计算机集成制造系统 ›› 2022, Vol. 28 ›› Issue (3): 735-744.DOI: 10.13196/j.cims.2022.03.008

• • 上一篇    下一篇

基于交路接续规律的动车组运营里程预测算法

贾丹龙1,2,刘峰1,2+,张宁1,2,张春1,2,高畅霞1,2,郝伟1,2,3   

  1. 1.北京交通大学计算机与信息技术学院
    2.北京交通大学高速铁路网络管理教育部工程研究中心
    3.中车青岛四方机车车辆股份有限公司信息技术部
  • 出版日期:2022-03-31 发布日期:2022-03-25
  • 基金资助:
    国家863计划资助项目(2015AA043701)。

Algorithm of EMU operating mileage prediction based on routing connection law

  • Online:2022-03-31 Published:2022-03-25
  • Supported by:
    Project supported by the National High-Tech.R&D Program,China(No.2015AA043701).

摘要: 为了实现高精度的动车组运营里程预测,提出一种新的以交路接续规律为依据的动车组运营里程预测算法。首先,将数据记录时间作为分段参数,提出用分段函数的形式为动车组历史开行数据附加时间权重。然后,根据动车组历史开行数据中的交路接续情况,结合时间权重,将交路转移概率矩阵作为交路接续规律的载体,并考虑新交路的情况对矩阵进行修正。最后,基于交路转移概率矩阵中的概率值,以随机的方式实现了动车组的交路接续预测。实验结果表明,与传统的日均里程法相比,所提算法在预测准确率和预测结果稳定性上均有显著提升。

关键词: 动车组, 里程预测, 高级修计划, 交路转移概率矩阵

Abstract: To achieve high precision mileage prediction of Electrical Multiple Units (EMU),a new mileage prediction algorithm of EMU based on the routes connection law was presented.The data recording time was taken as the piecewise parameter,and the piecewise function was proposed to attach the time weight to the history operating data of EMU.According to the situation of routing connection in the history data and combining with the time weight,a transportation probability matrix of routes as the carrier of the routes connection law was proposed,and the matrix considering the situation of new routes was revised.Based on the probability value of the routes' transportation probability matrix,the routes prediction was realized in a random way.Experiments showed that compared with the traditional daily average mileage method,the proposed algorithm had significantly improved the prediction accuracy and stability of the prediction results.

Key words: electrical multiple units, mileage prediction, high-level maintenance planning, transportation probability matrix of routes

中图分类号: