Driving Pattern Recognition for Control of Hybrid Electric Trucks

The design procedure for an adaptive power management control strategy, based on a driving pattern recognition algorithm is proposed. The design goal of the control strategy is to minimize fuel consumption and engine-out NOx and PM emissions on a set of diversified driving schedules. Six representative driving patterns (RDP) are designed to represent different driving scenarios. For each RDP, the Dynamic Programming (DP) technique is used to find the global optimal control actions. Implementable, sub-optimal control algorithms are then extracted by analyzing the behavior of the DP control actions. A driving pattern recognition (DPR) algorithm is subsequently developed and used to classify the current driving pattern into one of the RDPs; thus, the most appropriate control algorithm is selected adaptively. This 'multi-mode' control scheme was tested on several driving cycles and was found to work satisfactorily.     

并联混合动力汽车ECMS的时变等效因子提取算法的研究

为解决当前等效燃油消耗最小控制策略(ECMS)未能根据实际工况选取最优等效因子的问题,利用动态规划算法(DP)和ECMS各自的优点,构建并联混合动力汽车能量算法模型,即采用动态规划算法的等效燃油消耗最小控制策略(ECMSwDP),将等效因子作为全局最优算法的控制变量,通过对等效因子的离散全局优化,获得基于工况的最佳时变等效因子。在标准工况下对时变等效因子实时控制策略与全局最优控制策略DP的各项性能参数进行了数值仿真,验证了时变等效因子提取算法的有效性和等效因子初始值选取方法的可行性。     

混合动力汽车整车控制器开发和试验研究

以ISG(起动机/发电机一体化)混合动力汽车为对象,对车辆转矩需求、发动机工作区优化和整车控制策略进行了分析,开发了基于MC9S12DP256的整车控制器硬软件系统,并进行了实车试验,实现了发动机起动、纯发动机驱动、混合驱动、驻车充电等多种工作模式,证明了该整车控制器功能设计的合理性和控制策略设计的有效性.     

Human driving data-based design of a vehicle adaptive cruise control algorithm

This paper presents a vehicle adaptive cruise control algorithm design with human factors considerations. Adaptive cruise control (ACC) systems should be acceptable to drivers. In order to be acceptable to drivers, the ACC systems need to be designed based on the analysis of human driver driving behaviour. Manual driving characteristics are investigated using real-world driving test data. The goal of the control algorithm is to achieve naturalistic behaviour of the controlled vehicle that would feel natural to the human driver in normal driving situations and to achieve safe vehicle behaviour in severe braking situations in which large decelerations are necessary. A non-dimensional warning index and inverse time-to-collision are used to evaluate driving situations. A confusion matrix method based on natural driving data sets was used to tune control parameters in the proposed ACC system. Using a simulation and a validated vehicle simulator, vehicle following characteristics of the controlled vehicle are compared with real-world manual driving radar sensor data. It is shown that the proposed control strategy can provide with natural following performance similar to human manual driving in both high speed driving and low speed stop-and-go situations and can prevent the vehicle-to-vehicle distance from dropping to an unsafe level in a variety of driving conditions.     

基于小波和粒子群算法的HEV行驶状况辨识方法研究

针对混合动力汽车(HEV)行驶状况(道路坡度和整车载荷)变化难以有效识别,导致驱动系统控制策略不能有效满足驾驶员意图问题,以混联式HEV为研究对象,提出了基于小波滤波和粒子群算法的HEV行驶状况辨识方法。首先建立了汽车行驶状况辨识模型,采用最小二乘法确立了优化目标函数,其次研究了基于小波滤波和粒子群算法的HEV行驶状况辨识原理,最后进行了行驶状况粒子群智能算法辨识试验。在采集实车数据的基础上,对实车数据进行小波滤波,并运用行驶状况辨识方法对道路坡度和整车载荷进行了辨识,并对辨识结果进行小波滤波,结果表明,试验工况下整车载荷辨识的相对误差绝对平均值为2.71%,道路坡度辨识的相对误差绝对平均值为3.85%,验证了所提出方法的有效性。     

单轴并联式混合动力总成的设计

设计完成了驱动电机与电控共轨柴油机结合而成的混合动力汽车动力总成,该总成用于单轴并联式混合动力汽车。驱动电机既是电驱动装置,又是起动、发电一体化系统(ISG),基于MC 68H9S12DP256B单片机,研制了该总成的控制系统,通过CAN总线实现了联合控制,以电池充放电平衡和发动机燃油经济性为基础,应用了一种模糊逻辑控制策略,实现了混合动力系统的扭矩分配与不同工作模式以及模式间的切换,该总成能够在所要求的工作模式下运转。     

Economic value and utility of a powertrain system for a plug-in parallel diesel hybrid electric bus

This research is the first to develop a design for a powertain system of a plug-in parallel diesel hybrid electric bus equipped with a continuously variable transmission (CVT) and presents a new design paradigm of the plug-in hybrid electric bus (HEB). The criteria and method for selecting and sizing powertrain components equipped in the plug-in HEB are presented. The plug-in HEB is designed to overcome the vulnerable limitations of driving range and performance of a purely electric vehicle (EV) and to improve fuel economy and exhaust emissions of conventional bus and conventional HEBs. The control strategy of the complicated connected propulsion system in the plug-in parallel HEB is one of the most significant factors in achieving higher fuel economy and lower exhaust emissions of the HEV. In this research, a new optimal control strategy concept is proposed against existing rule-based control strategies. The optimal powertrain control strategy is obtained through two steps of optimizations: tradeoff optimization for emission control and energy flow optimization based on the instantaneous optimization technique. The proposed powertrain control strategy has the flexibility to adapt to battery SOC, exhaust emission amount, classified driving pattern, driving condition, and engine temperature. The objective of the optimal control strategy is to optimize the fuel consumption, electricity use, and exhaust emissions proper to the performance targets. The proposed control strategy was simulated to prove its validity by using analysis simulation tool ADVISOR (advanced vehicle simulator).     

基于行为融合的无人自动驾驶车辆的智能控制

针对动态环境下无人自动驾驶车辆控制的非线性、时变的特点,提出并设计了一种基于行为融合的无人驾驶车辆的智能控制策略。根据车辆行驶基于模糊逻辑方法设计了一系列的基本行为模式,用模糊控制的方法分别建立各行为模式控制器,进而对车辆的方向和速度进行控制。在行为选择机制设计中,对常用的行为竞争和行为融合2种方法进行分析比较后,提出限制各行为模式的使用范围,通过各行为的控制和融合,既达到有效避障,又能完成行驶目标的目的。通过几种典型障碍物环境下的避障仿真实验,结果显示设计达到了预期效果。     

基于神经网络的智能驾驶模式识别研究

为满足智能驾驶汽车高级驾驶辅助系统(ADAS)功能研发和验证的需求,提高ADAS功能的准确性,设计了一款基于神经网络的智能驾驶模式识别程序,该程序由数据采集、目标检测、场景识别预测3个模块组成.数据采集模块利用ESR毫米波雷达、前置摄像头对交通环境及周围车辆的数据信息进行采集;目标监测模块通过控制算法选择判断触发各类A...     

模拟驾驶环境下驾驶人分心状态判别

为了探寻驾驶人分心判别方法,构建了驾驶人分心状态判别模型。首先设计分心模拟驾驶试验,采集正常驾驶和发送语音信息过程中的驾驶绩效特征和驾驶人眼动特征数据,建立驾驶人分心状态判别指标备选集;其次,采用基因选择算法对备选指标进行筛选,得到29个备选指标的重要度排序;然后,依次选取重要度较高的部分指标作为BP神经网络的输入指标,利用遗传算法（GA）全局搜索的性能优化BP神经网络的初始权值和阈值,将优化后的GA-BP神经网络作为弱分类器,再将多个弱分类器组合成Adaboost强分类器,建立基于Adaboost-GA-BP组合算法的驾驶人分心状态判别模型;最后,利用模拟驾驶器试验平台采集的数据计算不同判别指标数量下模型的性能,从而确定最优判别指标,并对模型进行验证和评价。结果表明：模型最优判别指标为重要度排序中前14个指标;模型能够准确识别驾驶人分心状态,判别精度为95.09%;与BP神经网络算法、GA-BP神经网络算法和Adaboost-BP神经网络算法相比,Adaboost-GA-BP组合算法在准确率、精准率、召回率、F₁值和ROC曲线等模型性能方面均最优。建立的模型能够有效判别驾驶人分心状态,可为驾驶人分心预警系统和分心控制策略提供依据。     

商用车电液复合转向系统的车道保持策略

为了提高商用车的行驶安全性,避免因驾驶人的分心驾驶出现车辆偏离车道的问题,提出一种基于电液复合转向系统的商用车车道保持策略;在建立电液复合转向系统模型、二自由度车辆模型、预瞄驾驶人模型的基础上,设计基于驾驶人在环的MPC和ADRC串级的车道保持控制策略。首先,采用MPC算法将车辆横向位置控制的最优问题转化为二次规划求得目标前轮转角;然后,考虑电液复合转向系统的不确定和干扰问题,利用ADRC算法对目标转向盘转角和实际驾驶人的转向盘转角差值以转矩信号的形式进行补偿。同时研究车道保持系统对驾驶人的干预问题,引入干预系数的概念,采用模糊控制的方法,将驾驶人手力和车辆的运动状态作为输入变量,干预系数作为输出变量,保证整车行驶安全性的前提下减小车道保持辅助系统对驾驶人的干预。最后,通过MATLAB/Simulink仿真和硬件在环试验对所设计的控制策略进行验证。研究结果表明：所设计的基于商用车电液复合转向系统的车道保持策略能够及时地纠正因驾驶人的分心驾驶而导致车辆偏离所在行驶车道的行为,特别是在弯道处出现驾驶人转向不足或过度转向的情况时,能够将车辆维持在车道线之内,保证车辆的行驶安全性,同时由于干预系数的设计,使得驾驶人也有良好的人机交互体验感。     

直喷汽油机电控喷油系统的开发研究

开发了汽油直喷发动机电控喷油系统,选取飞思卡尔MC9S12DP512MPVE单片机作为发动机ECU的主控芯片,设计了喷油驱动电路模块,制订了不同工况下喷油控制策略.发动机试验证明,该电控喷油系统能提供不同工况所需喷射压力,符合设计的喷油控制策略,能够可靠保证发动机的喷油性能要求.     

Energy recovery based on pedal situation for regenerative braking system of electric vehicle

ABSTRACT

Energy recovery is a key technology to improve energy efficiency and extend driving range of electric vehicle. It is still a challenging issue to maximise energy recovery. We present an energy recovery mode (mode A) which recovers braking energy under all situations that accelerator pedal (AP) is lifted, brake pedal (BP) is depressed, as well as AP and BP are released completely; and propose a control strategy of regenerative braking based on driver's intention identified by a fuzzy recognition method. Other two modes: (1) recovery braking energy only the BP is depressed (mode B), (2) no energy recovery, have been studied to compare with mode A. Simulations are carried out on different adhesion conditions. Recovered energy and driving range are also obtained under FTP75 driving cycle. Road test is implemented to validate simulation results. Results show that mode A can improve energy recovery by almost 15.8% compared with mode B, and extend driving range by almost 8.81% compared with mode B and 20.39% with the mode of no energy recovery; the control strategy of regenerative braking can balance energy recovery and braking stability. The proposed energy recovery mode provides a possibility to achieve a single-pedal design of the electric vehicle.     

Fuzzy energy management strategy for a hybrid electric vehicle based on driving cycle recognition

By considering the effect of the driving cycle on the energy management strategy (EMS), a fuzzy EMS based on driving cycle recognition is proposed to improve the fuel economy of a parallel hybrid electric vehicle. The EMS is composed of driving cycle recognition and a fuzzy torque distribution controller. The current driving cycle is recognized by learning vector quantization in driving cycle recognition. The torque of the engine and the motor is controlled by a fuzzy torque distribution controller based on the required torque of the hybrid powertrain and the battery state of charge. The membership functions and rules of the fuzzy torque distribution controller are optimized simultaneously by using particle swarm optimization. Based on the identification results of driving cycle recognition, the fuzzy torque distribution controller selects the corresponding membership function and rule to control the hybrid powertrain. The simulation research based on ADVISOR demonstrates that this EMS improves fuel economy more effectively than fuzzy EMS without driving cycle recognition.     

基于轨迹数据的危险驾驶行为识别方法

连续的跟驰行为和换道行为是驾驶行为的主要构成部分,对交通拥挤和交通事故有着重要影响。通过无人机视频拍摄和图像处理方式,提取了曹安公路沿线的2个交叉路口间正常交通流状态下共600条多车高精度轨迹数据。首先,考虑车辆类型对驾驶行为产生直接的影响,分析了大车和小车的车辆轨迹特征变量分布的差异性,包括速度、加速度、碰撞时间倒数、车头时距等,在标记危险驾驶行为的过程中考虑车辆类型的影响。其次,针对不同的车辆类型,利用修正碰撞裕度对跟驰行为和换道行为进行风险性评估,将其划分为安全型和风险型。根据风险型行为发生的顺序以及持续时间,评估驾驶人的整体驾驶状态是否危险,作为危险驾驶行为识别的样本标记。分别利用离散小波变换和统计方法提取车辆轨迹的关键特征参数,为了提高模型识别效率,将关键特征参数进行排序,从而确定最优判别指标;最后,利用轻量梯度提升机（LGBM）算法对危险驾驶行为进行识别,并与随机森林、多层感知器、支持向量机等算法在精度上进行比较。研究结果表明：在上述研究条件下,LGBM算法对危险驾驶行为的理论识别率最高可达93.62%,可以实现基于机器学习算法的危险驾驶行为的高精度自动识别,该结果对于智能驾驶辅助系统的设计、道路交通安全决策的制定具有显著的意义。     

基于车辆状态识别的AFS与ESP协调控制研究

给出了基于滑模变结构的AFS控制策略和直接横摆力矩加变滑移率联合控制的ESP控制策略。在分析两者控制性能的基础上提出了协调控制的一般原则。阐述了车辆状态识别算法并给出了具体的协调控制策略,最后通过3个典型工况的仿真计算验证了该协调控制策略的有效性。     

基于模糊自适应PID的客车电控空气悬架车高调节控制策略研究

电控空气悬架能够根据客车行驶工况进行车身高度自适应调节,从而能够显著提升客车行驶稳定性以及燃油经济性,车高调节控制设计具有重要意义。文章利用模糊PID控制算法对车身高度调节进行控制策略设计,有效缓解了客车电控空气悬架车高调节过程中存在的空气弹簧的“过充”“过放”及“振荡”等问题,分析客车电控空气悬架车高调节具体过程,建立包括车身、储气罐、电磁阀以及空气弹簧等在内的车高调节系统数学模型,最后完成了客车电控空气悬架车高调节模糊自适应PID控制策略设计及性能仿真验证。研究结果表明,所运用的模糊自适应PID控制策略能够完成客车电控空气悬架车身高度的准确调节。     

Novel stability control strategy for distributed drive electric vehicle based on driver operation intention

In this paper, a novel direct yaw control method based on driver operation intention for stability control of a distributed drive electric vehicle is proposed. It was discovered that the vehicle loses its stability easily under an emergency steering alignment (EA) problem. An emergent control algorithm is proposed to improve vehicle stability under such a condition. A driver operation intention recognition module is developed to identify the driving conditions. When the vehicle enters into an EA condition, the module can quickly identify it and transfer the control method from normal direct yaw control to emergency control. Two control algorithms are designed. The emergency control algorithm is applied to an EA condition while the adaptive control algorithm is applied to other conditions except the EA condition. Both simulation results and real vehicle results show that: The driver module can accurately identify driving conditions based on driver operation intention. When the vehicle enters into EA condition, the emergent control algorithm can intervene quickly, and it has proven to outperform normal direct yaw control for better stabilization of vehicles.     

基于多分类监督学习的驾驶风格特征指标筛选

交通事故与驾驶风格具有强烈的相关性,而驾驶风格的直观体现是驾驶行为.为深入分析驾驶行为与驾驶风格的关联性,探索不同驾驶风格群体之间的差异,筛选驾驶风格分类与识别影响因素,建立驾驶风格识别模型并验证有效性.依托车联网实验数据,利用K-means++算法对驾驶员样本数据集进行驾驶风格聚类,设计支持向量机-递归特征消除(SV...     

From Offline to Adaptive Online Energy Management Strategy of Hybrid Vehicle Using Pontryagin’s Minimum Principle

This paper details the development of an energy management strategy (EMS) for real-time control of a multi hybrid plug-in electric bus. The energy management problem has been formulated as an optimal control problem in order to minimize the fuel consumption of the bus drivetrain for a typical day of operation. Considering the physical characteristics of the studied hybrid electric bus and its well-known daily tour, the Pontryagin’s minimum principle (PMP) is firstly used as the mean to obtain offline optimal EMS. Afterward, in order to adapt the proposed strategy for real-time implementation, the proposed control parameters are adapted online using feedback from the battery state of energy (SOE) which allows us to accurately control the battery SOE in the presence of wide range of uncertainties. The work proposed in this paper is conducted on a dedicated high-fidelity dynamical model of the hybrid bus, that was developed on MATLAB/TruckMaker software. The performance evaluation of the proposed strategy is carried out using a normalized driving cycles to represent different driving scenarios. Obtained results show that among the investigated methods, it is reasonable to conclude that the proposed adaptive online strategy based on PMP is the most suitable to design the targeted EMS.