针对自适应巡航的驾驶人风格辨识

车辆进入自适应巡航工况下行驶时,不同风格的驾驶人会对自适应巡航控制系统(Adaptive Cruise Control,ACC)有不同的需求。文章首先通过对不同驾驶人在9种跟随试验下获取的实验数据分析,选取表征驾驶人风格的驾驶特征参数;其次对所有驾驶人驾驶特征参数利用K-mean算法聚类分析,将驾驶人三类,并利用BP神经网络建立辨识模型对驾驶人风格进行辨识。结果表明;文章提出的方法可以较高的准确率对驾驶人风格进行分类,提高自适应巡航系统适应驾驶人的能力。     

基于便携式排放测试系统与BP神经网络的大型客车排放预测

以大型客车为研究对象,在长沙市的不同道路工况下进行了车载排放测试,借助道路测试得到的数据,利用BP神经网络,以逐秒的速度、加速度、比功率和油耗数据为输入,建立CO2、CO和NOx的排放预测模型,并用部分试验数据进行了验证.结果表明,CO2、CO和NOx预测结果的总体相关系数R为0.9167,线性高度相关,在整体误差水平...     

基于神经网络的安全航速的计算

对安全航速影响因素进行量化,借助神经网络,预测在当时海上航行条件下,舰船应该采用的安全航速,给出基于神经网络的安全航速计算模型,对船舶海上航行安全有一定的指导作用.     

基于有限元和神经网络的主动加热红外无损测厚技术

提出了通过对平板进行单面主动加热,根据平板的热响应测厚的红外无损测厚技术．使用有限元数值计算,得到了不同厚度、加热热流、加热温度、加热区域形状、加热面积下的碳钢平板热响应．使用BP神经网络(NN)建立了热响应与板厚之间的非线性映射,神经网络的训练和测试表明该方法具有较高的精度和较好的推广性．实际应用中可使用红外热像仪记录平板表面的热响应．提出的红外无损测厚技术具有单向性、不接触等优势,具有良好的应用前景．     

基于神经网络的感应电动机特性辨识新方法

提出并论证了一种基于神经网络的感应电动机特性辨识新方法,只需测得电机两相电流数值便可以辨识出电动机转矩和转速,用改进的Levenberg-Marquardt算法对神经网络进行学习和训练,构建了适合电动机转矩转速观测的BP神经网络。由于RBF神经网络无论是在逼近能力、函数拟合和学习速度方面都优于BP网络,也利用RBF网络进行了辨识。该方法较已经提出的方法相比,需要的检测量少,辨识方法简单。仿真研究表明,RBF神经网络辨识效果优于BP神经网络。     

大跨悬索桥MTMD抖振控制的参数优化

针对悬索桥抖振控制问题,建立有限元模型,应用神经网络和遗传算法对多重调频质量阻尼器(MTMD)进行双参数优化。以某大跨悬索桥为例,利用神经网络改进的谐波合成模拟方法(RBF-WAWS法)对脉动风速进行模拟,并换算成抖振力作用主梁上,通过时程分析及后处理获取主跨跨中横桥向响应值。将响应值的均方差作为优化目标函数,以MTMD总质量、个数及阻尼比作为优化变量和约束条件,采用神经网络拟合目标函数并应用改进的自适应遗传算法进行寻优。结果表明,优化后的MTMD能有效控制悬索桥在脉动风作用下的抖振响应,减振率达48%。提出的理论与计算方法对悬索桥中MTMD的设置及参数选取具有实际工程意义。     

海底混响非瑞利特性研究及神经网络应用

基于单元散射理论介绍了瑞利分布模型和K分布模型,通过计算混响偏度和峰度判断出海底混响偏离瑞利分布模型,并利用CW信号、LFM信号的试验混响数据进行阵元域、波束域上的PDF曲线拟合。结果表明,海底混响的统计特性更趋向于K分布模型。利用BP网络方法和海底混响、点目标仿真信号的PDF特性进行了目标识别验证,其正确识别率达到了92%以上,且计算量大大降低。     

智慧高速公路设计案例分析

本文以某智慧高速的设计案例为依托,首先对国内外智慧高速发展和应用现状进行归纳总结,分析认为电动化、智能化的新型运载工具,信息化和功能专业化的基础设施,开放、共享、协同的管理与服务将是未来高速公路三大发展趋势。通过对高速公路使用者和管理者的需求针对性地精准分析,构建面向高速公路使用者和管理者的创新型应用服务。结合新技术的发展趋势,以服务需求为导向,建设"三网合一"智慧高速基础设施和智慧云控平台构成、数据流为驱动的、"开放、包容、创新"的智慧高速公路。基于案例分析的智慧高速规划设计全过程,对于国内智慧高速的整体设计和建设规划具有重要参考价值,探索开辟全新的高速公路智能化建设方向和思路。     

Electric vehicle charging station locations: Elastic demand,station congestion,and network equilibrium

Battery-only electric vehicles (BEVs) generally offer better air quality through lowered emissions, along with energy savings and security. The issue of long-duration battery charging makes charging-station placement and design key for BEV adoption rates. This work uses genetic algorithms to identify profit-maximizing station placement and design details, with applications that reflect the costs of installing, operating, and maintaining service equipment, including land acquisition. Fast electric vehicle charging stations (EVCSs) are placed across a congested city's network subject to stochastic demand for charging under a user-equilibrium traffic assignment. BEV users’ station choices consider endogenously determined travel times and on-site charging queues. The model allows for congested-travel and congested-station feedback into travelers’ route choices under elastic demand and BEV owners’ station choices, as well as charging price elasticity for BEV charging users.Boston-network results suggest that EVCSs should locate mostly along major highways, which may be a common finding for other metro settings. If 10% of current EV owners seek to charge en route, a user fee of $6 for a 30-min charging session is not enough for station profitability under a 5-year time horizon in this region. However, $10 per BEV charging delivers a 5-year profit of $0.82 million, and 11 cords across 3 stations are enough to accommodate a near-term charging demand in this Boston-area application. Shorter charging sessions, higher fees, and/or allowing for more cords per site also increase profits generally, everything else constant. Power-grid and station upgrades should keep pace with demand, to maximize profits over time, and avoid on-site congestion.     

Transit network design with allocation of green vehicles: A genetic algorithm approach

The use of fossil fuels in transportation generates harmful emissions that accounts for nearly half of the total pollutants in urban areas. Dealing with this issue, local authorities are dedicating specific efforts to seize the opportunity offered by new fuels and technological innovations in achieving a cleaner urban mobility. In fact, authorities are improving environmental performances of their public transport fleet by procuring cleaner vehicles, usually called low and zero emission vehicles (LEV and ZEV, respectively). Nevertheless there seems to be a lack of methodologies for supporting stakeholders in decisions related to the introduction of green vehicles, whose allocation should be performed since the network design process in order to optimize their available green capacity.In this paper, the problem of clean vehicle allocation in an existing public fleet is faced by introducing a method for solving the transit network design problem in a multimodal, demand elastic urban context dealing with the impacts deriving from transportation emissions.The solving procedure consists of a set of heuristics which includes a routine for route generation and a genetic algorithm for finding a sub-optimal set of routes with the associated frequencies.