VIRTUOUS: vision-based road transportation for unmanned operation on urban-like scenarios

This work presents an intelligent transportation system (ITS) that was implemented on an autonomous vehicle designed to perform global navigation missions on a network of unmarked roads. This is the first step toward the complete implementation of ITS in urban environments, which is the long-term goal of this work. Using a global positioning system, global navigation is achieved by means of a global planner and a task manager that recurrently coordinate the execution of vision-based perception tasks for the road tracking of nonstructured roads and the navigation of intersections. In addition, a vision-based vehicle-detection task has been developed, which endows the global navigation system with a reactive capacity. The complete system has been tested on the BABIECA prototype vehicle, which was autonomously driven for hundreds of kilometers around a private circuit, designed to emulate an urban quarter, at speeds of up to 50 km/h, successfully carrying out different navigation missions. During the tests, the vehicle drove itself across crossroads and performed the appropriate turning maneuvers at intersections. It also demonstrated its robustness with regard to shadows, road texture, weather conditions, and changing illumination.     

电池感知的多核系统电压调节策略研究

移动设备的多核处理器应用越来越广泛。以优化电池容量消耗为目标,研究了多核系统的电压调节问题。根据锂电池放电过程可分为线性放电和非线性放电两个阶段的特点,提出的算法包括任务分派、放电阶段判断和空闲时间分配三个部分,其中空闲时间分配将根据电池放电阶段使用不同的分配方式。仿真实验表明,提出的算法节省电池容量消耗的效果和电池放电的非线性程度相关。     

基于车联网平台的分布式能源交易体系

智慧车联网平台是新时代电力、交通与互联网融合的产物,也是泛在电力物联网的重要组成部分,在能源互联网背景下展现出巨大的发展潜力。通过有效利用车联网平台资源促进分布式能源消纳,既可以为车联网平台提供可行的盈利模式,也可以促进我国能源体系转型。文章首先对车联网平台内分布式能源交易架构进行分析。在此基础上针对车联网平台点对点（peer-to-peer,P2P）交易进行研究,提出了一种基于区块链智能合约的分布式能源交易体系。最后,设计了分布式能源交易模式下车联网平台运营模式,主要包括产消者模式、综合能源服务模式和数字化连接模式,可为车联网平台建设分布式能源交易体系提供参考。     

基于MPSoC的轻量化汽车检测系统及硬件加速 平台设计与优化

针对车辆分类检测在精度和实时性方面存在的挑战,提出了一项改进方案,以优化YOLOv5s 模型,旨在实现轻量化 的汽车检测。通过在MPSoC硬件架构的现场可编程门阵列(FPGA) 上设计系统,成功打造了一个具备高精度、快速检测和低 能耗的解决方案。为了使得模型更适合嵌入式设备部署,采用了MobileNetv3 Small 替代YOLOv5s 的主干网络,并引入卷积 块注意力模块(CBAM) 注意力机制和Inner-IoU Loss 优化方法,使模型在轻量化的同时提升了检测精度和速度。改进后的模 型相较于原始Yolov5s模型,平均精度均值(mAP) 提升了14.8%,参数量减少了49.7%,模型体积减小了40.7%,计算量减 少了48.9%,在NVIDIA 3060上,改进后的检测速度提升了48.8%,达到了82 fps。此外,还利用FPGA 对YOLOv5s 进行了 硬件加速。经过优化的系统达到了45fps 的检测帧率,并保持了较高的精度和速度,这一系统易于部署,适用于智能交通系 统,满足其高效实时监测的需求。     

燃料电池在电动汽车中的应用前景

以石油燃料为动力的汽车,其尾气是空气污染的主要来源,以充电电池为动力的电动汽车是解决汽车尾气污染的途径之一.目前,由于充电电池贮能量比内燃机低而使电动汽车数量仍然很少.燃料电池是未来最有希望替代内燃机的汽车动力,它的运行效率高,能够使用甲醇、乙醇、天然气或氢气等非石油基燃料,还可以显著改善排气质量,减少大气污染.可用于电动汽车的燃料电池类型有磷酸型燃料电池、离子交换膜燃料电池和固体氧化物燃料电池.本文对上述燃料电池的原理和性能作了详细介绍,对世界各国的研究开发活动作了介绍.     

计及季节性氢储的新能源汽车供能站分布式规划模型

为了克服电力和交通系统的信息壁垒、改善新能源装置实际利用率低的困境,提出了一种计及季节性氢储的新能源汽车供能站分布式规划模型。首先,提出一种含冬-夏跨季节氢储的供能架构并对配电网、供能站、交通网的运行情况进行建模;接着,以经济性为目标建立电-交联合规划模型;然后,提出一种定制交替方向乘子法(alternating direction multiplier method, ADMM)实现供能系统和交通系统的分布式求解;最后,基于IEEE-33节点配电网和12节点典型交通网验证季节性氢储模型和分布式算法的有效性和先进性,并探讨了多种储能间的协同情况。     

Lightweight type linear induction motor and its characteristics

At the Institute for Posts and Telecommunications Policy, a postal transportation system has been studied. This system would make use of linear induction motor (LIM)-driven vehicles for transporting mail between post offices in the Tokyo Metropolitan area. The system would connect the main post offices in the Tokyo area with tunnels circularly constructed underground and would transport mail with linear induction motor-driven vehicles. In this study, it is found that if vehicle weight is reduced, climbing capability could be considerably improved. Accordingly, the potential for reducing the weight of vehicle-mounted LIMs has been explored, and a prototype lightweight LIM has been manufactured. This paper reports on the lightweight LIM and its characteristics.     

一种新型双激光测速系统的设计与应用

机动车速度检测是现代智能交通系统中的一个重要组成部分。基于激光测距技术,研究了一种新型双激光机动车测速系统。在沿车流方向的两个固定位置各垂直安装一个激光测距传感器,通过测距值的变化检测到有没有车辆通过,根据车辆通过两个激光测距传感器的时间差和传感器的水平间距,可以计算出车辆的行驶速度。同时测距值可以完整地反映出车辆的外形轮廓。该系统主要由事件检测模块、数据协议转换模块以及轮廓检测器模块组成。通过与美国STALKER公司的BASIC型移动式测速仪测试数据进行比对实验,结果表明该系统测量误差在1 km/h之内,具有成本低、测速快和精度高的特点。     

ACC+Stop&go maneuvers with throttle and brake fuzzy control

Research on adaptive cruise control (ACC) with Stop&Go maneuvers is presently one of the most important topics in the field of intelligent transportation systems. The main feature of such controllers is that there is adaptation to a user-preset speed and, if necessary, speed reduction to keep a safe distance from the vehicle ahead in the same lane of the road, whatever the speed. The extreme case is the stop and go operation in which the lead car stops and the vehicle at the rear must also do so. This paper presents the development of an ACC system and related experiments. The system input information is acquired by a real-time kinematic phase differential global positioning system (GPS) (i.e., centimetric GPS) and wireless local area network links. The outputs are the variables that control the pressure on the throttle and brake pedals, which is calculated by an onboard computer. In addition, the car control is based on fuzzy logic. The system has been installed in two mass-produced Citroe/spl uml/n Berlingo electric vans, in which all the actuators have been automated to achieve humanlike driving. The results from real experiments show that the unmanned vehicles behave very similarly to human-driven cars and are very adaptive to any kind of situation at a broad range of speeds, thus raising the safety of the driving and allowing cooperation with manually driven cars.     

Next-Generation Automated Vehicle Location Systems: Positioning at the Lane Level

The majority of today's automated vehicle location (AVL) systems use Global Positioning System (GPS) technology, which can provide position information with an accuracy of approximately 15 m. Recently, low-cost Differential GPS (DGPS) receivers, which have a positioning accuracy of approximate 2-3 m, have become available. With this increased accuracy, it is now possible to perform AVL down to specific roadway lanes. In this paper, a vehicle-lane-determining system is described, consisting of an onboard DGPS receiver that is connected with a wireless communications channel, a unique lane-level digital roadway database, a developed lane-matching algorithm, and a real-time vehicle location display. Lane-level positioning opens up the door for a number of new intelligent transportation system applications such as better fleet management, lane-based traffic measurements from probe vehicles, and lane-level navigation. The developed low-cost system has been tested on a number of roadways and has performed very well when used with accurately surveyed map data. Based on more than 100 000 s, it has correctly determined the lane 97% of the time.     

城市路网中考虑多方影响的电动汽车能耗预测

为加快电动汽车行业低碳发展进程,调整交通运输领域能源组成结构,对于电动汽车能量消耗方面的研究成为当下重点。然而传统物理能耗模型存在参数难以实时获取,缺乏与车辆行驶工况以及交通特性的联系等缺陷。因此,文中首先分析电动汽车能耗与天气因素、社会因素以及路网线路特性等因素的关系,构造连接微观层面平均行驶速度与宏观层面交通状态的能耗预测模型;其次,采用改进的LSTM神经网络对不同行驶工况下电动汽车平均速度进行预测,结合空调附加耗能对单位里程汽车耗电量进行计算。最后,以杭州市交通路网为例,验证了能耗预测模型的准确性,改进的LSTM网络相较传统LSTM网络以及BP网络,均方根误差（RMSE）分别降低了33.2%和40.2%、平均绝对误差（MAE）分别降低了34.8%和41.5%。     

计及灵活性多目标电-热-交通综合能源系统区间优化运行

大量新能源和电动汽车接入后,导致电-热-交通综合能源系统有较大的净负荷变化,需要系统具有一定的灵活性以匹配源荷两侧的不确定性。如何处理不确定性与灵活性的矛盾,以及如何实现经济性和灵活性的平衡,是电-热-交通综合能源系统目前面临的难题。鉴于此,提出一种计及灵活性多目标电-热-交通综合能源系统区间优化运行模型,以经济成本最小和系统灵活性最大为目标,综合平衡系统的经济性和灵活性。利用区间数学描述风电出力和电动汽车负荷的不确定性,将传统等式约束转化为区间表达的形式,使其更具合理性。利用改进的多目标量子免疫算法对优化模型进行求解。以辽北某综合能源系统为例,设定3种不同场景以验证所提方法的有效性。     

基于ZigBee的车联网辅助驾驶平台设计

随着我国汽车保有量的飞速增长,道路拥堵与交通事故问题日益严峻.作为未来智能交通的重要环节,车联网是物联网这一新兴概念在城市交通中的具体应用.提出一种基于ZigBee的车联网辅助驾驶平台的设计,可在车辆与车辆之间、车辆与道路之间进行信息交互,实现车辆异常行为提醒、防碰撞、结合路况的路径规划等功能,提升行车的便捷性,增加车辆间行驶的安全性.该设计实用性强、成本低、可扩展性好,对智能交通的发展与规划具有一定的参考价值.     

Development of a distributed power outage scheduling system by using bee‐gent

The Power Outage Scheduling Problem is a distributed constraint satisfaction problem in which scattered local power stations have to make schedules that are consistent with one another. However, synchronous backtrack algorithms, a well‐known method for distributed constraint satisfaction problems, have difficulty handling rapid schedule adjustments and impartial assignment of power station schedules. Thus, we propose two kinds of heuristics: parallel assignment and multiple priority strategies. We also developed a distributed system for the power outage scheduling problem which makes use of the above heuristics in order to ensure efficiency. The system is based on Bee‐gent (Bonding and Encapsulation Enhancement aGENT framework) and consists of schedulers for each power station and mediation agents which have cloning and merging functions to support the implementation of the heuristics. The result of the experiment shows an improvement when handling rapid adjustment and impartiality issues and indicates that this improvement is provided with reasonable computational overhead. © 2002 Wiley Periodicals, Inc. Electr Eng Jpn, 139(3): 62–72, 2002; Published online in Wiley InterScience ( www.interscience.wiley.com ). DOI 10.1002/eej.1161     

电缆隧道巡检AGV视觉导引技术的研究

路径识别与路径跟踪是AGV（Automated Guided Vehicle）视觉导引技术的两个关键问题。应用迭代法分割路面图像后,使用先闭后开的形态学方法去除图像噪声,然后应用改进的场扫描方法以确定路径在图像中位置。得到车辆的位置参数后,应用模糊控制策略实现路径跟踪。实验表明,该控制算法取得了良好的控制效果。     

微服务架构下配电台区任务云边协同在线调度策略

由电网域向社会服务域延伸的配电网需要支持更多的业务,应用随新业务拓展不断增加可能会导致边设备资源不足。为了从边设备层面支撑资源受限情况下任务的调度与协同处理,提出了微服务架构下配电台区任务云边协同在线调度策略。从任务及设备角度对云边容器化场景下任务调度问题进行了分析,在容器化电力任务云边调度机制基础上,设计了优先级策略与任务分配策略,并通过改进的在线算法对任务进行实时调度。仿真结果表明,所提策略具有更高的任务执行效率,通过资源置换,能够提高边设备资源受限时重要任务的完成率以及系统安全性。     

Design of optimal electromagnets of magnetic-levitation and lateral-stabilization systems for ground transportation based on solving inverse problems

Scientific and technical works on development of transport with magnetic levitation of the vehicle have been reviewed and the main stages of design of such transport have been analyzed. An iterative algorithm for design of the elecFtromagnets used in systems of magnetic levitation and lateral stabilization of high-speed ground transportation has been constructed. The algorithm is based on solving the inverse problems of the theory of an electromagnetic field. Relationships for calculating the initial values of the sought parameters, which are very close to the exact solution, have been suggested. An additional stage of minimizing the electromagnet mass is introduced into the algorithm; as a result, the useful weight of a vehicle can be increased. In addition, the necessary and sufficient conditions for the object of design to have minimal mass were used. An example of implementation of the algorithm during design of a levitation electromagnet has been considered. The influence of eddy currents induced in the ferromagnetic rail during movement of a vehicle on the levitation force has been determined. A coefficient that allows one to take into account this effect has been determined. To justify the formula for calculations of a ferrorail width, the dependences of levitation-force components that arise upon shifting the electromagnet in respect to the ferrorail axis have been obtained. The results of investigations show that the methodology based on solving the inverse problems in designing electromagnets of levitation and lateral-stabilization systems is highly efficient. The proposed algorithm for optimal design of the electromagnets can be used in the design of similar devices in electric-instrument engineering.     

电动车用MH/Ni电池快速充电系统

为了解决电动车用MH/Ni电池的快速充电问题,提出了充电终止的方法.在充电过程中对电池组的多个参数进行实时监测,通过参数运算和逻辑判断,控制充电过程的结束;采用充电去极化放电脉冲提高充电效率.快速充电系统的数据采集精度高于0.5%.自动导引车车栽24 V/90 Ah电池组的应用表明,60 d后电池的SOC从70.0%降至69.4%.     

一种暂态稳定并行仿真的改进算法及其加速比分析

提出了一种基于因子路径树网络划分的暂态稳定空间并行仿真的改进算法。采用新的网络划分性能评价指标、任务划分后续调整策略进行任务划分,使各处理器间计算负荷的分配更为合理;同时,还提出了该算法在理想状况下加速比的计算公式,分析了影响并行仿真计算效率的各个因素,并以某3872节点系统为例介绍了一种估计实现最大加速比所需处理器数目的方法。在Cluster1350集群系统上的算例表明,所提改进算法提高了仿真效率。     

基于机器视觉的岩屑自动拣选系统设计

为解决混合岩屑样品颗粒细小条件下,人工拣选含油岩屑工作效率低的问题,研究设计了岩屑自动拣选系统。系统以含油岩屑在紫外光照射条件下发射荧光的特性为基础,以机器视觉技术为支撑,辅以岩屑输送和归整装置,实现含油岩屑的识别和定位;以电磁阀组、气源以及控制板构成气动执行机构,实现含油岩屑的自动拣选。实验表明,系统对含油岩屑识别准确率100%,定位和拣选可靠,误选率为0。为改变传统的拣选方式,提高工作效率提供了新途径。