基于改进BP算法神经网络的路况评价模型研究

通过利用在BP神经网络中增加反馈信号及偏差单元的网络模型,生成内部回归网络,对BP神经网络进行改进,据此得出改进的BP神经网络的具体步骤.在此基础上,结合陕西省高速公路沥青路面的实际情况建立了路况评价模型,并对该模型的具体应用做了研究.研究结果表明:网络的收敛速度很好,训练结果与实际路况结果相差很小,利用改进BP算法神经网络建立的路况评价模型不仅方便易用,而且精度很高.     

基于可靠性的列车关键部件机会预防性维修优化模型研究

针对列车关键部件预防性维修存在欠维修或过维修问题,在传统预防性维修策略基础上,提出一种基于可靠性的列车关键部件机会预防性维修优化模型,该模型考虑部件可靠性对机会维修阈值的影响,通过偏最小二乘回归方法优化机会维修阈值,求解得出最佳预防性维修役龄和机会维修役龄,综合分析机会役龄因子和安全失效概率因子对维修策略的影响,从而达到优化总维修费用的目标。以某地铁公司B型车辆关键部件的记录数据为例,通过对建立的模型进行求解分析,表明采取该检修模式能有效减少固定维修次数、延长检修周期、降低总维修费用、提高列车正线运营率,从而为轨道交通关键部件修程修制的改进提供科学依据和实践参考。     

基于非参数回归的城轨实时进出站客流预测

为准确预测城轨实时进出站客流,构建基于非参数回归的实时进出站客流预测模型。首先,对不同特征日分时进出站客流量进行对比分析,据此构建历史数据库;其次,通过计算历史分时数据的相关系数,并设置阈值对分时客流数据间的相关性进行判断,从而确定合适的非参数模型状态向量;再次,根据K近邻样本与预测目标的客流量差异性,设计基于权重加权的预测算法;最后利用广州市城轨客流数据对预测模型进行精度分析,对全网站点多天的预测结果显示:全天平均绝对百分比误差均在2%以下,分时平均绝对百分比误差均在14%以下,表明模型具有较高的预测精度和良好的适用性。     

城市轨道交通的牵引能耗估算方法

为解决目前城市轨道交通面临的能源消耗总量过大的问题,以北京轨道交通运营线路能耗数据为基础,分析影响城市轨道交通能耗的主要因素,并通过多元线性回归的方法,建立基于运营数据的牵引能耗估算模型,通过测算与实际运营数据的误差为1.6%;同时将不同城市轨道交通的能耗测算方法进行对比,包括列车单位能耗测算法、电力机车耗电量测算法和单位指标测算法,前两者与估算模型的结果误差不超过5%,验证了模型的可行性;通过单位指标测算法的对比分析,反映出估算指标的不合理性。结果表明,相关对比为既有线路能耗的估算和新建线路能耗的预测提供了参考的方法。     

铁路货运量组合预测方法

为了对铁路货运量进行科学预测,在指数平滑、模糊移动、线性回归、灰色预测4种单一模型的基础上建立组合预测模型.结果表明:组合预测模型能有效综合各模型的有用信息,并能提高其预测精度,预测结果可靠.与单一模型相比,该法具有较好的实用价值.     

改进的K近邻非参数回归在短时交通流量预测中的应用

针对现有K近邻非参数回归方法的局限,为了进一步提高算法的精度和速度,做出了两方面的改进:利用相关性理论选择状态向量和采用基于聚类分析的变K近邻搜索算法.用仿真实验验证了该方法的有效性,给出了仿真试验结果.实例研究结果表明,预测效果优于传统的非参数回归方法.     

����������ͨ�����㷽���о�

诱增交通量是交通需求预测与交通建设项目评价中的重要组成部分.本文从诱增交通量概念出发，从宏观和微观两个角度阐述了区域诱增交通量产生的机理，分析了现行单个建设项目诱增交通量计算思路的局限性，研究提出了基于区域的诱增交通量计算的多元线性回归模型.论文结合我国的国情，对该模型参数进行了标定，提出了符合中国实际的基于区域诱增交通量计算方法.利用北京地区改革开放之后(1978年至2003年)的数据进行了实例分析，得到了道路建设对交通量的近期影响弹性系数0.17,远期影响弹性系数0.29的结果.     

SPSS在拱桥轴线变形观测回归拟合中应用

根据实测获取的桥拱轴线的观测数据,通过应用SPSS程序软件,对桥拱轴线的设计线形进行了拟合,确定了其有关参数和理论数据,使桥梁及其他建筑物的曲线回归、变形分析和精度评定更规律化简单化和高效率,为旧危建筑加固维护,新建筑物施工质量评价,提供了翔实可靠的依据.     

Comparing prediction methods for maritime accidents

ABSTRACT

The purpose of maritime accident prediction is to reasonably forecast an accident occurring in the future. In determining the level of maritime traffic management safety, it is important to analyze development trends of existing traffic conditions. Common prediction methods for maritime accidents include regression analysis, grey system models (GM) and exponential smoothing. In this study, a brief introduction is provided that discusses the aforementioned prediction models, including the associated methods and characteristics of each analysis, which form the basis for an attempt to apply a residual error correction model designed to optimize the grey system model. Based on the results, in which the model is verified using two different types of maritime accident data (linear smooth type and random-fluctuation type, respectively), the prediction accuracy and the applicability were validated. A discussion is then presented on how to apply the Markov model as a way to optimize the grey system model. This method, which proved to be correct in terms of prediction accuracy and applicability, is explored through empirical analysis. Although the accuracy of the residual error correction model is usually higher than the accuracy of the original GM (1,1), the effect of the Markov correction model is not always superior to the original GM (1,1). In addition, the accuracy of the former model depends on the characteristics of the original data, the status partition and the determination method for the status transition matrix.     

Measuring the influence of bus service quality on the perception of users

Encouraging the use of public transport is a key policy goal in many countries. Therefore, public transport should offer the level of quality that accommodates the demands of current users, and importantly, the desires of potential users. This study investigates the influence of the perceived quality of bus service on the perception of both current and potential users. The study draws upon data from 512 questionnaires distributed across Belfast City in the UK. The study utilises a binary logistic regression model to quantify the relationships between the perceived quality of 29 bus indicators (independent) and the perceptions of users towards the overall bus service (dependent). Eleven significant indicators are reported to have significant influence on the perception of users. These indicators are utilised to propose scenarios for optimising the quality of bus service with the perceptions of current and potential users.