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.     

基于多层次模型的波函数法在凹域问题应用研究

波函数法（Wave Based Method，WBM）是近年来发展的基于间接 Trefftz 理论的结构—声辐射中频问题的一种重要方法。 WBM 函数收敛的充要条件是分析域为凸域。为提高使用 WBM 理论的应用范围和应用效率，根据多层次模型，提出了补域概念用于解决凹域问题。最后，以一个周边简支矩形薄板为例进行验证数值，计算结果表明了方法准确性和有效性。     

Fracture mechanics analysis for mooring chain links subjected to out-of-plane bending (OPB)

A fracture mechanics (FM) based investigation on the mechanism of out-of-plane bending (OPB) between mooring chain links and its effects on fatigue lives of mooring chain links are conducted. Four types of OPB problems that mooring chain links laying on the chain wheel, chain links passing over the bending shoe, chain links constraint provided by the chain hawse, and chain links constraint provided by the chain stopper are considered. Tension ranges of mooring lines are calculated based on the combined loading process induced by the motions of wave frequency (WF) and low frequency (LF). Initial cracks are assumed to propagate from surfaces of chain links and stress intensity factors are calculated in terms of stress ranges determined by a finite element (FE) analysis. The results show that fatigue lives of mooring chain links are decreased significantly due to OPB effects. In addition, the increase of the number of pockets of chain wheel mitigates OPB effects on fatigue lives of mooring chain links laying on the chain wheel, and the increase of the track diameter would reduce OPB effects on fatigue lives of mooring chain links passing over the bending shoe as well. However, for chain links constraint provided by the chain hawse, the diameter of mooring chain hawse has no significant effect on fatigue lives of the mooring chain links subject to OPB if without the abrupt change of the contact conditions between chain links and chain hawse. For mooring links constraint provided by chain stoppers considering the effect of proof loading test, fatigue lives of mooring chain links would drop significantly with the increase of interlink angles and friction coefficient.     

MARK III 型LNG模拟舱结构安全评估及优化设计研究

液化天然气（Liquefied Natural Gas）运输船的建造技术复杂，货物维护系统（Cargo Containment System） 种类繁多，船上 LNG 常采用低温高压的储藏方式，该方式对储舱结构强度以及货物维护系统的 变形要求非常高。本文采用有限元方法， 对根据行业规范设计的 MARK III 型 LNG 模拟舱结构进行结构 强度安全性评估，并在满足 LNG 模拟舱结构承载能力要求的基础上，对 MARK III 型 LNG 模拟舱进行结 构优化设计研究，为今后 MARK III 型 LNG 运输船的船体结构设计和优化提供可靠的技术支撑。     

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.     

Port-city exhaust emission model: An application to cruise and ferry operations in Las Palmas Port

Exhaust emissions cause air pollution and climate change. The exhausts of shipboard fuel combustion are equally damaging particularly, so close to the environmentally sensitive mainland and island coasts, as well as at ports due to their urbanized character. This paper estimates, for the first time, exhaust pollutants related to cruise and ferry operations in Las Palmas Port and, in an island context. Emission assessment is based on a full bottom-up model and messages transmitted by the Automatic Identification System during 2011. Results are described as a breakdown of NOx, SOx, PM_2.5, CO and CO₂, according to ship classes, operative type and time, providing valuable information to environmental policy makers in port-city areas and islands under similar conditions. It is generally concluded that vessel traffic and passenger shipping in particular are a source of air pollution in Las Palmas Port. Emission maps confirm location of hot spots in quays assigned for cruise and ferry operations. Policy recommendations encourage regular monitoring of exhaust emissions and market-based incentives supported by details on polluting and operative profiles. On the other hand, feasibility studies are suggested for automated mooring, LNG bunkering facilities and also shore-side energy services, prioritizing berthing of shipping sectors (or sub-sectors) with the highest share of exhaust emissions once their local effects have been confirmed by a dispersion, exposure and impact assessment.     

CTCS2+ATO列控车载设备测试平台设计

列车运行控制系统测试平台是列车运行控制系统研发、生产及调试的重要支撑。通过分析车载设备的测试需求,提出测试平台解决方案,并进行了设计实现。研究成果可为城际铁路列控系统的测试提供一定的参考。     

驾驶人“感知-决策-操控”行为模型

为准确模拟驾驶人跟车行为，提出基于隐马尔可夫模型(Hidden Markov Model，HMM)的驾驶人“感知-决策-操控”行为模型。建立描述驾驶意愿的HMM模型，模拟驾驶人感知过程，获得期望的车间距；预测模块模拟驾驶人根据交通环境和自身生理、心理状态预测车辆未来轨迹，即决策过程；优化模块描述驾驶人为使预测的车辆轨迹跟踪上期望的车辆间距而采取的操控汽车的执行动作，即操控过程。上述3个模块的滚动过程实现了对驾驶人跟车行为的模拟。利用自然驾驶数据进行算例分析，结果表明，本文模型预测车间距平均误差仅为1.47%，证明了所建模型的有效性及准确性。本文为驾驶行为建模方法的理论研究和应用拓宽了思路。     

基于CATIA平台的三维集装箱导轨设计

在集装箱导轨设计中,存在着导轨需要安装的结构剖面多,不同剖面中连接肘板布置复杂,连接肘板种类繁多,重量统计繁琐等问题。该文基于计算机辅助三维交互应用(CATIA)平台,提出一种集装箱导轨的三维设计方法,利用CATIA的知识工程、参数化设计、统一装配等功能,有效提升了设计效率,使设计更加智能化,降低了后期修改工作量。