基于变车头时距的汽车自适应巡航系统设计

距离模型和控制算法是汽车自适应巡航系统（Adaptive Cruise Control,ACC）设计的关键。采用分层式控制方法设计ACC系统控制策略。设计上层控制器,基于多行车因素影响设计变车头时距模型,利用状态机搭建模式切换策略,同时设计一种车距-速度串联式PID控制策略求取期望加速度;依靠下层控制器,计算节气门开度/制动压力并输入到CarSim中控制执行器,从而使整个系统实现闭环控制。通过CarSim/Simulink建立联合仿真模型,在多种工况下对模型进行验证。仿真结果表明,改进的变车头时距模型与其他模型相比具有一定优势,所设计ACC系统在多种工况下能够实现稳定的定速巡航和前车跟随功能,保证汽车行驶安全性。     

基于神经网络的列车自动驾驶控制算法研究

对列车自动驾驶系统的速度控制过程进行了分析,针对传统PID算法缺乏自适应能力的缺点,在传统神经网络算法的基础之上对神经元的学习算法作出改进,设计出了基于RBF网络辨识的单神经元自适应PID控制器,仿真结果表明该控制器能够满足列车自动驾驶系统速度控制要求。     

基于模型预测控制的无人驾驶车辆纵向跟车控制研究

为提升自适应巡航系统(adaptive cruise control, ACC)在纵向跟车工况下的安全性及乘车舒适性,基于模型预测控制(model predictive control, MPC)设计了面向无人驾驶车辆的跟车控制器,并在Matlab/Carsim联合仿真平台中搭建仿真模型,对该控制器在纵向跟车工况下的有效性进行验证,仿真结果表明：基于MPC的控制器可以使车辆在纵向跟车工况下实现稳定速度跟随并保持安全车距,同时车辆的实际加速度与期望加速度一致,能够保持在舒适范围内。     

基于V-结构&对数似然函数定向与禁忌爬山的贝叶斯网络结构算法

针对爬山算法搜索空间过大和易陷入局部最优的问题,该文提出基于V-结构&对数似然函数定向与禁忌爬山的贝叶斯网络结构算法(VTH).该算法利用定向最大支撑树约束搜索空间,在最大支撑树定向过程中,提出V-结构与对数似然函数(VLL)结合的定向策略;在评分搜索过程中,提出禁忌爬山(VTH)评分搜索策略,该策略将禁忌表清空机制与爬山搜索的局部择优准则结合,在提高全局寻优能力的同时也能保证搜索效率.该算法与其他算法在Asia,Car,Child和Alarm 4种标准网络中进行仿真实验,对比汉明距离、F1值、平衡评分函数(BSF)值、运行时间4个指标,验证了该算法的有效性.     

基于V-结构&对数似然函数定向与禁忌爬山的贝叶斯网络结构算法

针对爬山算法搜索空间过大和易陷入局部最优的问题,该文提出基于V-结构&对数似然函数定向与禁忌爬山的贝叶斯网络结构算法(VTH)。该算法利用定向最大支撑树约束搜索空间,在最大支撑树定向过程中,提出V-结构与对数似然函数(VLL)结合的定向策略;在评分搜索过程中,提出禁忌爬山(VTH)评分搜索策略,该策略将禁忌表清空机制与爬山搜索的局部择优准则结合,在提高全局寻优能力的同时也能保证搜索效率。该算法与其他算法在Asia, Car, Child和Alarm 4种标准网络中进行仿真实验,对比汉明距离、F1值、平衡评分函数(BSF)值、运行时间4个指标,验证了该算法的有效性。     

基于CBOC信号的导航接收机设计与实现

对BOC及其衍生信号CBOC(6,1,1/11)的时域频域特性进行分析和在Matlab环境下进行了仿真。根据仿真的信号特性,对已有的跟踪算法进行的分析和比较。基于工程实现和算法性能,选择了多相关器结构的算法(S-curveshaping方法),并根据此算法设计在原有接收机结构上进行改进,设计出了基于CBOC(6,1,1/11)接收机结构。最终对设计的接收机结构进行了硬件上的实现,完成了原理样机的制作。     

一种基于信息素的蚁群聚类算法

提出了一种改进的蚁群聚类分析算法,通过改进LF算法中群体相似度函数,加入参数的自适应调整策略,利用短期记忆和网格信息素的局部分布控制蚂蚁的随机移动,并结合蚂蚁速度动态变化、半径递增、强制放下等特性。采用测试数据和不同的算法进行了对比实验分析,仿真实验结果表明,该算法显示出了较高的稳定性和准确率。     

自适应策略在实数编码遗传算法中的应用研究

为解决简单遗传算法收敛速度慢以及局部收敛问题,在研究自适应策略的基础上,提出了一种基于实数编码,综合精英保留策略、2/4竞争选择策略和自适应策略的改进遗传算法.该改进算法将自适应策略及其在遗传算法中的应用方法做了改进,仿真实验证明,该算法可以提高收敛速度,有效实现全局最优化.     

基于零均值特性的改进G-SVSLMS算法

为解决改进的基于Sigmoid函数变步长最小均方(G-SVSLMS)算法步长更新公式易受噪声干扰的问题,根据高斯白噪声的零均值特性,对G-SVSLMS算法进行改进,提出基于零均值特性的改进G-SVSLMS算法,使算法的抗噪声干扰能力明显增强。理论分析和仿真结果表明:若两算法选取相同参数α、β,则基于零均值特性的改进G-SVSLMS算法相对于G-SVSLMS算法具有小的稳态误差;在保证算法收敛的条件下,基于零均值特性的改进G-SVSLMS算法相对于G-SVSLMS算法具有较快的收敛速度。     

基于自适应状态转移集合的多帧积累检测DP-TBD算法北大核心CSCD

针对机动目标在多帧积累检测算法中存在的问题展开讨论与研究,提出了基于自适应状态转移集合的多帧积累检测与跟踪算法,并设计了相应的仿真实验验证算法的有效性。针对目标机动性较强时算法性能严重下降的问题,详细介绍相应的改进策略,使用当前统计模型提高对机动目标的适应能力。利用值函数积累过程中的目标预测路径实时估计目标的转移加速度并进行加速度约束,有效地减小目标状态的搜索空间。通过转移加速度在时间维上的相关性结合当前统计模型,自适应地调整目标状态转移集合的范围,进而减少目标搜索空间内的干扰信息,提高算法的检测精度与计算效率。利用不同机动目标场景,仿真结果证明所提改进算法具有更好的检测与跟踪性能。     

A new strategy for traction control in turning via engine modeling

The driving stability is affected by driven wheel slip, which can be controlled by the driven wheel torque. In a vehicle powered by an internal combustion engine, the torque can be controlled by an engine management system. The sliding mode algorithm is the mechanism behind the design of the traction control system (TCS). The longitudinal slip is controlled by the position of the throttle valve. The vehicle model used has seven degrees of freedom and a two-state engine model, i.e., the mass of air in the intake manifold and the engine speed. Time-delay transport is considered in the engine model used. A nonlinear tire model for combined slip is used for tire force computation. Due to the nonlinear dynamic of the tire, vehicle, and engine, the control method of sliding mode is used for its robustness. A controller is designed based on the dynamic surface control, for which two first-order surfaces are defined. The effectiveness of the controller is demonstrated with simulation results for different maneuvers. Results show that for different road conditions, the acceleration performance, directional stability, and steerability of a vehicle equipped with TCS is improved. The reason is that the slip is controlled by keeping it in a desired range     

纯电动中型客车动力系统参数匹配及性能研究

针对现有车辆改装技术缺乏相应的参数匹配研究及动力学仿真分析,提出利用参数匹配和动力学分析研究汽车改制的方法,该方法以“LS6600C1”型普通中型客车改装的纯电动试验车为研究对象,对动力系统进行参数匹配设计,并利用电动汽车仿真软件ADVISOR建立相应的纯电动汽车动力系统及整车仿真模型,对整车模型的最高车速、加速能力、爬坡性能和续驶里程等指标进行了仿真研究。结果表明,典型工况下改装后的纯电动试验车续驶里程、最高车速、加速性能和爬坡性能等均满足普通中型客车的运行要求和使用条件,该改装技术具有广泛的应用前景。     

An ANFIS controller for the car-following collision preventionsystem

This paper presents a controller based on an adaptive network fuzzy inference system (ANFIS) for the car-following collision prevention system to nonlinearly control the speed of the vehicle. The distance and speed relative to the car in front are measured by a radar sensor and applied to the controller. The output acceleration or deceleration rate of the controller is based on the characteristics of the vehicles. The initial input and output membership functions and 25 rules of ANFIS are constructed by a fuzzy inference system (FIS). The design method of the reference signals, which is used to update on-line the consequent parameters of ANFIS according to recursive least square (RLS) algorithm, are proposed. The presented ANFIS controller can solve the problems of the oscillations for final distance between the leading vehicle (LV) and the following vehicle (FV) and relative speed. The required processing time to achieve safe distance between the LV and the FV is about 7-8 s, which is faster than the other models. The ANFIS controller of the car-following collision prevention system proposed in this paper can provide a safe, reasonable, and comfortable drive     

Novel motors and controllers for high-performance electric vehiclewith four in-wheel motors

We have, in accordance with new concepts, undertaken the development of a high-performance electric motor vehicle, designated as the IZA. The main performance features of the IZA are a maximum speed of 176 km/h, a range of 548 km per charge at a constant speed of 30 km/h, and acceleration from 0 to 400 m in 18 s. We have developed a direct driving in-wheel motor and controller in order to achieve high performance characteristics. The in-wheel motor is composed of an outer rotor with a rare earth permanent magnet (Sm-Co) and an inner stator. The motor drive controller consists of a three-phase inverter and a microprocessor-based controller. The maximum output and maximum torque of each total drive system, including motor and inverter, are 25 kW and 42.5 kg·m, respectively, and the total efficiency of the drive system is over 90% at the rated speed. The performance of the motor, controller, and drive system have been confirmed by numerous simplex and vehicle transit tests. This paper describes the design concepts, configuration, and performance of the motor, controller, and drive system developed for this high-performance electric vehicle     

基于深度强化学习的端到端无人驾驶决策

端到端的驾驶决策是无人驾驶领域的研究热点.本文基于DDPG（Deep Deterministic Policy Gradient）的深度强化学习算法对连续型动作输出的端到端驾驶决策展开研究.首先建立基于DDPG算法的端到端决策控制模型,模型根据连续获取的感知信息（如车辆转角,车辆速度,道路距离等）作为输入状态,输出车辆驾驶动作（加速,刹车,转向）的连续型控制量.然后在TORCS（The Open Racing Car Simulator）平台下不同的行驶环境中进行训练并验证,结果表明该模型可以实现端到端的无人驾驶决策.最后与离散型动作输出的DQN（Deep Q-learning Network）模型进行对比分析,实验结果表明DDPG决策模型具有更优越的决策控制效果.     

Modeling, Analysis, and Neural Network Control of an EV Electrical Differential

This paper presents system modeling, analysis, and simulation of an electric vehicle (EV) with two independent rear wheel drives. The traction control system is designed to guarantee the EV dynamics and stability when there are no differential gears. Using two in-wheel electric motors makes it possible to have torque and speed control in each wheel. This control level improves EV stability and safety. The proposed traction control system uses the vehicle speed, which is different from wheel speed characterized by a slip in the driving mode, as an input. In this case, a generalized neural network algorithm is proposed to estimate the vehicle speed. The analysis and simulations lead to the conclusion that the proposed system is feasible. Simulation results on a test vehicle propelled by two 37-kW induction motors showed that the proposed control approach operates satisfactorily.     

Location prediction algorithm for a nonlinear vehicular movement in VANET using extended Kalman filter

Vehicular ad-hoc network (VANET) is an essential component of the intelligent transportation system, that facilitates the road transportation by giving a prior alert on traffic condition, collision detection warning, automatic parking and cruise control using vehicle to vehicle (V2V) and vehicle to roadside unit (V2R) communication. The accuracy of location prediction of the vehicle is a prime concern in VANET which enhances the application performance such as automatic parking, cooperative driving, routing etc. to give some examples. Generally, in a developed country, vehicle speed varies between 0 and 60 km/h in a city due to traffic rules, driving skills and traffic density. Likewise, the movement of the vehicle with steady speed is highly impractical. Subsequently, the relationship between time and speed to reach the destination is nonlinear. With reference to the previous work on location prediction in VANET, nonlinear movement of the vehicle was not considered. Thus, a location prediction algorithm should be designed by considering nonlinear movement. This paper proposes a location prediction algorithm for a nonlinear vehicular movement using extended Kalman filter (EKF). EKF is more appropriate contrasted with the Kalman filter (KF), as it is designed to work with the nonlinear system. The proposed prediction algorithm performance is measured with the real and model based mobility traces for the city and highway scenarios. Also, EKF based prediction performance is compared with KF based prediction on average Euclidean distance error (AEDE), distance error (DE), root mean square error (RMSE) and velocity error (VE).     

Compensation of axle-generator errors due to wheel slip and slide

Significant errors of train axle generators (tachometers) are due to wheel slip and slide. An algorithm is designed to compensate for these errors. The algorithm identifies the wheel slip and slide by examining the variation of the processed vehicle longitudinal acceleration. Whenever wheel slip/slide is identified, then the vehicle speed is adjusted if a certain condition is met. The adjustment is a simple linear interpolation between the two speed values recorded before and after wheel slip/slide detection. In addition, a speed and acceleration observer using a Kalman filter is implemented. Experimental results using three different axle encoders aboard a freight train are provided to illustrate the performance of the proposed algorithm     

基于VC++的汽车语音驾驶助手的设计与实现

在VC++的编程环境下设计了一个小词汇量孤立词非特定人的汽车语音识别系统,系统中的识别词汇都是汽车驾驶员在驾驶过程中可能做的一些手控操作.语音预处理采用的是改进后的端点检测算法.实验分析时,在测试数据中加入噪声库(NoiseX-92)中的车内噪声来模拟汽车驾驶环境,并提出随机映射梅尔频率倒谱系数来增强噪声环境下系统的鲁棒性.测试数据表明,使用随机映射特征参数使得系统的抗噪声能力得到了很大的提升.     

基于Kalman预测的四轮转向状态估计算法

针对车辆运动状态测量存在的成本高、难度大问题,提出了一种基于Kalman预测技术的车辆状态估计算法,该估计算法以线性二自由度的车辆模型为基础,对四轮转向过程中车辆横摆角速度、车辆侧向加速度分别进行估计,并与实测结果对比分析,结果表明,Kalman预测算法能准确估计四轮转向时车辆的横摆角速度、侧向加速度,并结合车速信息对4WS转向车辆采用低速时,前后轮采用反向转向、高速时前后轮采用同向转向的控制策略,以实现汽车低速行驶的机动性和高速行驶的操作稳定性。