| 基于AHP和ANN的不同车型收费系数确定 |
| |
| 引用本文： | 贺向阳,张庆年,丁涛.基于AHP和ANN的不同车型收费系数确定[J].武汉理工大学学报(交通科学与工程版),2007,31(1):137-139,179. |
| |
| 作者姓名： | 贺向阳 张庆年 丁涛 |
| |
| 作者单位： | 武汉理工大学交通学院,武汉,430063 |
| |
| 摘 要： | 不同车型收费系数反映了不同车型用户承担收费公路通行费的比价关系,合理的收费系数,应该实现责任和效益的双重公平.在建立影响不同车型收费费率的指标体系前提下,综合考虑定量和定性因素,分别建立了关于道路破坏和级差效益指标的两个BP神经网络,利用层次分析法,构造BP网络的输入和输出样本,通过训练获得稳定的网络结构和权重,然后输入不同车型代表性指标值,确定不同车型的收费系数.实验表明,该方法不仅理论上可行,而且实践上得到了不同车型收费系数的合理取值区间.
|
| 关 键 词： | 指标体系 层次分析法 BP神经网络 收费系数 |
| 修稿时间： | 2006-11-11 |
A Mixed AHP-ANN Method to Determine Toll Rate Coefficient |
| |
| He Xiangyang,Zhang Qingnian,Ding Tao.A Mixed AHP-ANN Method to Determine Toll Rate Coefficient[J].journal of wuhan university of technology(transportation science&engineering),2007,31(1):137-139,179. |
| |
| Authors: | He Xiangyang Zhang Qingnian Ding Tao |
| |
| Institution: | School of Transportation, Wuhan University of Technology, Wuhan 430063 |
| |
| Abstract: | Different toll rate coefficient should reflect that how much toll falls on different vehicle class users in order to achieve equality of cost and profits.Taking into account of both objective and subjective factors,road cost and user profits index system is established.Then analytic Hierarchy Process and BP Neural Network are used to determine toll rate coefficients.Experiments show that this method is not only reasonable and feasible,but also has good effects. |
| |
| Keywords: | index system AHP method BP Neural Network toll rate coefficient |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
