粗糙—神经网络在高速列车运行调整决策的应用  

Application of Rough-neural Network in High-speed Train Operation Adjustment Decision

作　　者：李浩然 彭其渊[1,2] LI Haoran;PENG Qiyuan(School of Transportation and Logistics,Southwest Jiaotong University,Chengdu 611756,China;National and Local Joint Engineering Laboratory for Comprehensive Transportation,Chengdu 610031,China)

机构地区：[1]西南交通大学交通运输与物流学院,四川成都611756 [2]综合交通运输智能化国家地方联合工程实验室,四川成都611756

出　　处：《综合运输》2024年第2期116-121,共6页China Transportation Review

摘　　要：列车运行调整自动化是智能高铁建设的重要内容,建立准确快速的列车运行调整决策选择模型具有重要研究意义。本文提出基于粗糙集—径向基函数(RBF)神经网络的列车运行调整决策选择方法,利用粗糙集对列车运行数据进行处理,得到最小决策属性集,构建RBF神经网络进行数据的训练,以得到较为准确的列车运行调整策略选择模型。以武广高铁中部分列车运行数据进行训练和测试,证明了算法的实用性,效率和准确性都得到了提升,在列车运行调整决策中有更好的应用效果。Automatic train operation adjustment is an important part of intelligent high-speed railway construction.It is of great significance to establish accurate and fast train operation adjustment decision selection model.Therefore,this paper proposes a train operation adjustment decision selection method based on rough set and radial basis function(RBF)neural network.The train operation data is processed by rough set processing,and the minimum decision attribute set is obtained.Then the RBF neural network is constructed to train the data,so as to obtain a more accurate train operation adjustment measurement strategy selection model.It is proved that the practicability,efficiency and accuracy of the algorithm have been improved by training and testing on the running data of some trains in Wu-Guangzhou high-speed Railway,and it has a better application effect in the decision-making of train operation adjustment.

关 键 词：高速铁路 列车运行调整 粗糙集 RBF神经网络 决策选择 

分 类 号：U491[交通运输工程—交通运输规划与管理]