.10.020
	WANG W Q, WANG W D, SUN X X, et al. Joint optimal control strategy for multi-speed parallel hybrid power system of heavy vehicle[J]. Acta Armamentarii, 2021, 42(10): 2242-2250. (in Chinese)
[13]	胡东坡. 纯电动汽车两挡机械变速器效率分析及考虑工况和变速器效率的换挡策略[D]. 重庆: 重庆大学, 2016.
	HU D P. Efficiency analysis of two-gear mechanical transmission in pure electric vehicle and shifting strategy considering working conditions and transmission efficiency[D]. Chongqing: Chongqing University, 2016. (in Chinese)
[14]	CHEN S W, MATSUMOTO S. Influence of relative position of gears and casing wall shape of gear box on churning loss under splash lubrication condition-some new ideas[J]. Tribology Transactions, 2016, 59(6): 993-1004.
[15]	WANG E L, MENG F. Down shift control with power of planetary-type automatic transmission for a heavy-duty vehicle[J]. Mechanical Systems and Signal Processing, 2021, 159: 107828.
[16]	黄凯, 丁恒, 郭永芳, 等. 基于数据预处理和长短期记忆神经网络的锂离子电池寿命预测[J]. 电工技术学报, 2022, 37(15): 3753-3766.
	HUANG K, DING H, GUO Y F, et al. Lithium-ion battery life prediction based on data preprocessing and long short-term memory neural network[J]. Chinese Journal of Electrotechnical Technology, 2022, 37(15): 3753-3766. (in Chinese)
[17]	LIAN J, WANG X R, LI L H, et al. Plug-in HEV energy management strategy based on SOC trajectory[J]. International Journal of Vehicle Design, 2020, 82(1/2/3/4): 1-17.
[18]	韩少剑, 张风奇, 任延飞, 等. 基于深度学习的混合动力汽车预测能量管理[J]. 中国公路学报, 2020, 33(8): 1-9. doi: 10.19721/j.cnki.1001-7372.2020.08.001
	HAN S J, ZHANG F Q, REN Y F, et al. Predictive energy management strategies in hybrid electric vehicles using hybrid deep learning networks[J]. China Journal of Highway and Transport, 2020, 33(8): 1-9. (in Chinese)
[19]	ZHOU M, JIN H. Development of a transient fuel consumption model[J]. Transportation Research, Part D: Transport and Environment, 2017, 51: 82-93.
[20]	张通彤, 姜湖海, 岳巍, 等. 基于径向基函数神经网络的光电系统自适应控制[J]. 兵工学报, 2022, 43(3): 556-564. doi: 10.12382/bgxb.2021.0117
	ZHANG T T, JIANG H H, YUE W, et al. Adaptive control of photoelectric system based on radial basis function neural network[J]. Acta Armamentarii, 2022, 43(3): 556-564. (in Chinese)