检索结果-南通市图书馆

Numerical simulation of boundary heat flow effects on directional solidification microstructure of a binary alloy

在线全文

学校读者我要写书评

暂无评论

China Foundry 2010年第3期7卷 253-258页

作者： Xue Xiang tang jinjun School of Materials Science and Engineering Harbin Institute of Technology P. O. Box 434 Harbin 150001 China Ningbo Sub-academy of the National Weapons Science Research Academy Ningbo 315103 China

The boundary heat flow has important significance for the microstructures of directional solidified binary *** evolution of the directional solidified microstructure with different boundary heat flow was *** this study, only one interface was allowed to have heat flow, and Neumann boundary conditions were imposed at the other three *** the calculated results, it was found that different boundary heat flows will result in different *** the boundary heat flow equals to 20 W·cm-2, the growth of longitudinal side branches is accelerated and the growth of transverse side branches is restrained, and meanwhile, there is dendritic remelting in the calculation *** the boundary heat flow equals to 40 W·cm-2, the growths of the transverse and longitudinal side branches compete with each other, and when the boundary heat flow equals to 100-200 W·cm-2, the growth of transverse side branches dominates *** temperature field of dendritic growth was analyzed and the relation between boundary heat flow and temperature field was also investigated.

关键词： numerical simulation directional solidification phase field method boundary heat flow

Road traffic anomaly monitoring and warning based on DeepWalk algorithm

在线全文

学校读者我要写书评

暂无评论

Transportation Safety and Environment 2023年第2期5卷 38-46页

作者： Zihe Wang Junqing Ye jinjun tang School of Traffic and Transportation Engineering Central South UniversityChangsha 410075HunanChina School of Traffic and Transportation Beijing Jiaotong UniversityNo.3 ShangyuancunHaidian DistrictBeijing 100044China

In the complex urban road traffic network,a sudden accident leads to rapid congestion in the nearby traffic region,which even makes the local traffic network capacity quickly ***,an efficient monitoring system for abnormal conditions of the urban road network plays a crucial role in the tolerance of the urban road *** traditional traffic monitoring system not only costs a lot in construction and maintenance,but also may not cover the road network comprehensively,which could not meet the basic needs of traffic *** a more comprehensive and intelligent monitoring method is able to identify traffic anomalies more effectively and quickly,so that it can provide more effective support for traffic management *** extensive use of positioning equipment made us able to obtain accurate trajectory *** paper presents a traffic anomaly monitoring and prediction method based on vehicle trajectory *** model uses deep learning to detect abnormal trajectory on the traffic road *** method effectively analyses the abnormal source and potential anomaly to judge the abnormal region,which provides an important reference for the traffic department to take effective traffic control ***,the paper uses Internet vehicle trajectory data from Chengdu(China)to test and obtains an accurate result.

关键词： trajectory data deep learning anomaly trajectory detection traffic abnormal region

Lane-changing trajectory prediction based on multi-task learning

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Transportation Safety and Environment 2023年第4期5卷 67-77页

作者： Xianwei Meng jinjun tang Fang Yang Zhe Wang Smart Transport Key Laboratory of Hunan Province School of Transport and Transportation EngineeringCentral South UniversityChangsha 410075HunanChina

As a complex driving behaviour,lane-changing(LC)behaviour has a great influence on traffic *** lane-changing behaviour often leads to traffic *** studies are currently being conducted to predict lane-change trajectories to minimize ***,most of their models focus on how to optimize input variables without considering the interaction between output *** study proposes an LC trajectory prediction model based on a multi-task deep learning framework to improve driving ***,in this work,the coupling effect of lateral and longitudinal movement is considered in the L.C *** changes in two directions will be modelled separately,and the information interaction is completed under the multi-task learing *** addition,the trajectory fragents are clustered by the driving features,and trajectory type recognition is added to the trajectory prediction framework as an auxiliary ***,the prediction process of lateral and longitudinal trajectory and LC style is completed by long short-term memory(LSTM).The model training and testing are conducted with the data collected by the driving simulator,and the proposed method expresses better performance in LC trjectory prediction compared with several traditional *** results of this study can enhance the trajectory prediction accuracy of advanced driving assistance systems(ADASs)and reduce the traffic accidents caused by lane changes.

关键词： lane-changing behaviour trajectory prediction long short-term memory(LSTM)network multi-task learning trajectory clustering

Examining the characteristics between time and distance gaps of secondary crashes

在线全文

学校读者我要写书评

暂无评论

Transportation Safety and Environment 2024年第1期6卷 116-131页

作者： Xinyuan Liu jinjun tang Chen Yuan Fan Gao Xizhi Ding Smart Transport Key Laboratory of Hunan Province School of Transport and Transportation EngineeringCentral South UniversityChangsha 410075China Department of Computer Science City University of Hong Kong999077Kowloon TongHong KongChina Department of Geography and Resource Management The Chinese University of Hong KongShatinNT 999077Hong KongChina

Understanding the characteristics of time and distance gaps between the primary(PC)and secondary crashes(SC)is crucial for preventing SC ccurrences and improving road *** previous studies have tried to analyse the variation of gaps,there is limited evidence in quantifying the relationships between different gaps and various influential *** study proposed a two-layer stacking framework to discuss the time and distance ***,the framework took random forests(RF),gradient boosting decision tree(GBDT)and eXtreme gradient boosting as the base classifiers in the first layer and applied logistic regression(LR)as a combiner in the second *** this basis,the local interpretable model-agnostic explanations(LIME)technology was used to interpret the output of the stacking model from both local and global *** SC dentification and feature selection,346 SCs and 22 crash-related factors were collected from California interstate *** results showed that the stacking model outperformed base models evaluated by accuracy,precision,and recall *** explanations based on LIME suggest that collision type,distance,speed and volume are the critical features that affect the time and distance *** volume can prolong queue length and increase the distance gap from the SCs to *** collision types,peak periods,workday,truck involved and tow away likely induce a long-distance ***,there is a shorter distance gap when secondary roads run in the same direction and are close to the primary *** speed is a significant factor resulting in a long-time gap,while the higher speed is correlated with a short-time *** results are expected to provide insights into how contributory features affect the time and distance gaps and help decision-makers develop accurate decisions to prevent SCs.

关键词： secondary crash(SC) time and distance gaps stacking framework local interpretable model-agnostic explanations(LIME)

Analysing taxi customer-search behaviour using Copula-based joint model

在线全文

学校读者我要写书评

暂无评论

Transportation Safety and Environment 2022年第1期4卷 49-62页

作者： Helai Huang Zhenyuan Fang Yiwei Wang jinjun tang Xin Fu Smart Transportation Key Laboratory of Hunan Province School of Traffic and Transportation EngineeringCentral South UniversityChangsha 410075China School of Transportation Engineering Chang’an UniversityXi’an 710064China Engineering Research Center of Highway Infrastructure Digitalization Ministry of EducationXi’an 710064China

The drivers of vacant taxis tend to cruise the road network searching new passengers,which leads to additional traffic congestion,air pollution and other *** study introduces a Copula-based joint model to analyse destination selection and route choice behaviour in the customer-search process.A multinomial logit model is used to analyse the destination selection behaviour,and a path size logit model is used to explore the routes choice ***,the joint model applied Copula function is then established to analyse the correlation between these two *** destination customer generation rate,destination distance,route customer generation rate,path travel time,cumulative intersection delay,path size and route length are selected as explanatory *** taxis trajectory data were collected by global positioning system in Xidan District of Beijing City from September 2014 to February *** the log-likelihood,Bayesian information criterion as evaluation indexes to measure the fitting result,the joint model applied Copula function has the highest *** effect of explanatory variables on customer search behaviour is discussed based on the parameter estimation *** results of this study are helpful to understand the customer-search behaviour of taxi drivers to reduce operating costs and improve the efficiency of the taxi operation system.

关键词： customer-search behaviour destination selection route choice model Copula function taxi trajectory data

Speech at the Reception Commemorating the 30^(th) Anniversary of the Chinese Association for International Understanding

在线全文

学校读者我要写书评

暂无评论

International Understanding 2011年第3期 8-10页

作者： Li jinjun tang Yu

Honorable Mr. Luo Haocai, Advisor to CAFIU,Representatives of the diplomatic corps and the Press,Distinguished Guests,Comrades and Friends,Tonight, we are gathered here at this reception to commemorate the 30thanniver... 详细信息

关键词： Anniversary of the Chinese Association for International Understanding Speech at the Reception Commemorating the 30 th

基于路径预测的不确定性推理组合地图匹配算法

在线全文

学校读者我要写书评

暂无评论

测绘学报 2010年第5期39卷 546-550页

作者：唐进君刘芳内蒙古农业大学能源与交通工程学院内蒙古呼和浩特010018

提出一种新的基于预测的不确定性推理组合地图匹配算法。该方法首先利用云模型这样一种处理定性与定量间不确定转换的工具,通过对当前信息的不确定性推理,计算定位点相对于候选道路的匹配可信度。之后,利用隐马尔科夫模型预测驾驶员出... 详细信息

提出一种新的基于预测的不确定性推理组合地图匹配算法。该方法首先利用云模型这样一种处理定性与定量间不确定转换的工具,通过对当前信息的不确定性推理,计算定位点相对于候选道路的匹配可信度。之后,利用隐马尔科夫模型预测驾驶员出行路径及目的地,通过对模型中的观察值函数重新设定,将路径预测信息与当前地图匹配算法结合,构建组合地图匹配算法。同时,采用学习算法更新模型中的信息。最后,通过仿真实例证明该组合算法的可行性与有效性。结果表明:该方法能够预测驾驶员行驶路径,起到预匹配的作用,提高地图匹配算法的精度。

关键词：地图匹配算法车辆导航云模型隐马尔科夫模型驾驶员路径预测

在线全文

学校读者我要写书评

暂无评论

基于多准则粒子滤波算法的车辆轨迹重构

铁道科学与工程学报 2022年第8期19卷 2407-2416页

作者：唐进君王凯叶峻青中南大学交通运输工程学院湖南长沙410075

完整的车辆轨迹数据为高效交通管控提供数据支撑。为从城市车牌识别数据(ALPR:Automatic license plate recognition)中提取完整车辆轨迹信息,提出一种粒子滤波框架下的多准则车辆轨迹重构方法。首先,对提取到的初始车辆轨迹进行断点识... 详细信息

完整的车辆轨迹数据为高效交通管控提供数据支撑。为从城市车牌识别数据(ALPR:Automatic license plate recognition)中提取完整车辆轨迹信息,提出一种粒子滤波框架下的多准则车辆轨迹重构方法。首先,对提取到的初始车辆轨迹进行断点识别,确认车辆轨迹中需重构部分的位置和数量,并结合k则最短路算法对这些部分搜索生成轨迹集。然后,将轨迹集中的每条轨迹视作初始粒子输入到改进的粒子滤波器中,新粒子滤波器的5个重采样过程与5个时空校正因子一一对应,即:行程时间一致性因子、可测性准则因子、路径尺寸因子、转弯次数因子和距离准则因子。新粒子滤波器对含有主观因素的校正因子重采样过程加入了一定的随机性,以模拟车辆在行驶时的主观行为,粒子滤波器最终输出的轨迹为重构后的完整轨迹。最后,以长沙市天心区实测车牌识别数据为例,对比本文算法与传统算法轨迹重构的准确性。结果表明,本文算法考虑了车辆行驶时的随机性,在重构准确率方面具有一定优势,重构平均准确率达到94.8%。综上,提出的算法在传统方法基础上进行了多方面的改进,有利于提升轨迹重构的可靠性和精度,为城市路网车辆轨迹分析提供高质量的数据基础。

关键词：城市交通轨迹重构粒子滤波车牌识别数据路径搜索

在线全文

学校读者我要写书评

暂无评论

基于递阶优化的城市区域路网交通控制

铁道科学与工程学报 2023年第1期20卷 63-73页

作者：吉柯唐进君曾捷刘鑫源中南大学交通运输工程学院湖南长沙410075

城市道路拥堵问题随着城市机动化的快速发展日益凸显,采用合理的控制手段提高区域路网效率成为急需解决的问题。以长沙市部分路网作为研究对象,选取连续5个工作日的早高峰流量数据进行研究。在VISSIM仿真软件中根据抽象路网搭建仿真路网... 详细信息

城市道路拥堵问题随着城市机动化的快速发展日益凸显,采用合理的控制手段提高区域路网效率成为急需解决的问题。以长沙市部分路网作为研究对象,选取连续5个工作日的早高峰流量数据进行研究。在VISSIM仿真软件中根据抽象路网搭建仿真路网,将仿真路网中的交通数据与实际道路车牌识别数据相匹配,以交叉口通过车辆数为评价标准计算仿真路网与实际道路的误差率,保证仿真路网真实性。采用反压力值作为道路反馈指标,计算路网中的压力分布情况。基于周期稳定性,将研究范围内的交叉口划分为2类,以大小周期的方式进行信号配时优化,考虑交通高峰期道路饱和度偏高的情况,将传统韦伯斯特算法进行改进后作为控制方法。采用递阶优化的思想进行控制策略计算。对控制策略进行仿真验证,在结果中从路网和车辆2个方面选取在网车辆数、到达车辆数、车均延误和车辆速度四4个指标对优化前后的路网状况进行评价。优化后的路网较原始路网在到达车辆数和车辆速度方面有所提升,在网车辆数和车均延误有所下降。同时,针对不同饱和度的交叉口,控制策略在4个评价指标方面也有相同的优化趋势。研究结果表明,基于递阶优化的路网交通控制能够提高路网的通行效率,改善路网运行环境。

关键词：交通控制递阶优化交通仿真城市路网车牌识别数据