基于分布式光纤的隧道振动监测系统试验研究

运营期隧道突发事件发生频率的不断增高对隧道的健康监测提出了挑战。目前,国内铁路隧道对突发事件自动化监测的研究仍处于初期阶段。为验证京雄高速铁路隧道基于分布式光纤的振动监测系统的实施效果,本文开展了钻机打孔、挖掘机铲土、工程车辆行驶和隧道内落石等振动事件的模拟试验。结果表明：该监测系统对振动事件具有较高的灵敏度,通过时、频域分析方法可短时间确定振动事件的发生位置,定位精度较高,满足工程对突发事件准确定位的需求。     

基于Q-learning和BP神经元网络的交叉口信号灯控制

解决单交叉口信号灯最优控制问题。提出了基于强化学习的信号灯控制系统结构,应用强化学习中Q学习,将信号灯最优控制问题转变成是否切换运行相位的决策问题,提出了采用BP神经元网络实现Q学习的信号灯控制系统。应用微观交通仿真软件PARAMICS进行仿真分析,结果表明该系统能够感知交通流变化,并能够自适应地调整信号灯切换策略,以达到最优的控制效果,该方法是可行的,与定时控制相比具有明显的优势。     

集通铁路长大隧道GSM-R冗余方案研究

针对集通铁路的长大隧道,论述分布式基站和数字光纤直放站的两种冗余方案,通过分析比较两种方案的单网交织以及同站址双网冗余覆盖方式,推荐采用分布式基站单网交织冗余方案.     

一种基于语义分割结果的车道线检测拟合方法

车道线等地面标志物的检测是自动驾驶车辆环境感知的重要内容,能够为车辆提供可行驶区域的信息。文章提出一种基于语义分割结果的车道线检测拟合方法。使用车载单目相机获取车辆行驶过程中采集的道路图像,送入卷积神经网络进行车道线语义分割。将分割得到的仅含车道线的二值图像进行透视变换得到鸟瞰图,筛选有效车道线像素点,对有效车道线点使用最小二乘法进行多项式拟合,输出左右车道线多项式拟合系数,能够有效解决传统车道线检测算法的环境适应性差,鲁棒性不强,对弯道车道线检测信息不够准确等问题。     

Study on Distributed Motion of Self-Reconfigurable Robot Based on Local Rules

The eigenvector of a module with six adjacent module's state was constructed according to self-reconfigurable robot M-Cubes and the configuration of system was expressed with the eigenvectors of all modules.According to the configuration and motion characteristics of the modules,a 3-dimension motion rule set was provided.The rule sets of each module was run according to eigenvector of the module after the motion direction of system decided and motion rules were selected.At last,the rapid and effective motion and metamorphosis were realized in system.The rule sets are operated on three systems and the distributed motion of system is fully realized.The result of simulation shows that the 3-dimension motion rule sets has perfect applicability and extensibility.The motion steps and communication load of the modules increase with the module number in linear.     

Controller design for gating traffic control in presence of time-delay in urban road networks

Recent studies demonstrated the efficiency of feedback-based gating control in mitigating congestion in urban networks by exploiting the notion of macroscopic or network fundamental diagram (MFD or NFD). The employed feedback regulator of proportional-integral (PI)-type targets an operating NFD point of maximum throughput to enhance the mobility in the urban road network during the peak period, under saturated traffic conditions. In previous studies, gating was applied directly at the border of the protected network (PN), i.e. the network part to be protected from over-saturation. In this work, the recently developed feedback-based gating concept is applied at junctions located further upstream of the PN. This induces a time-delay, which corresponds to the travel time needed for gated vehicles to approach the PN. The resulting extended feedback control problem can be also tackled by use of a PI-type regulator, albeit with different gain values compared to the case without time-delay. Detailed procedures regarding the appropriate design of related feedback regulators are provided. In addition, the developed feedback concept is shown to work properly with very long time-steps as well. A large part of the Chania, Greece, urban network, modelled in a microscopic simulation environment under realistic traffic conditions, is used as test-bed in this study. The reported results demonstrate a stable and efficient behaviour and improved mobility of the overall network in terms of mean speed and travel time.     

Achieving transport modal split targets at intermodal freight hubs using a model predictive approach

The increase of international freight commerce is creating pressure on the existing transport network. Cooperation between the different transport parties (e.g., terminal managers, forwarders and transport providers) is required to increase the network throughput using the same infrastructure. The intermodal hubs are locations where cargo is stored and can switch transport modality while approaching the final destination. Decisions regarding cargo assignment are based on cargo properties. Cargo properties can be fixed (e.g., destination, volume, weight) or time varying (remaining time until due time or goods expiration date). The intermodal hub manager, with access to certain cargo information, can promote cooperation with and among different transport providers that pick up and deliver cargo at the hub. In this paper, cargo evolution at intermodal hubs is modeled based on a mass balance, taking into account hub cargo inflows and outflows, plus an update of the remaining time until cargo due time. Using this model, written in a state-space representation, we propose a model predictive approach to address the Modal Split Aware – Cargo Assignment Problem (MSA–CAP). The MSA–CAP concerns the cargo assignment to the available transport capacity such that the final destination can be reached on time while taking into consideration the transport modality used. The model predictive approach can anticipate cargo peaks at the hub and assigns cargo in advance, following a push of cargo towards the final destination approach. Through the addition of a modal split constraint it is possible to guide the daily cargo assignment to achieve a transport modal split target over a defined period of time. Numerical experiments illustrate the validity of these statements.     

Impact assessment of extreme weather events on transport networks: A data-driven approach

The present paper presents a data-driven method for assessing the resilience of the European passenger transport network during extreme weather events. The method aims to fill in the gap of current research efforts regarding the quantification of impacts attributed to climate change and the identification of substitutability opportunities between transport modes in case of extreme weather events (EWE). The proposed method consists of three steps concerning the probability estimation of an EWE occurring within a transportation network, the assessment of its impacts and the passengers’ flow shift between various transport modes. A mathematical formulation for the proposed data-driven method is provided and applied in an indicative European small-scale network, in order to assess the impacts of EWE on modal choice. Results are expressed in passenger differentiated flows and the paper concludes with future research steps and directions.     

Analysis of air traffic control operational impact on aircraft vertical profiles supported by machine learning

The Air Traffic Management system is under a paradigm shift led by NextGen and SESAR. The new trajectory-based Concept of Operations is supported by performance-based trajectory predictors as major enablers. Currently, the performance of ground-based trajectory predictors is affected by diverse factors such as weather, lack of integration of operational information or aircraft performance uncertainty.Trajectory predictors could be enhanced by learning from historical data. Nowadays, data from the Air Traffic Management system may be exploited to understand to what extent Air Traffic Control actions impact on the vertical profile of flight trajectories.This paper analyses the impact of diverse operational factors on the vertical profile of flight trajectories. Firstly, Multilevel Linear Models are adopted to conduct a prior identification of these factors. Then, the information is exploited by trajectory predictors, where two types are used: point-mass trajectory predictors enhanced by learning the thrust law depending on those factors; and trajectory predictors based on Artificial Neural Networks.Air Traffic Control vertical operational procedures do not constitute a main factor impacting on the vertical profile of flight trajectories, once the top of descent is established. Additionally, airspace flows and the flight level at the trajectory top of descent are relevant features to be considered when learning from historical data, enhancing the overall performance of the trajectory predictors for the descent phase.     

Dynamic traffic metering in urban street networks: Formulation and solution algorithm

Traffic metering offers great potential to reduce congestion and enhance network performance in oversaturated urban street networks. This paper presents an optimization program for dynamic traffic metering in urban street networks based on the Cell Transmission Model (CTM). We have formulated the problem as a Mixed-Integer Linear Program (MILP) capable of metering traffic at network gates with given signal timing parameters at signalized intersections. Due to the complexities of the MILP model, we have developed a novel and efficient solution approach that solves the problem by converting the MILP to a linear program and several CTM simulation runs. The solution algorithm is applied to two case studies under different conditions. The proposed solution technique finds solutions that have a maximum gap of 1% of the true optimal solution and guarantee the maximum throughput by keeping some vehicles at network gates and only allowing enough vehicles to enter the network to prevent gridlocks. This is confirmed by comparing the case studies with and without traffic metering. The results in an adapted real-world case study network show that traffic metering can increase network throughput by 4.9–38.9% and enhance network performance.