基于BP神经网络的西安地铁后全运期客流预测

Prediction of Xi'an Metro Passenger Flow in the Post-National Games Period Based on BP Neural Network

随着全运会等综合性的大规模赛事的成功举办,极大地对外宣传了西安的历史文化与旅游资源,为后全运时期西安的旅游高质量发展带来新机遇和强劲动力。论文基于西安轨道交通的布局现状,分析了后全运时期西安城市轨道交通各线路和各关键换乘站的客流特征,分析了客流量较大的地铁2号线的断面客流特征,并以具有代表性的小寨站为例,对后全运时期一周内的客流时间分布特征以及每日的进、出站小时客流量进行分析。基于BP神经网络的进出站客流时间序列法预测后全运时期小寨站客流情况,设定目标误差为0.001,分析了不同学习速率与误差率关系,确定学习速率,编写Matlab程序代入样本数据,得出了基于BP神经网络的客流预测结果,客流预测结果与实际观测数据接近,能较好的反应小寨站客流量的变化趋势,预测结果为西安地铁的运营管理提供数据参考,更好地打造后全运时期高质量的“轨道+旅游”绿色旅游模式,为这类客流量较大、波动显著、规律性不强的站点客流预测提供参考。

With the successful holding of the National Games and other comprehensive large-scale events,the history,culture and tourism resources in Xi'an have been greatly publicized to the outside world,bringing new opportunities and strong impetus for the high-quality development of tourism in Xi'an during the post-National Games period.Based on the current layout of Xi'an rail transit,this paper analyzes the passenger flow characteristics of each line and key transfer station of Xi'an urban rail transit in the post-National Games period,analyzes the passenger flow characteristics of Metro Line 2 with a large passenger flow,and takes the representative Xiaozhai Station as an example to obtain the passenger flow prediction results based on BP neural network,which are close to the actual observation data.