Short‐term traffic flow prediction with linear conditional Gaussian Bayesian network

Traffic flow prediction is an essential part of intelligent transportation systems (ITS). Most of the previous traffic flow prediction work treated traffic flow as a time series process only, ignoring the spatial relationship from the upstream flows or the correlation with other traffic attributes like speed and density. In this paper, we utilize a linear conditional Gaussian (LCG) Bayesian network (BN) model to consider both spatial and temporal dimensions of traffic as well as speed information for short‐term traffic flow prediction. The LCG BN allows both continuous and discrete variables, which enables the consideration of categorical variables in traffic flow prediction. A microscopic traffic simulation dataset is used to test the performance of the proposed model compared to other popular approaches under different predicting time intervals. In addition, the authors investigate the importance of spatial data and speed data in flow prediction by comparing models with different levels of information. The results indicate that the prediction accuracy will increase significantly when both spatial data and speed data are included. Copyright © 2016 John Wiley & Sons, Ltd.     

基于发动机在挡转速控制策略的HBB性能试验研究

发动机冷启动后,排放及快速暖机需要较高的发动机转速,车辆在冷启动后易出现制动踏板变硬、制动效能不足的问题,尤其在高原地区,存在一定的安全隐患。文中通过对某一车型的ESP增加HBB(Hydraulic Brake Boost)功能并优化发动机在挡怠速的控制策略,改善真空助力泵的真空度水平来增加辅助制动,满足正常制动要求。     

Experimental study of EGR cooler regeneration aided by oxygen-fed NTP and air-fed NTP

Based on non-thermal plasma (NTP) technology fed by oxygen and air as the gas source respectively, the experimental system of exhaust gas recirculation (EGR) cooler regeneration was built to do a study at different regeneration temperatures. By measuring the concentration of main active substance and CO_x in regeneration process, the influence of temperature on regeneration aided by oxygen-fed NTP and air-fed NTP was investigated. The experimental results indicate that EGR cooler can be regenerated both by air-fed NTP and oxygen-fed NTP at a wide temperature range of 18 °C ～ 300 °C. By comparison of the regeneration with oxygen-fed NTP and air-fed NTP, it can be easily known that the regeneration effect is most remarkable at 150 °C with oxygen-fed NTP and at 120 °C with air-fed NTP. In addition, when the temperature is below 150 °C especially at 120 °C, the regeneration efficiency of air-fed NTP is lower than oxygen-fed NTP, nevertheless, when the temperature is above 150 °C, air-fed NTP has a superiority in regeneration and the higher the temperature is, the more obvious the superiority will be.     

燃料电池发动机系统空气加湿器实验研究

由于质子交换膜燃料电池(PEMFC)性能受反应气体的湿度影响很大,进气湿度必须加以控制,其大致范围应高于80%,低于100%。电解质的质子传导能力与水含量成正比,但水分含量又不能过高,否则会引起电解质淹没。当PEMFC在不加湿的情况下,工作温度升高60℃时,反应气体会非常干燥,这对质子交换膜是灾难性的,所以对反应气体加湿必不可少。通过实验证明了某型加湿器能够满足车用燃料电池发动机的需要。     

汽车电气故障诊断的流程与分析方法（I）

对汽车故障、汽车故障诊断和汽车故障诊断标准进行了重新定义,详细介绍汽车电气故障诊断的一般流程与分析方法,结合汽车故障诊断仪、汽车示波器、汽车万用表等仪器设备的使用操作、测试数据分析与电路分析,一一举例加以说明。     

大体积高墩盖梁剪力销法设计与施工技术

以泸州泰安长江大桥工程为例,介绍了大体积高墩盖梁剪力销法支撑体系的设计与施工,及其施工中应注意的有关问题.     

混合交通状态下交叉口排队机动车流启动车头时距研究和应用

研究的主要内容包括:信号灯控制道路交叉口红灯周期形成的排队车辆,在放行后不同车型的启动时间和不同车型组成的混合机动车流车头时距的分布研究;混合交通状态下机动车启动通过交叉口时受到干扰后的延误时间研究;利用上述研究成果对混合交通状态下交叉口排队车辆的放行绿灯时间进行估算。课题以现实交通数据为基础,通过统计分析结果最终建立放行绿灯时间估算表,对混合交通状态下道路交叉口信号灯的配时起到指导意义。     

混合小生境遗传-模拟退火算法在动态交通分配中的应用

为了解决已有的动态交通分配模型普遍存在的优化计算时间过长,严重影响网络规模扩展的问题,提出了一种新的动态交通分配优化算法。将模拟退火和隔离小生境技术有机地结合起来,融入到遗传训练过程中形成了一种混合小生境遗传-模拟退火算法,不仅可以有效地避免传统遗传算法可能出现的不收敛现象,加快进化速度,具有更强的全局寻优能力,而且计算速度和算法稳定性也得到提高。将其与Papageorgiou M.提出的动态交通分配模型框架相结合,设计了动态交通分配的快速模拟优化算法,并进行了实例研究。仿真结果表明,新的优化算法显著降低了优化计算时间,大大提高了动态交通分配模型的实用价值。     

基于ADAMS的某悬架系统运动特性分析及结构优化

根据多体动力学理论,运用ADAMS／car软件对某微型轿车悬架系统建立了模型并进行仿真分析;使用ADAMS／Insight以轮胎横向滑移量、主销偏距和四个车轮定位参数为设计目标对悬架的结构关键点进行了优化分析,使该悬架的运动学特性更符合理想设计值。     

时变MIMO系统的联合符号检测与信道估计

针对MIMO系统时变多径信道,结舍分集舍并,提出一种带判决反馈的修正混和型MLSE（DF-MHMLSE）为基础的低复杂度联合符号检测与信道估计的递推算法．发送端仅需少量导频符号用于信道估计初始化,在此基础上,针对系统中各MISO子系统,分别采用修正混和型MLSE算法（MHMLSE）,形成临时判决符号矢量集合及对应的临时信道矢量集合,最终根据分集合并确定最佳判决符号矢量,同时实现信道矢量的自适应更新,该算法减小了传统MIMOMLSE的计算复杂度,实现了逐符号检测,并取得了较低的误比特率．