基于强化学习的干线信号混合协同优化方法

交通拥堵已成为很多大中城市普遍存在的社会问题。信号控制作为缓堵保畅的重要措施之一，愈发受到社会关注。信号优化手段可分为模型驱动和数据驱动两类，且随着交通大数据的不断充实，基于强化学习的数据驱动方法日益成为新兴发展方向。然而，现有数据驱动类研究主要偏重于决策模型设计，缺乏对智能体结构的探讨；同时，在多路口协同方面多采用分布式策略， 忽略了智能体之间信息交互，无法保障区域层面的整体最优性。为此，本文以干线信号为对象， 构建一种多智能体混合式协同决策的信号优化方法。首先，针对交通状态的多样性、异构性及数据不均衡性，设计分布训练-分区记忆的单智能体决策模型，并优化状态空间和回报函数，界定单路口控制的最佳方案；其次，融合分布式和集中式学习的模型优势设计多智能体交互方法，在单路口分布式控制的基础上，设置中心智能体评价局部智能体的决策行为并反馈附加回报以调整局部智能体的决策模型，实现干线多信号的协同运行。最后，搭建仿真平台完成效果测试与算法对比。结果表明：新方法与独立优化和分布式协同相比，在支路交通流基本不受影响的前提下， 干线停车次数分别降低了14.8%和13.6%，具有更好的控制效果。     

A modified reinforcement learning algorithm for solving coordinated signalized networks

This study proposes Reinforcement Learning (RL) based algorithm for finding optimum signal timings in Coordinated Signalized Networks (CSN) for fixed set of link flows. For this purpose, MOdified REinforcement Learning algorithm with TRANSYT-7F (MORELTRANS) model is proposed by way of combining RL algorithm and TRANSYT-7F. The modified RL differs from other RL algorithms since it takes advantage of the best solution obtained from the previous learning episode by generating a sub-environment at each learning episode as the same size of original environment. On the other hand, TRANSYT-7F traffic model is used in order to determine network performance index, namely disutility index. Numerical application is conducted on medium sized coordinated signalized road network. Results indicated that the MORELTRANS produced slightly better results than the GA in signal timing optimization in terms of objective function value while it outperformed than the HC. In order to show the capability of the proposed model for heavy demand condition, two cases in which link flows are increased by 20% and 50% with respect to the base case are considered. It is found that the MORELTRANS is able to reach good solutions for signal timing optimization even if demand became increased.     

Analyzing passenger train arrival delays with support vector regression

We propose machine learning models that capture the relation between passenger train arrival delays and various characteristics of a railway system. Such models can be used at the tactical level to evaluate effects of various changes in a railway system on train delays. We present the first application of support vector regression in the analysis of train delays and compare its performance with the artificial neural networks which have been commonly used for such problems. Statistical comparison of the two models indicates that the support vector regression outperforms the artificial neural networks. Data for this analysis are collected from Serbian Railways and include expert opinions about the influence of infrastructure along different routes on train arrival delays.     

Prioritizing road extension projects with interdependent benefits under time constraint

Since transportation projects are costly and resources are limited, prioritizing or sequencing the projects is imperative. This study was inspired by a client who asked: “I have tens of approved road extension projects, but my financial resources are limited. I cannot construct all the projects simultaneously, so can you help me prioritize my projects?” To address this question, the benefits and costs of all the possible scenarios must be known. However, the impacts (or benefit) of road extension projects are highly interdependent, and in sizable cases cannot be specified thoroughly. We demonstrate that the problem is analogous to the Traveling Salesman Problem (TSP). Dynamic change in travel demand during construction is another aspect of the complexity of the problem. The literature is yet to provide efficient methods for large cases. To this end, we developed a heuristic methodology in which the variation of travel demand during the construction period is considered. We introduce a geometrical objective function for which a solution-finding policy based on “gradient maximization” is developed. To address the projects’ interdependency, a special neural network (NN) model was devised. We developed a search engine hybridized of Ant Colony and Genetic Algorithm to seek a solution to the TSP-like problem on the NN based on gradient maximization. The algorithm was calibrated and applied to real data from the city of Winnipeg, Canada, as well as two cases based on Sioux-Falls. The results were reliable and identification of the optimum solution was achievable within acceptable computational time.     

混合式教学在《汽车测试技术》课程中的应用探索与反思

混合式教学是将线上教学与线下教学相结合的新型教学模式,充分利用混合式教学的优势以达到提升课程质量的目的。文章以《汽车测试技术》课程为例,对课程混合式教学的设计与实践进行了探索,分析了实施效果,进而总结了教学反思,旨在指导课程教学质量持续改进,同时为同类课程的混合式教学提供一定参考。     

基于PSO算法的地铁智能调线调坡系统开发与研究

为解决人工调线调坡费时费力、效率低下，且无有效评价指标评判方案优劣的现状问题，从分析线路平纵断面设计变量入手，依据规范相关规定制定约束条件，创新性地建立带有侵限容忍值惩罚项和合规性惩罚项的目标函数，提出一套基于粒子群优化算法，适用于矩形、马蹄形、圆形等多种隧道断面类型的地铁调线调坡数学分析模型，并以此开发地铁智能调线调坡系统。以长沙地铁4号线某区间右线隧道为例，对比人工设计和智能系统的调线调坡结果。由对比结果可知，智能系统在线路参数选择的合理性和改善侵限情况等方面均明显优于人工调线调坡，且具有可靠性和高效性。     

考虑驾驶风格差异的高原公路危险路段识别研究

针对高原环境中驾驶人风格、生理变化与危险路段特征之间的潜在关联，提出一种基于驾驶状态的危险路段识别方法，辨识和分析不同风格驾驶人具有潜在风险的路段，并提出优化方案。首先，通过实车实验采集驾驶人行为及生理指标数据，使用DBSCAN(Density Based Spatial Clustering of Applications with Noise)得出驾驶风格类型，并依据行为特征对驾驶风格进行差异性 分析；其次，采用卷积神经网络、双向长短时记忆神经网络与注意力机制搭建危险状态识别模型，通过GPS(Global Positioning System)点位对应实现危险路段辨识，并基于驾驶风格差异，从驾驶人感知、操纵与生理角度对危险路段进行致因分析；最后，将生理与道路线形作为优化参考，以车速建议为着力点进行多元回归分析，并按照生理舒适域确定车速建议区间。结果表明：驾驶人根据行为特点分为谨慎、稳健和激进型，3类驾驶人在上行和下行途中的危险路段多为具有弯坡特征的组合型路段；海拔提升可加速危险驾驶状态的出现，各类驾驶人在上行时的紧张状态多源于弯坡组合值和转角值的增长，激进型驾驶人在坡度大于6%的直纵坡路段时亦会开始高度紧张；下行时，谨慎与激进型驾驶人在直纵坡坡度大于3%时易出现危险状态，激进型驾驶人在转角值大于80°且弯坡组合值大于50时亦存在驾驶风险。研究成果可满足高原公路人因事故预防的需求，为线形设计与交通管理措施制定提供理论依据。     

A model for the biaxial dynamic bending of unbonded flexible pipes

An analytical model is given to investigate the behavior of unbonded flexible pipes under biaxial dynamic bending. The stick-slip conditions of each wire are studied in the framework of incremental analysis by an operator splitting of the time step into a stick-state prediction and a slip-state correction step. The tension gradient is calculated using the classical return-mapping algorithm and the obtained tension gradients are integrated numerically to find the axial tension by imposing appropriate boundary conditions. From the axial tension the bending moments with respect to the principal bending axes of the pipe are obtained. Poisson's effect, bending induced tension in the wire, shear deformations of the supporting plastic layer and the changes of the effective torsion and curvature increments of the wire after slip occurs are taken into account in the model. The results of bending moment–curvature relationship from this model are compared with the test data from simple bending and good correlations are found. The comparison of the biaxial bending moment results between this model and the available model also shows good agreement.     

Towards data-driven car-following models

Car following models have been studied with many diverse approaches for decades. Nowadays, technological advances have significantly improved our traffic data collection capabilities. Conventional car following models rely on mathematical formulas and are derived from traffic flow theory; a property that often makes them more restrictive. On the other hand, data-driven approaches are more flexible and allow the incorporation of additional information to the model; however, they may not provide as much insight into traffic flow theory as the traditional models. In this research, an innovative methodological framework based on a data-driven approach is proposed for the estimation of car-following models, suitable for incorporation into microscopic traffic simulation models. An existing technique, i.e. locally weighted regression (loess), is defined through an optimization problem and is employed in a novel way. The proposed methodology is demonstrated using data collected from a sequence of instrumented vehicles in Naples, Italy. Gipps’ model, one of the most extensively used car-following models, is calibrated against the same data and used as a reference benchmark. Optimization issues are raised in both cases. The obtained results suggest that data-driven car-following models could be a promising research direction.     

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.