基于随机森林结合前向序列选择算法的铁路隧道防水板检测数据关键影响因素识别北大核心

针对参数特征复杂度高的铁路产品,提出了一种基于随机森林(RF)结合前向序列选择(SFS)算法的铁路产品检验检测数据关键影响因素识别方法,以辅助基于经验的识别方法。创新使用RF-SFS算法,将其应用于铁路隧道防水板检验检测数据关键影响因素的识别研究。根据多年铁路隧道防水板检测数据,建立RF模型,获得了影响铁路隧道防水板检测结果的特征关键性评分序列。随后,结合SFS方法得出关键性评分序列的阈值,将排名前6位的影响因素识别为关键特征,模型的预测能力达到99.98%。为验证关键特征识别方法的有效性,对比分析3种模型在使用不同特征子集时的预测能力。当仅选用关键特征时,3种模型的预测能力均达到最佳,加入冗余特征后模型的预测能力逐渐降低。     

公共自行车使用时空特性挖掘及租还需求预测

基于宁波市公共自行车刷卡数据、POI(Point of Interest)数据、气象和空气质量等数据，从数据驱动视角，深入挖掘公共自行车使用的时空特征及站点租还车需求预测。在时间上，采用KMeans算法，将站点聚为5类，探讨各类站点的时变需求规律及影响因素；在空间上，提出基于POI 数据的站点用地类型识别方法，将站点分为居住类、交通设施类、办公类和商业休闲类。构建以 15，30，60 min 为间隔，以租还车需求为目标变量的随机森林预测模型，并与常用的 BP (Back Propagation)神经网络、K最近邻方法进行比较。结果表明，随机森林模型的精度更高，适用性更强。以30 min为间隔的站点租还车需求预测精度最高，考虑站点土地利用类型后能有效提高模型的预测精度。本文结果可作为未来站点平衡调度的依据并推广应用于共享单车系统，为改善服务水平提供技术和理论支撑。     

Statistical Approaches to Mapping QTL of Dynamic Traits

Dynamic traits are those that change with timein the development process of life or other quanti-tative factor (e. g. environmental condition).These traits also are called infinite-dimensionalcharacters by Kirkpatrick and Heckman[1]andfunction-valued traits by Pletcher and Geyer[2], be-cause they can be expressed as a function of someindependent and continuous variables. Dynamictraits are collected at many time points during thecourse of life. Therefore, studies of dynamic traitsare regarded…     

基于模糊可靠性理论的高速线材轧辊优化设计研究

工作时受交变应力的作用,高速线材轧辊断裂问题时有发生.文章利用模糊可靠性理论,探讨在随机变量和模糊变量组合时轧辊的模糊可靠性设计方法.设计实例和生产实践证实了该方法具有优化设计的效果,使轧辊使用寿命显著提高.     

基于虚拟样机技术的机车车辆钢弹簧疲劳寿命研究

机车车辆在轨道上运行时,线路的不平顺及车轮的变形会使悬挂装置受到各种有害冲击。断裂和应力松弛是机车车辆钢弹簧最常见的失效形式,有研究证明弹簧断裂绝大部分都是因疲劳引起的。发生松弛失效的弹簧没有及时更换,会给列车的安全运行埋下隐患,引发严重的行车事故。运用多体动力学软件SIMPACK建立整车模型．提取弹簧随机载荷谱,通过疲劳分析软件FE—Safe对某电力机车二系悬挂钢弹簧进行随机疲劳寿命分析,对轨道车辆钢弹簧寿命预测及确定更换周期具有一定的工程实用价值。     

Real-time trip purpose prediction using online location-based search and discovery services

The use of smartphone technology is increasingly considered a state-of-the-art practice in travel data collection. Researchers have investigated various methods to automatically predict trip characteristics based upon locational and other smartphone sensing data. Of the trip characteristics being studied, trip purpose prediction has received relatively less attention. This research develops trip purpose prediction models based upon online location-based search and discovery services (specifically, Google Places API) and a limited set of trip data that are usually available upon the completion of the trip. The models have the potential to be integrated with smartphone technology to produce real-time trip purpose prediction. We use a recent, large-scale travel behavior survey that is augmented by downloaded Google Places information on each trip destination to develop and validate the models. Two statistical and machine learning prediction approaches are used, including nested logit and random forest methods. Both sets of models show that Google Places information is a useful predictor of trip purpose in situations where activity- and person-related information is uncollectable, missing, or unreliable. Even when activity- and person-related information is available, incorporating Google Places information provides incremental improvements in trip purpose prediction.     

A new model for temporal–spatial stochastic analysis of vehicle–track coupled systems

The vehicle–track coupled system has a random nature in the time–space domain. This paper proposes a computational model to analyse the temporal–spatial stochastic vibrations of vehicle–track systems, where the vehicle–track system is divided into a vehicle subsystem, track subsystem, and interfacial subsystem between the wheel and rail. In this model, the time-varying randomicity of dynamical parameters of the vehicle system, correlation, and randomness of the track structural parameters in the time–space joint dimensions, and randomness of the track random irregularities are considered. A probability dimension-reduction method was used to randomly combine different random variables. Furthermore, the probability density evolution method was applied to solve the delivery problem of probabilities between excitation inputs and response outputs. The temporal–spatial stochastic vibrations of the vehicle–track system with different coefficients of variation were studied, in which we assumed that the dynamic parameters obeyed the normal distribution, and the stochastic simulation method of the track random irregularities is probed into. The calculated results from this model are consistent with the actual measured results and physical conceptions. Thus, the temporal–spatial stochastic evolutionary mechanism can be explored, and the limits of dynamic indices can be formulated by using this developed model.     

海堤内坡种植防护林的安全影响分析及尺度论证

海堤从外海堤脚至内侧护堤之间的滩涂围垦空间,既是陆地边缘,也是水的边缘。外侧可构建滨海景观,内侧结合随塘河形成亲水景观,具有得天独厚的优势。内侧平台的防护林及景观有机结合,可构建人们休闲旅游的"黄金绿带"。结合台州某海堤生态提升工程,提出海堤生态提升总体技术方案,重点对海堤内坡种植景观防护林对海堤安全的影响进行分析,明确种植平台高程、尺度布置等主要技术参数,为类似海堤生态改造工程提供参考。     

基于旅游动机的旅游目的地选择行为分析

旅游目的地选择是游客出行决策的核心问题,本文对游客的目的地选择行为进 行了研究.本课题组选取北京市区8个景点,以在京旅游的游客作为研究对象,组织进行了 游客出行行为调查.问卷设计22 项旅游动机,通过对游客旅游动机项提取因子,并对旅游 动机的因子得分进行聚类分析把游客分为4 类.在构建游客旅游目的地选择行为模型时, 对首个目的地和非首个目的地分别建模.模型中引入了旅游动机类型变量,证明旅游动机 对游客目的地选择行为影响显著.另外出行距离在不同阶段对游客目的地选择的影响存 在显著的差异.该模型精度较高,为进一步研究旅游目的地选择行为提供了理论依据.     

考虑随机裂隙的寒区隧道冻胀力研究

研究目的:为进一步研究围岩和衬砌结构的冻胀力,以2022年冬奥会重大交通保障项目金家庄特长螺旋隧道为依托,通过现场实测、室内试验和COMSOL数值模拟相结合的方法,探究考虑随机裂隙条件下,孔隙率、渗透率、随机裂隙孔径和模型下边界水头对冻胀力量值和分布规律的影响. 研究结论:(1)衬砌结构的最大拉、压应力随孔隙率的增大而...