基于车辆位置与速度特征的驾驶行为模式分类方法

精细车辆轨迹中包含连续的时间戳、位置,以及速度等信息。通过对车辆轨迹数据进行量化表达与挖掘分析,可以实现对车辆行为模式的分类。现有研究大多关注对位置的聚类,很少对车速、加速度等特征进行研究分析,而车速等是反映驾驶行为模式的重要特征。为了将轨迹多维信息纳入分析框架,研究了基于位置与速度特征的车辆轨迹行为模式分类方法。为克服现有行为模式分类方法的维度单一性,运用豪斯多夫轨迹距离算法计算出位置和速度特征的综合距离矩阵,针对豪斯多夫距离算法鲁棒性差的缺点,采用单向豪斯多夫距离90%分位值对算法进行了改进,降低噪声影响。同时,引入了车辆位置和速度来进一步提高分类的准确性,运用多次分层聚类算法依次对位置与速度轨迹图进行分类,得到车辆位置和速度上的行为模式。以HighD数据集为样本,提取了三车道上的行车轨迹,验证了基于速度与位置特征的车辆行为模式分类方法。结果表明：(1)本方法可以得到位置和速度的综合行为模式,聚类平均准确率达到94.8%,优于DBTCAN准确率89.3%和t-Cluster准确率86.4%;(2)基于换道模式轨迹偏移率曲线的分析,得到了4种互异的典型车辆换道模式。该方法可利用多维轨...     

基于数据驱动的电动汽车动力电池SOC预测

为准确预测电动汽车动力电池的能耗,缓解驾驶者的里程焦虑,本文中提出一种基于数据驱动的电动汽车动力电池SOC预测模型.首先分析电动汽车能耗构成并提取能耗影响因素,接着基于某款电动出租车CAN总线采集的汽车运行数据,采用机器学习算法,提出基于温度分层的能耗模型,通过宏观数据与微观数据的融合减小误差,最后使用该模型对车载BM...     

纯电动车热管理系统构建研究

现在国内专业领域针对电动车热管理多集中在电池热管理方向,探讨电机、电池、空调系统整合的整车热管理参考文献不多;主要介绍了纯电动汽车电机、电控等散热需求零件的热管系统构建和电池温控系统发展技术综述与技术趋势。希望通过本文的介绍,对后续热管理系统的发展,推动相关热管理零部件产业化发展提供参考(如通断式电子水阀、流量比例调节的电子水阀、高功率水泵、新型材料的冷却管路等);同时也对控制策略、控制阀值、零部件作动方式进行较为详细的介绍,有一定的参考意义。     

Optimal power distribution of front and rear motors for minimizing energy consumption of 4-wheel-drive electric vehicles

In this paper, the optimal power distribution of the front and rear motors for minimizing energy consumption of a 4WD EV is investigated. An optimal power distribution control is developed based on the mathematical energy consumption model of an EV. The objective function is defined while ignoring time. And, the time effect is applied by considering the objective function for every single driving point which consists of the vehicle driving force and velocity. From the optimization problem, the optimal torque distribution maps of the front and rear motors can be obtained for all vehicle driving force and velocity ranges. These maps can be expressed using a 3-dimensional map. If the vehicle driving force and velocity are determined, the optimal front and rear motor torques can be determined using these maps. These maps can distribute the front and rear motor torques for the entire velocity range. Thus, these maps can perform the optimal power (torque times speed) distribution of the front and rear motors for minimizing the energy consumption of the 4WD EV. The performance of the optimal power distribution is evaluated by comparing the energy consumption to that of simple power distribution control. For obtaining the energy consumption, a vehicle driving simulation is performed. For the simulation, the driving cycle is required, and the NEDC (New European Driving Cycle) is used. From the simulation results, it is found that the energy consumption of simple power distribution is 4.8 % larger than the optimal one. Thus, the optimal power distribution can minimize the 4WD EV energy consumption as the optimization objective function.     

纯电动车动力系统选型和基于AVL Cruise的性能仿真

纯电动车作为新能源车的一个重要解决方案,得到了快速发展。根据整车动力性参数对动力系统进行了选型,并利用先进的整车模拟软件Cruise进行了仿真验证。首先,利用Cruise搭建了一个纯电动车模型,并利用原车数据进行了标定,在此基础上进行了整车动力性能仿真计算,仿真结果表明该纯电动车选型的动力性能能够达到预期的目标,为纯电动车的前期开发节约了时间和成本。     

基于多维信息特征分析的驾驶人认知负荷研究

准确评估驾驶人认知负荷水平，对于深入研究驾驶人行为特性，改善驾驶安全性具有重要意义。现有的驾驶人认知负荷分类方法，大多基于心电、脑电等生理信息和车辆信息，由于特征选择上的单一性，导致驾驶人认知负荷分类模型的分类精度不高。设计基于跟驰场景的不同认知负荷N-back次任务试验，通过采集受试者的生理信号和车辆信号，结合NASA_TLX主观评分和机器学习算法，提出了基于多维信息特征融合的驾驶人认知负荷分类方法。研究表明：基于生理信息和车辆信息的多维信息特征认知负荷分类方法，其精度显著高于传统的基于生理信息的认知负荷分类方法，以多维信息特征为输入，随机森林法以其稳定性好、抗过拟合能力强的特点，表现出优异的分类效果，相比神经网络和支持向量机，具有最高的平均分类精度。     

Simulation of a powertrain system for the diesel hybrid electric bus

The plug-in hybrid electric bus (HEB) is designed to overcome the vulnerable driving range and performance limitations of a purely electric vehicle (EV) and have an improved fuel economy and lower exhaust emissions than those of a conventional bus and convention HEBs. The control strategy of the plug-in parallel HEB??s complicated connected propulsion system is one of the most significant factors for achieving a higher fuel economy and lower exhaust emissions than those of the HEV. The proposed powertrain control strategy has flexibility in adapting to the battery??s state of charge (SOC), exhaust emissions, classified driving patterns, driving conditions, and engine temperature. Simulation is required to model hybrid powertrain systems and test and develop powertrain control strategies for the plug-in parallel HEB. This paper describes the simulation analysis tools, powertrain components?? models and modifications, simulation procedure, and simulation results.     

电动汽车电源管理的基础框架和实施

电池组电源管理系统(BMS)是纯电动和混合动力的电动汽车结构的关键要素。其电源管理的设计要点是确保锂电池效能的最佳化和最高的可靠性和安全性。智能型的方案不仅延长电池组的寿命,也增加了车辆的行驶距离。提供驱动电机电源的锂电池组有数百伏的高电压,对汽车电子系统的电磁兼容性、安全性带来一系列的影响,其可靠的实现方案也是电源管理系统的核心要求之一。     

纯电动汽车设计软件的开发与应用

首先概述目前纯电动汽车的设计软件的进展,然后介绍海马纯电动汽车的设计软件的数学模型、用户界面和程序代码设计方法,接着应用该软件设计了一个低速纯电动汽车的项目,同时对整车品质等指标与续驶里程的关系进行了分析,最后评价使用效果。     

基于双MCU的纯电动汽车整车控制器硬件设计

根据长城汽车某传统车型改装成纯电动车的实际需求,及对整车控制系统的要求设计整车控制器,详细介绍电源管理、CAN通信、输入信号处理以及继电器驱动等电路的设计方法。基于双MCU的硬件设计方案增强了整车控制系统的硬件故障自诊断能力,大大提高了整车控制器的可靠性。     

电动汽车能量回馈的整车控制

以4种典型循环工况为例对电动汽车进行能量分析，设计了基于常规汽车制动系统的整车能量回馈控制方式，研究了控制策略，完成了车辆道路试验与标定优化。试验表明，整车能量回馈控制方式与控制策略安全、可靠，且柔顺性良好；利用能量回馈技术，蓄电池能量消耗可减少10％，能有效延长电动汽车的一次充电续驶里程。     

电动汽车驱动系统再生制动特性分析与仿真

电动汽车行驶时对能量的需求以及延长续驶里程要求驱动电机具有再生制动能力,既可以提供制动力,又可以将制动过程中的能量回收。通过对汽车制动模式及其产生的能量进行分析。以永磁无刷直流电机系统在作电动汽车动力时实现电气制动为控制策略,仿真了回馈制动,并对仿真结果进行了分析、探讨。结果表明,再生制动的算法是可行的,能满足能量回收要求。     

Normal and risky driving patterns identification in clear and rainy weather on freeway segments using vehicle kinematics trajectories and time series cluster analysis

Enhancing traffic safety on freeways is the main goal for all transportation agencies. However, to achieve this goal, many analysis protocols of network screening models need to be improved through considering human factors while analyzing traffic data. This paper introduces one on the new analysis protocol of identifying and discriminating between normal and risky driving in clear and rainy weather. The introduced analysis protocol will consider the effect of human factors on updating the networking screening process of identifying hotspots of crash risk. This paper employs the Second Strategic Highway Research Program (SHRP2) Naturalistic Driving Study (NDS) data to investigate the behavior of normal and risky driving under both rainy and clear weather conditions. Near-crash events on freeways, which were used as Surrogate Measure of Safety (SMoS) for crash risk, were identified based on the changes in vehicle kinematics, including speed, longitudinal and lateral acceleration and deceleration rates, and yaw rates. Through a trajectory-level data analysis, there were significant differences in driving patterns between rainy and clear weather conditions; factors that affected crash risk mainly included driver reaction and response time, their evasive maneuvers such as changes in acceleration rates and yaw rates, and lane-changing maneuvers. A cluster analysis method was employed to classify driving patterns into two clusters: normal and risky driving condition patterns, respectively. Statistical results showed that risky driving patterns started on average one second earlier in rainy weather conditions than in clear weather conditions. Furthermore, risky driving patterns extended in average three seconds in rainy weather conditions, while it was two seconds in clear weather conditions. The identification of these patterns is considered as a primary step towards an automated development that would distinguish between different driving patterns in a Connected Vehicle CV environment using Basic Safety Messages (BSM) and to enhance the network screening analysis for increased crash risk hotspots.     

4WID/4WIS电动车建模和特殊工况仿真

介绍了四轮独立驱动/四轮独立转向(4WID/4WIS)电动车的特点,基于Matlab/Simulink搭建了各子系统及整车的动力学仿真模型,设置了该类型电动车特有的驾驶模式选择功能。模型允许对4个车轮输入不同的驱动转矩和转角;考虑了驱动电机、转向电机的动态响应特性。针对4WID/4WIS电动车特有的蟹行、斜行和原地转向工况进行了仿真。结果表明,模型能够较好地反映4WID/4WIS电动车的动力学响应特性。     

Urban driving cycle for performance evaluation of electric vehicles

Nowadays, a number of environmental issues have seriously come to the fore. For this reason, the R & D spending on eco-friendly vehicles that use electric power has been gradually increasing. In general, fuel economy and pollutant emissions of both conventional and eco-friendly vehicles are measured through chassis dynamometer tests that are performed on a variety of driving cycles before an actual driving test. There are a number of driving cycles that have been developed for the for performance evaluation of conventional vehicles. However, there is a lack of research into driving cycle for EV. Because large differences exist between the drive system and driving charateristics of EV and that of CV, a study on driving cycle for EV should be conducted. In this study, the necessity of an urban driving cycle for the performance evaluation of electric vehicles is confirmed by developing the driving cycle. First, the Gwacheon-city Urban Driving Cycle for Electric Vehicles (GUDC-EV) is developed by using driving data obtained through actual driving experiments and statistical analysis. Second, GUDC-EV is verified by constructing EV simulators and performing simulations that use the actual driving data. The simulation results are then compared against existing urban driving cycles, such as FTP-72, NEDC, and Japan 10–15. These results confirm that GUDC-EV can be used as an urban driving cycle to evaluate the performance of electric vehicles and validate the necessity of development of the driving cycle for electric vehicles.     

Characteristic analysis for cognition of dangerous driving using automobile black boxes

Automobile black boxes are devices that collect information regarding vehicle operation and the driver’s operating situation in the case of a traffic accident. The information collected from the automobile black box, which can also be used during normal driving, can provide information about dangerous driving cognition. This study was designed to analyze characteristics of dangerous driving data and build a dangerous driving cognition system as follows. First, dangerous driving is divided into four types by considering the vehicle’s movement, such as acceleration, deceleration, turning and statistical data of traffic accidents. Second, dangerous driving data were collected by vehicle tests using the automobile black box, and characteristics of the driving data were analyzed to classify dangerous driving. Third, a standard threshold was chosen to recognize dangerous driving, and an algorithm of dangerous driving cognition was created. Finally, verification was conducted by vehicle tests with automobile black boxes embedded with the developed algorithm. The presented recognition methods of dangerous driving can be used for on/off-line management of drivers and vehicles. Scientific traffic accident databases can be built with this driving and accident information, and can be used in various industrial areas.     

In-vehicle display HMI safety evaluation using a driving simulator

Recently, telematics services and in-vehicle display devices such as the CNS (Car Navigation System) have become new causes of traffic accidents. These accidents are caused by ‘Inattention’ from the increase of the driver’s mental workload while he/she is driving. The driver of a vehicle (except for emergency or police vehicles) must not use a hand-held mobile phone while the vehicle is moving. To address this problem, Australia, England, Italy, Brazil and some states in the US have banned the use of hand-held mobile devices during driving. However, there are no restrictions on the use of in-vehicle displays or on the display’s positions. The position of a navigation system in a vehicle should be assessed objectively, and the effect of the position on the driver’s attention should be studied. Some existing research reports that in-vehicle distraction not only leads to reduced speeds and more frequent lane switching, but also more gazing by the driver to the centre of the road. In this study, to develop an assessment method and to propose the proper position of a CNS, an experiment is carried out in a driving simulator environment. Different methods to track the gaze and physical parameters of the driver are used for HMI (Human-Machine Interface) assessment. The experiment is carried out in a driving simulator to observe the glancing distribution during driving according to the position of the navigation system. Fourteen subjects participated in this experiment. Changes in subjects’ physiological signals and glancing distribution rates were collected.     

电动轿车动力系统参数设计和动力性能分析

以某电动轿车研发为对象,对其动力传动系的参数进行匹配设计。基于MATLAB／SIMULINK软件平台建立了整车仿真模型,并应用ADVISOR软件对整车动力性和续驶里程进行了仿真分析。在转鼓试验台上实车测试表明,所设计的动力传动系统能满足设计要求,同时验证了所建立整车模型的准确性。     

Hierarchical map representation using vector maps and geometrical maps for self-localization

Map-based self-localization estimates the pose of the self-driving vehicle in an environment, becoming an essential part of autonomous driving tasks. Generally, maps used in self-localization have detailed geometric information on an environment in formats such as point cloud maps and Gaussian mixture model (GMM) maps. As other maps are widely developed for autonomous driving, vector maps store more object-focused information, such as buildings and road facilities, for navigation and scene understanding in autonomous driving tasks. However, it is not compatible with self-localization due to the lack of detailed geometric information. The two different map formats of vector maps and maps for self-localization complicate the management, preventing the development of the area where a self-driving vehicle can drive stably. This paper proposes a unified map format with a hierarchical structure that enables both vector maps and self-localization maps (i.e., GMM maps) to be managed more easily. Because proposed maps can be treated as vector maps at the high-level layer, various tasks related to navigation and scene understanding in autonomous driving can utilize. A GMM map is stored at the low-level layer associated with a vector map component, enabling accurate self-localization in an environment. The proposed map format is compatible with vector maps widely developed by mapping companies on the surface and facilitates future map management. The experimental results of self-localization in urban areas showed that the proposed map gives the competitive self-localization accuracy compared with the GMM map even with fewer cells that link to vector components. The proposed maps enable self-localization with sufficient accuracy for safe autonomous driving operations.     

基于多属性决策的无人驾驶自主变道决策技术研究

在无人驾驶领域,随着车辆上布置的传感器不断丰富,无人驾驶系统可以从周围环境获得更多的信息,从而为车辆的自主判断行为决策带来可能。然而即使是有经验的驾驶员在进行变道动作的时候也需要格外的小心,因此无人驾驶系统的变道行为分析需要做到足够准确和谨慎,才能保证安全性,这也正是目前为止还没有非常完善的无人驾驶变道决策系统的原因。本文提出一种基于多属性决策的无人驾驶自主变道决策技术,帮助无人驾驶车辆在道路行驶中进行更有效、更安全的自主变道决策。