基于网络算法的地铁长大区间隧道火灾通风模式

建立通风网络模型,通过模拟列车车头火灾下6种典型工况的通风排烟,着重分析不同位置隧道风机的开闭数量对通风排烟效果的影响。讨论了不同模式下的气流组织方向及风速特征值。分析模拟结果发现,开启起火隧道列车车头前车站风井的2台隧道风机正转排风、列车车尾后中间风井的2台隧道风机反转送风,同时开启未起火隧道侧2台隧道风机反转辅助送风,则通风效果最好。     

基于数字伺服控制的电控罗经设计及仿真

本电控罗经采用数字伺服控制方案来取代传统的模拟伺服控制方案,将微处理机引入控制系统,可以克服系统调试困难的缺点,具有实现复杂计算和现代化控制算法的能力。设计了基于PID控制的静基座和摇摆基座下电控罗经的控制算法,运用Simulink进行建模和仿真,并通过实际转台测试实验得出,所设计的数字伺服控制电控罗经在摇摆实验环境下,稳定时间为1.8h,罗经的稳态误差为0.5 °,满足设计预期指标和国际标准要求。     

接驳轨道枢纽的混合式灵活公交服务优化研究

为解决居民在轨道与小区间的出行难题，本文提出一种新型的混合式灵活公交接驳服务模式，构建了在轨道交通枢纽的客流吸引范围内灵活与固定接驳公交的协同运行机制. 在已知灵活乘客需求和车队规模的条件下，综合兼顾出行者与运营者的时间成本，以及同步考虑轨道线路和固定接驳公交线路发车计划，建立了混合式接驳公交系统线路和乘客接运计划优化模型，并采用基于重力模型的遗传算法进行求解，最后通过实例验证该模型的有效性和实用性.结果表明，该优化模型在能够有效减小车辆行驶距离和乘客出行时间的同时，提高了混合式接驳公交系统的乘客服务量，相比于单一的灵活型接驳公交系统目标结果更优.     

A distributed VNS algorithm for optimizing dial-a-ride problems in large-scale scenarios

These days, transportation and logistic problems in large cities are demanding smarter transportation services that provide flexibility and adaptability. A possible solution to this arising problem is to compute the best routes for each new scenario. In this problem, known in the literature as the dial-a-ride problem, a number of passengers are transported between pickup and delivery locations trying to minimize the routing costs while respecting a set of prespecified constraints. This problem has been solved in the literature with several approaches from small to medium sized problems. However, few efforts have dealt with large scale problems very common in massive scenarios (big cities or highly-populated regions). In this study, a new distributed algorithm based on the partition of the requests space and the combination of the routes is presented and tested on a set of 24 different scenarios of a large-scale problem (up to 16,000 requests or 32,000 locations) in the city of San Francisco. The results show that, not only the distributed algorithm is able to solve large problem instances that the corresponding sequential algorithm is unable to solve in a reasonable time, but also to have an average improvement of 9% in the smaller problems. The results have been validated by means of statistical procedures proving that the distributed algorithm can be an effective way to solve high dimensional dial-a-ride problems.     

基于条件生成对抗网络的扇区复杂度评估

扇区复杂度作为管制员工作负荷和动态空域配置的重要参考依据，需要事先准确地对其 进行评估。本文针对有监督复杂度数据集存在的小样本问题，提出基于条件生成对抗网络的扇 区复杂度评估框架。首先，构建交通流量、航空器性能和潜在冲突这3类复杂度指标，并结合主观 复杂度等级得到标定样本；其次，利用条件生成对抗网络设计有标记样本生成算法，获得增广数 据集；最后，分别采用逻辑回归、支持向量机和随机森林算法建立复杂度评估模型。以中南区域 扇区为例，从定性和定量的视角验证生成样本的有效性，并在多种训练集配置下对比各模型评估 结果。研究结果表明：条件生成对抗网络在200次迭代后逐步收敛至稳定；生成样本与真实样本 的绝大多数指标在均值上的相对误差小于5%，在标准差上的相对误差大于5%；在多分类评价指 标下，增广数据集对3种模型整体评估精度分别提升11.77%、11.04%和8.34%。本文提出的评估 框架可以在有限数据条件下提高样本多样性，是解决扇区复杂度评估问题的一种有效方法。     

基于不确定理论的常规公交车辆调度优化

为提高公交车的利用效率，本文将公交车辆调度方案划分为高峰型和平峰型。在考虑乘 客候车时间与站间运行时间不确定的现实条件下，综合考虑不同车型的运营成本和乘客候车成 本；基于不确定理论建立混合车型下的双重不确定多目标规划模型，并通过遗传算法的python编 码求解。以南昌市211路公交上行为例，进行sumo仿真结果表明：在保证公交持续运营的前提 下，调整车辆调度方案有助于降低成本和提高运行效率；在高峰期，将发车间隔降低25%，公交车 统一使用纯电动客车，总成本降低5%，平均延误减少4%；平峰期，总成本降低10%，平均延误降 低3%。两组仿真结果发现，考虑不确定因素的公交车辆合理调度安排有利于充分利用公交车辆 资源和提高运行效率。     

Association rule learning to improve deficiency inspection in port state control

ABSTRACT

The inspection of foreign ships in national ports is a critical measure in port state control (PSC), preventing substandard ships from entering national ports. Multifarious inspection items, limited inspection time and inspector manpower are challenging PSC inspection. This research applies data mining to analyze historical PSC inspection records in Taiwan’s major ports to extract potential valuable information for PSC onboard inspections. Using the Apriori Algorithm, the analysis identifies many useful association rules among PSC deficiencies in terms of specific ship characteristics, such as ship types, societies, and flags. The general rules identified show that the items ‘Water/Weathertight conditions’ and ‘Fire safety’ are significantly related. Besides, in the analysis of the various ship types, several different rules are found. After comparing the analysis of ship types and ship societies, it can be observed that the association rules for specific ship types, such as oil tankers, have a better effect than those for individual ship societies do. These identified rules can not only help inspectors effectively spot the associated deficiencies, but also improve the efficiency of PSC inspection. The ports other than Taiwan’s ports can apply a similar analysis method to identify corresponding association rules suitable for their own inspections.     

基于遗传算法的军用飞机智能起降调度方法研究

计及军用飞机起降过程中的时间窗口约束和尾流间隔约束条件,基于遗传算法建立了军用飞机智能起降调度的数学模型。飞机队列顺序采用整数染色体编码方案,依据初始化种群、求解适应度函数和轮盘赌方式的选择操作,并配合相应的交叉、变异算子,对军用飞机航班规划问题进行了求解和优化。通过仿真计算,并与其他调度方法进行对比分析,验证和说明了所采用的模型和算法的有效性。     

面向服务的P2P模型研究与设计

随着网络规模以及应用范围的不断扩大,C/S模式面临的中心压力大、单点失效等问题日趋突出;P2P模式具有分布性、易拓展、负载均衡等优势,赢得了广泛关注,但P2P模式在服务提供和控制上还存在不足.文中引入SOA思想,在P2P模式下设计分布式服务模型;借鉴Petri-net中模型描述和控制的思想对服务组合控制模式进行改进;采用改进的遗传算法对不同性能的服务节点进行选择,提高服务提供质量.通过实验验证,该方法对提高系统性能和服务效率具有重要意义.     

基于连续图谱的船舶吃水及纵倾优化

为解决船舶压载工况下的配载吃水和纵倾优化问题,对船舶压载工况的营运特点进行分析,给出考虑船舶吃水、纵倾、航速及主机功率等因素的多目标问题优化模型;针对大量离散试验和计算数据难以有效分析及优化求解的问题,提出基于空间二元拉格朗日插值算法的吃水、纵倾、主机功率三维连续图谱构建方法,并选取一艘典型散货船,通过图谱优化计算输出其最佳工况参数;最后通过实船海试验证该研究的有效性和实用性。