基于时空特性和组合深度学习的交通流参数估计

为深入挖掘交通流时空特性,提高交通流参数估计精度,基于深度学习提出一种交通流参数估计的组合方法.根据目标断面及其上游断面的交通流数据构造输入矩阵,利用卷积神经网络捕捉交通流的空间特性,使用长短期记忆和门控循环神经网络挖掘交通流的时间特性,组合3种深度学习方法所得输出,得到交通流参数估计值.采用中国安徽省合肥市和美国加州...     

基于多时间尺度的城市轨道交通短时OD估计

基于状态空间模型构建了城市轨道交通短时OD估计的多模型组合方法,估计早晚高峰期间15 min内进站客流的去向目的站.组合模型以不同时间尺度下的进站客流分流率为状态变量,并利用历史数据预估其中通勤客流的分流率,然后通过交互多模型算法加权融合不同时间尺度下的分流率估计结果.以北京地铁为案例,研究表明:早高峰期间的15 min分流率估计误差的平均值和最大值分别为16.4%和21.8%,晚高峰期间分别为22.7%和24.6%,比既有文献的估计误差减小了约一半.本文的研究成果可为实时的线网客流分布预测提供更准确的输入数据,以辅助运营管理部门实现客流预警和应急响应.     

黄土沟壑区湿软路基沉降预测模型

为合理考虑路基沉降预测时诸多影响因素的不确定性与随机性,提出基于神经网络范例推理的路基沉降预测模型。以同类工程的成功经验为基础,建立了基于神经网络的沉降范例检索模型,在范例相似度计算中,引入归一化效用函数,通过神经网络的学习,建立当前沉降范例与沉降源范例之间的相似关系,最终实现当前沉降范例的沉降预测。对黄土沟壑区湿软路基沉降预测结果表明,该模型具有较高的预测准确性,预测值与实测值绝对误差小于10%。     

湿式离合器出油口甩出油温度预测方法

为了实现对湿式离合器出油口甩出油温度传感器的冗余校验和自我诊断，提出了一种基于粒计算约简的离合器出油口甩出油温度的模糊预测方法。首先分析出油口甩出油温度的影响因素，将主要影响因素作为预测输入量，并采用模糊推理理论预测当前离合器出油口甩出油温度。在设计模糊预测方法的过程中，通过分析实车数据得到车辆行驶时离合器处于高滑摩功率过程和低滑摩功率过程的不同特性，分别确定相对应的隶属度函数和模糊预测规则，从而进一步提高出油口甩出油温的预测精度。为了提高模糊预测算法的实时性，基于模糊预测规则创建模糊决策表，模糊输入量和模糊输出量分别作为决策表的条件属性集与决策属性集。利用粒计算理论对模糊决策表的条件属性集进行属性约简，通过削减冗余信息有效降低模糊输入量和模糊预测规则的个数。最后利用实车采集的数据对比分析约简前后模糊预测算法的单步运行时间和预测误差等性能指标。试验结果表明：基于粒计算约简的模糊预测算法能够有效保障预测精度，同时拥有更少的模糊预测规则数和模糊输入量，有效解决了模糊预测算法占用资源较多以及实用性较差的问题。     

Optimizing the locations of electric taxi charging stations: A spatial–temporal demand coverage approach

Vehicle electrification is a promising approach towards attaining green transportation. However, the absence of charging stations limits the penetration of electric vehicles. Current approaches for optimizing the locations of charging stations suffer from challenges associated with spatial–temporal dynamic travel demands and the lengthy period required for the charging process. The present article uses the electric taxi (ET) as an example to develop a spatial–temporal demand coverage approach for optimizing the placement of ET charging stations in the space–time context. To this end, public taxi demands with spatial and temporal attributes are extracted from massive taxi GPS data. The cyclical interactions between taxi demands, ETs, and charging stations are modeled with a spatial–temporal path tool. A location model is developed to maximize the level of ET service on the road network and the level of charging service at the stations under spatial and temporal constraints such as the ET range, the charging time, and the capacity of charging stations. The reduced carbon emission generated by used ETs with located charging stations is also evaluated. An experiment conducted in Shenzhen, China demonstrates that the proposed approach not only exhibits good performance in determining ET charging station locations by considering temporal attributes, but also achieves a high quality trade-off between the levels of ET service and charging service. The proposed approach and obtained results help the decision-making of urban ET charging station siting.     

Chaotic movement of vortices in superconductors of high-Tc superconducting maglev system at a high speed

Vortex motion in superconductors of higb-Tc superconducting maglev system is studied by a computational simulation.The vortex system is treated in a similar fashion,as a system where defects arc arrang...     

基于知识工程的自升式钻井平台方案设计方法

针对目前自升式钻井平台方案设计特点,引入知识工程的理念,建立面向对象的知识表达方法及基于实例和规则的混合推理机制,采用参数化设计方法进行特征驱动,在快速生成设计方案的同时对设计进行检验并提出建议,使设计人员的工作重点从数据处理转移到对设计对象的分析上来.开发了原型系统,证明了该方法的有效性和实用性.     

一种燃气轮机状态监测和故障诊断专家系统的研究

介绍了一种燃气轮机状态监测和故障和故障诊断专家系统。提出了产生式规则和框架相结合的知识表示方法；合理地组织了知识库，并提供了较完善的知识库管理功能；实现了该诊断问题中故障严重程度和可信度两种模糊概念的推理；建造了适合本问题的正、反向混合推理机。     

A week in the life of baby boomers: how do they see the spatial–temporal organization of their activities and travel?

In this paper, we take an initial look at the spatial and temporal flexibility in the activity patterns of the so-called “baby-boomer” cohort (born 1947–1966) in comparison with younger and older adults. Using a unique longitudinal survey carried in Quebec City from 2002 to 2005, we explore activity patterns and trip rates over a seven-day observation period during the first wave, and take a first look at some aspects of their evolution over two subsequent waves at about one-year intervals. We model the propensity to undertake activities within selected conventional non-work classifications such as “shopping” and “leisure”, and also according to respondents’ own perceptions of the spatial and temporal flexibility of each out-of-home activity that they had executed. While we cannot strictly separate cohort effects from age-related effects, after controlling for gender and household structure, we infer that age and related lifestyle effects dominate in explaining these propensities. However, the boomers were the only age stratum to increase their total out-of-home activity participation over the course of the panel, an intriguing starting point for the future study of this cohort.

����ģʽ�ij��н�ͨ״̬�����������о�

首先选用较多的交通参数,设计提出了基于聚类方法的细粒度交通模式划分算法,将交通模式划分为较多的类别。结合实际数据,进行了实验,在四个路段参数的基础上,划分得到了十类交通模式。这其中都用到了模糊集合划分和定性推理。使用状态核确定一系列模式,随后系统状态被划分成若干个模式。提出了模式转移方程来描述在定性推理基础之上的状态转移,并从模式转移的角度进一步研究了系统的稳定性。一个城市交通系统的应用实例显示了本文提出方法的有效性,可以看出细粒度交通模式划分要比粗粒度有更多的优势,同时得出了聚类算法在细粒度交通模式划分中的劣势。