铁路钢轨网格化维修规划优化编制模型  

Optimal Maintenance Planning Model for Railway Rail Grids

作　　者：白磊[1,2] 贾传峻 李擎[1] 刘仍奎[1] 孙全欣[1] BAI Lei;JIA Chuan-jun;LI Qing;LIU Reng-kui;SUN Quan-xin(School of Traffic and Transportation,Beijing Jiaotong University,Beijing 100044,China;Beijing E-Hualu Information Technology Co.,Ltd.,Beijing 100043,China)

机构地区：[1]北京交通大学交通运输学院,北京100044 [2]北京易华录信息技术股份有限公司,北京100043

出　　处：《交通运输系统工程与信息》2018年第4期171-177,共7页Journal of Transportation Systems Engineering and Information Technology

基　　金：国家自然科学基金(51578057);中央高校基本科研业务费专项资金(2017RC026)~~

摘　　要：优化编制铁路钢轨维修规划,对管理者合理利用维修资源、确保铁路行车安全具有重要意义.本文基于铁路基础设施网格化管理思想,按照一定规则将线性、连续的铁路钢轨设备,分割为等长的小区段,这些小区段称为钢轨网格.以钢轨网格为基本对象,采用多阶段指数Markov模型,个性化描述钢轨网格状态变化规律;在此基础上,采用Markov决策过程方法,以规划周期内的期望总成本最小为目标函数,建立基于状态的维修策略模型,确定一个较长规划周期内的最优维修策略.作者采用了陇海线实际数据对提出模型的有效性进行了验证,计算结果表明,本文提出的模型优于基于阈值的中国铁路既有的管理方法.Optimal maintenance planning is of great significance for managers to allocate resource properly and ensure the railway traffic safety.Using the grid-based management theory for railway infrastructure,a railway line is divided into adjacent segments of the same specific length.Each segment is termed a“rail grid”.Rail grids are the subjects of this paper.Employing the multi-stage exponential Markov model,the degradation law of each rail grid is obtained.Markov decision process is employed to establish a condition-based maintenance policy model,and find optimal maintenance policies over a finite planning horizon.The objective is to minimize the total expected cost.Actual data for the Longhai Railway is used to verify the proposed model.The proposed model is superior to the threshold-based China Railway's existing management methods.

关 键 词：铁路运输 铁路钢轨 维修规划 网格化 MARKOV决策过程 

分 类 号：U216.2[交通运输工程—道路与铁道工程]