机器人生产线在船舶智能制造中的应用研究

智能制造是“中国制造2025”的主攻方向。本文先浅谈了智能船厂，并结合国内首个智能船厂试点对智能船厂的初级发展建设等进行初步探索，主要对船舶智能制造机器人生产线应用进行梳理分析，如工艺流程及布置、生产模式改进、提质增效和人员减配等。     

An optimization model for integrated planning of railway traffic and network maintenance

Railway transportation systems are important for society and have many challenging and important planning problems. Train services as well as maintenance of a railway network need to be scheduled efficiently, but have mostly been treated as two separate planning problems. Since these activities are mutually exclusive they must be coordinated and should ideally be planned together. In this paper we present a mixed integer programming model for solving an integrated railway traffic and network maintenance problem. The aim is to find a long term tactical plan that optimally schedules train free windows sufficient for a given volume of regular maintenance together with the wanted train traffic. A spatial and temporal aggregation is used for controlling the available network capacity. The properties of the proposed model are analyzed and computational experiments on various synthetic problem instances are reported. Model extensions and possible modifications are discussed as well as future research directions.     

港珠澳大桥建设对珠三角地区物流业的影响

港珠澳大桥将改变珠江口东西两岸之间的空间运输联系方式,从而改变整个珠三角地区的物流格局.从珠三角地区城市空间布局结构、产业特点出发,总结珠三角地区物流业特点,对港珠澳大桥影响珠三角物流格局的途径进行介绍；并逐一分析港珠澳大桥建成后对香港、深圳、珠海等珠三角主要城市物流业的不同影响.     

上海松江区现代有轨电车规划研究

现代有轨电车因其环保、舒适、高效、低造价、高品质等特点,在国际上得到广泛应用,我国多个城市也在规划和建设之中。但是,由于其在国内尚为一种全新的交通方式,没有标准或规范予以指导,规划及设计体系不完善,有些已建项目已呈现问题。文章结合上海松江区规划背景及交通特征,阐述有轨电车示范线T1、T2线的布局规划、建设的必要性及适应性,为即将开展有轨电车规划及建设的城市提供借鉴与参考。     

基于语义挖掘的快递运输货品风险评价研究

为提高快递运输的风险监测管控能力，降低因快递货品风险导致城市安全事件发生的可 能性，本文基于语义挖掘方法将快递运输货品描述转化为风险的量化表征，为快递运输风险评价 提供可量化的客观指标依据。基于网络大数据资源提供的法院判决书数据，将物品词条与判决 结果相关联，通过隐狄利克雷分布模型挖掘物品风险主题，结合模糊均值聚类方法，实现对快递 货品语义风险的量化表征与柔性划分。与传统方法中依赖检视人员查验既定违禁品清单后的主 观判断方法不同，本文充分挖掘网络文本数据中的可迁移知识，并应用于种类繁多的快递运输货 品，有效避免人工评价造成的漏检、错检情况。研究结果表明，本文方法具有较高的准确率与较 低的误报率，获得的风险评价值不再是0或1的是非判断，有利于开展多样化、针对性的风险预警 及应对措施。     

A combined assessment of air and noise pollution on the High Line,New York City

The High Line is an elevated public park in New York City, transformed from an unused freight rail line. Pedestrians walking through Manhattan’s West Side can walk either on the High Line or on a footpath below. Using Manhattan as a laboratory, this paper offers a combined assessment of noise and particulate matter pollution for its pedestrians. Noise and PM_2.5 levels were recorded simultaneously for two cases (i) pedestrians walking on a footpath alongside road traffic and (ii) pedestrians walking on the elevated High Line. Testing took places over three days in autumn 2014. Results were analysed to investigate if pedestrians using the High Line would have a lower pollution exposure to those using the footpath below. Results showed statistically significant differences between the upper and lower levels in exposure to both pollution types. In order to quantify the overall impact, results are expressed through a combined air–noise pollution index. This index indicates that the average reduction in PM_2.5 and noise pollution along the High Line compared to the footpath below is approximately 37%.     

新城区轨道交通线路规划关键问题研究

对国内外主城与新城衔接的新城区(郊区)轨道线特征及交通功能等因素进行总结分析，并结合武汉市及国内外典型城市新城区轨道交通规划建设经验，对新城区轨道交通线路规划关键问题做深入研究。提出对新城区轨道交通线路规划中与其他不同层次轨道线网功能及技术标准的衔接关系；与新城区发展应注重以轨道交通引领新城区协同发展，与城市空间结构高度契合关系；新城区轨道线路走向应沿预测主要客流走廊，串联新城区商业、交通枢纽等大型客流集散点，以缓解开通初期普遍面临客流量增长缓慢，客运强度偏低的问题。     

Reducing CO2 emissions in temperature-controlled road transportation using the LDVRP model

Temperature-controlled transport is needed to maintain the quality of products such as fresh and frozen foods and pharmaceuticals. Road transportation is responsible for a considerable part of global emissions. Temperature-controlled transportation exhausts even more emissions than ambient temperature transport because of the extra fuel requirements for cooling and because of leakage of refrigerant. The transportation sector is under pressure to improve both its environmental and economic performance. To explore opportunities to reach this goal, the Load-Dependent Vehicle Routing Problem (LDVRP) model has been developed to optimize routing decisions taking into account fuel consumption and emissions related to the load of the vehicle. However, this model does not take refrigeration related emissions into account. We therefore propose an extension of the LDVRP model to optimize routing decisions and to account for refrigeration emissions in temperature-controlled transportation systems. This extended LDVRP model is applied in a case study in the Dutch frozen food industry. We show that taking the emissions caused by refrigeration in road transportation can result in different optimal routes and speeds compared with the LDVRP model and the standard Vehicle Routing Problem model. Moreover, taking the emissions caused by refrigeration into account improves the estimation of emissions related to temperature-controlled transportation. This model can help to reduce emissions of temperature-controlled road transportation.     

Integrating mesoscopic dynamic traffic assignment with agent-based travel behavior models for cumulative land development impact analysis

A number of approaches have been developed to evaluate the impact of land development on transportation infrastructure. While traditional approaches are either limited to static modeling of traffic performance or lack a strong travel behavior foundation, today’s advanced computational technology makes it feasible to model an individual traveler’s response to land development. This study integrates dynamic traffic assignment (DTA) with a positive agent-based microsimulation travel behavior model for cumulative land development impact studies. The integrated model not only enhances the behavioral implementation of DTA, but also captures traffic dynamics. It provides an advanced yet practical approach to understanding the impact of a single or series of land development projects on an individual driver’s behavior, as well as the aggregated impacts on the demand pattern and time-dependent traffic conditions. A simulation-based optimization (SBO) approach is proposed for the calibration of the modeling system. The SBO calibration approach enhances the transferability of this integrated model to other study areas. Using a case study that focuses on the cumulative land development impact along a congested corridor in Maryland, various regional and local travel behavior changes are discussed to show the capability of this tool for behavior side estimations and the corresponding traffic impacts.     

Human-like autonomous car-following model with deep reinforcement learning

This study proposes a framework for human-like autonomous car-following planning based on deep reinforcement learning (deep RL). Historical driving data are fed into a simulation environment where an RL agent learns from trial and error interactions based on a reward function that signals how much the agent deviates from the empirical data. Through these interactions, an optimal policy, or car-following model that maps in a human-like way from speed, relative speed between a lead and following vehicle, and inter-vehicle spacing to acceleration of a following vehicle is finally obtained. The model can be continuously updated when more data are fed in. Two thousand car-following periods extracted from the 2015 Shanghai Naturalistic Driving Study were used to train the model and compare its performance with that of traditional and recent data-driven car-following models. As shown by this study’s results, a deep deterministic policy gradient car-following model that uses disparity between simulated and observed speed as the reward function and considers a reaction delay of 1 s, denoted as DDPGvRT, can reproduce human-like car-following behavior with higher accuracy than traditional and recent data-driven car-following models. Specifically, the DDPGvRT model has a spacing validation error of 18% and speed validation error of 5%, which are less than those of other models, including the intelligent driver model, models based on locally weighted regression, and conventional neural network-based models. Moreover, the DDPGvRT demonstrates good capability of generalization to various driving situations and can adapt to different drivers by continuously learning. This study demonstrates that reinforcement learning methodology can offer insight into driver behavior and can contribute to the development of human-like autonomous driving algorithms and traffic-flow models.