摘要
针对国内地铁车站客流无序性和突发性的现状,提出基于广义回归神经网络GRNN的地铁车站客流预警模型。以南京地铁全线网某时段客流数据为输入样本,运用GRNN神经网络进行训练与测试,得出预测数据并对比实际数据进行误差分析。结果表明:预测数据拟合,精度可行。将预测数据与南京地铁实时客流预警系统相结合,提出突发性大客流应急情况下的运营服务对策措施,为地铁运营管理单位避免突发大客流造成人员踩踏、恐慌等事故提供参考。
A passenger flow warning model was introduced on the basis of the generalized regression neural network （GRNN） to solve the problems of disorder and sudden passenger flows in Chinese metro stations. The AFC data of Nanjing Metro was taken as an example and the GRNN model was used for data training and testing. The error analysis of predicted data and actual data was compared. Results showed that the predicted data was fitting to the actual ones and the accuracy is ensured. The countermeasures were derived from the predicted data and the real- time passenger flow warning system of Nanjing metro. The research will provide a reference for metro operation and management companies to avoid stampede accidents arising from sudden passenger flows.
出处
《都市快轨交通》
北大核心
2016年第3期37-41,共5页
Urban Rapid Rail Transit
基金
广西壮族自治区教育厅科研基金项目(2014YB565)
关键词
地铁
神经网络
误差分析
客流预警
对策
metro
neural network
error analysis
passenger flow warning
countermeasure
