基于信令数据的城市群空铁联程客流识别及预测框架

针对城市群空铁联程客流需求获取困难、客流规律难以把握的问题,提出一套集成空铁联程客流识别及预测模块的综合分析框架.首先,考虑交通枢纽的空间范围及旅客出行的时空特征,提出一种基于信令数据的空铁联程客流识别方法,并挖掘其时空分布规律.然后,在双向门控循环神经网络模型(Bidirectional Gated Recurrent Unit,BiGRU)的基础上,引入时间周期编码,构建具有时间周期性的双向门控循环神经网络模型(Temporal-Bidirectional Gated Recurrent Unit,T-BiGRU)对空铁联程客流进行预测.最后,以京津冀城市群为实例,对研究框架进行验证.研究结果表明:京津冀城市群空铁联程客流呈现出明显的聚集分布特征,其中北京南站—天津站—天津滨海机场和北京西站—正定机场站—石家庄正定机场两个场景的联程客流占比最高,超过联程客流总量的65%;T-BiGRU模型可以对联程客流的需求进行精准预测,对两个主要场景的双向联程客流的预测精度均超过了89%,优于多个基线模型.研究结果可为城市群空铁协同发展及空铁联程服务优化提供参考.

基于贝叶斯网的空铁联程乘客出行满意度模型

为揭示空铁联程乘客感知对乘客总体满意度影响情况,建立了包含目标层、中间层以及指标层的三层指标体系,结合GTT(Greedy thick thinning)与EM(Expectation maximization)算法构建了贝叶斯网,分析了9个分类满意度对乘客总体满意度的影响。结果显示,各分类满意度对总体满意度影响从强到弱依次为个性化、衔接性、运营、可靠性、票务、舒适性以及信息服务,可达性与安全性对总体满意度影响甚微。交叉分析结果定量反映了乘客满意度指标间的复杂相互关系。采用重要性-绩效分析法(IPA)定量分析了后续改善策略,得出目前运营班次、行李托运、开通线路、运营时段需要进行重点改善,换乘指示、座椅舒适、取票便捷、票价、换乘质量、信息规划存在过度改善问题。

Investigation of Cross-Correlation Characteristics for Multi-Link Channels in High-Speed Railway Scenarios

This paper investigates the cross-correlation characteristics of large-scale parameters(LSPs) and small-scale fading(SSF) for high-speed railway(HSR) multilink propagation scenarios, based on realistic measurements conducted on Beijing to Tianjin HSR line in China. A long-term evolution-based channel sounding system is utilized in the measurements to obtain the channel data. By applying a proposed time-delay based dynamic partition method, multi-link channel impulse responses are extracted from the raw channel data. Then, the statistical results of LSPs, including shadow fading, K-factor, and root-mean-square delay spread are derived and the cross-correlation coefficients of these LPSs are calculated. Moreover, the SSF spatial correlation and cross-correlation of SSF are analyzed. These results can be used to exploit multi-link channel model and to optimize the next-generation HSR communication system.

高铁时代催生铁路货运新格局

高速铁路的陆续开通,一方面增加了客运能力、提升了客运品质,另一方面也使既有铁路通道能力紧张地区的货运能力得到了较大释放。今年1月至8月,全国铁路货物发送量完成240838万吨,同比增长12.8%,超年进度7824万吨。