基于BP神经网络的铁路客运服务质量评价研究  

Railway Passenger Service Quality Evaluation Based on BP Neural Network

作　　者：杨国元[1] 史天运[1] 张秋亮[1] 

机构地区：[1]中国铁道科学研究院电子计算技术研究所,北京100081

出　　处：《交通运输系统工程与信息》2016年第5期33-38,44,共7页Journal of Transportation Systems Engineering and Information Technology

基　　金：国家自然科学基金(61374059);中国铁道科学研究院基金项目(J2015DZ015)~~

摘　　要：为了客观、准确地评价铁路客运服务质量,从旅客感知角度出发,构建了评价指标体系,建立了BP神经网络求解模型,提出了基于BP算法的铁路客运服务质量评价算法.通过对网络的训练,使得网络输出达到了期望的精度,满足了客运服务质量评价的要求.最后通过对铁路旅客的调查问卷实例,从均方误差、统计识别率方面进行了分析、仿真,对客运服务质量进行综合评价,并与模糊综合评价法进行了对比.实验结果表明,本文构建的评价指标体系科学、合理,提出的评价算法收敛速度快、误差小,评价结果能够有效地反映客运服务质量水平,为提高和改进铁路客运服务质量提供参考依据.In order to objectively and accurately evaluate the railway passenger service quality, an evaluation system is built from the perspective of passenger perception. Railway passenger service quality evaluated algorithm and BP evaluated network model of solving are built based on BP algorithm. Through the network training, the network output reached a desired accuracy and met the requirements of passenger service quality evaluation. Finally, through the railway passenger questionnaire examples, it is analyzed and simulated from the aspects of the mean square error, statistical the recognition rate. Passenger service quality is comprehensive evaluated and compared with fuzzy comprehensive evaluation method. Experimental results show that the evaluation index system built is scientific and reasonable.The convergence is faster and the error is smaller of evaluation algorithm proposed. It can effectively reflect the quality of passenger service and provide reference for advancing and improving passenger service quality.

关 键 词：铁路运输 BP神经网络 客运服务质量 评价体系 评价指标 

分 类 号：U292.4[交通运输工程—交通运输规划与管理]