基于Xgboost的铁路货运装卸作业时间预测

doi:10.3969/j.issn.1673-4440.2024.03.007

铁路通信信号工程技术 ›› 2024, Vol. 21 ›› Issue (3): 36-41.DOI: 10.3969/j.issn.1673-4440.2024.03.007

基于Xgboost的铁路货运装卸作业时间预测

周瑾¹，王文斌²，刘子扬¹，刘永壮¹

1．北京全路通信信号研究设计院集团有限公司，北京 100070；
2．中国神华能源股份有限公司，北京 100040

收稿日期:2023-05-29 修回日期:2024-03-06 出版日期:2024-03-25 发布日期:2024-03-25
作者简介:周瑾（1994—），女，工程师，硕士，主要研究方向：数据挖掘，邮箱：zhoujin@crscd.com.cn。
基金资助:
中国神华重载铁路运输大数据分析平台研究项目（SHGF-22-02）

Loading and Unloading Time Estimation Based on Xgboost for Railway Freight Transport

Zhou Jin¹, Wang Wenbin², Liu Ziyang¹, Liu Yongzhuang¹

1. CRSC Research & Design Institute Group Co., Ltd., Beijing 100070, China;
2. China Shenhua Energy Co., Ltd., Beijing 100040, China

Received:2023-05-29 Revised:2024-03-06 Online:2024-03-25 Published:2024-03-25

摘要/Abstract

摘要： 传统方法推算货运装卸作业时间直接使用站细里的标准时间，难以刻画复杂因素影响下作业时间的变化情况，准确率较低。通过数据挖掘的方法，收集铁路综调信息系统记录的货运装卸作业相关数据，利用增强决策树模型Xgboost学习装卸作业相关影响因素对其作业时间的影响，实现货运装卸作业时间预测，对比基线模型准确率提升明显，能更有效辅助车流推算与运行图自动编制。

关键词: 重载铁路, 货运作业, 装卸作业时间, 决策树, Xgboost

Abstract: The traditional method of loading and unloading time prediction of freight transport, which directly utilizes the standard time specified in the Detailed Instructions Governing Train Operation at Station, cannot properly characterize the time change under the impacts of complex factors, and achieves low prediction accuracy. This paper utilizes the data mining method to gather the relevant data on the loading and unloading time of freight transport from the railway integrated dispatching information system. It also utilizes the boosted decision tree model Xgboost to predict the loading and unloading time of freight transport. Compared with the reference model, the proposed model can achieve substantial improvement in prediction accuracy, and provide more effective support for traffic flow prediction and automatic drawing of train operation charts.

Key words: heavy haul railway, freight transport, loading and unloading time, decision tree, Xgboost

中图分类号:

U294.27

周瑾, 王文斌, 刘子扬, 刘永壮. 基于Xgboost的铁路货运装卸作业时间预测[J]. 铁路通信信号工程技术, 2024, 21(3): 36-41.

Zhou Jin, Wang Wenbin, Liu Ziyang, Liu Yongzhuang. Loading and Unloading Time Estimation Based on Xgboost for Railway Freight Transport[J]. Railway Signalling & Communication Engineering, 2024, 21(3): 36-41.

图/表 5

参考文献

[1]刘结平.神华铁路调度信息系统建设方案研究[J].铁路通信信号工程技术，2018，15（10）：25-31.
Liu Jieping. Construction Scheme of Train Dispatching Information System of Shenhua Company[J]. Railway Signalling & Communication Engineering, 2018, 15(10): 25-31.
[2]宋宗莹，王文斌，刘子扬，等.重载铁路运输大数据分析平台架构设计研究[J].铁路通信信号工程技术，2023，20（11）：44-49.
Song Zongying, Wang Wenbin, Liu Ziyang, et al.Design and Research on Architecture of Big Data Analytics Platform in Heavy-haul Railway Transportation[J]. Railway Signalling & Communication Engineering, 2023, 20(11): 44-49
[3]李静，康巍.基于微服务架构的国家能源集团铁路货运营销与调度系统研究[J].铁道运输与经济，2022，44（Z1）：176-182.
Li Jing, Kang Wei. Research on Railway Freight Marketing and Dispatching System of National Energy Group Based on Micro-Service Architecture[J]. Railway Transport and Economy, 2022, 44(Z1): 176-182.
[4]李志兵，王文泓，许扬.铁路货运枢纽综合自动化系统设计[J].铁路通信信号工程技术，2022，19（1）：7-11.
Li Zhibing, Wang Wenhong, Xu Yang. Design of Integrated Automation System of Railway Freight Hub[J]. Railway Signalling & Communication Engineering, 2022, 19(1): 7-11.
[5]付立斌.多维空间下的列车运行图仿真与分析[D].兰州:兰州交通大学，2014.
[6]顾闻.列车运行及货车装载状态智能化检测技术优化[J].铁路通信信号工程技术，2023，20（5）：48-52，56.
Gu Wen. Optimization of Intelligent Detection Technology for Train Operation and Freight Train Loading States[J]. Railway Signalling & Communication Engineering, 2023, 20(5): 48-52, 56.
[7]Breiman L, Friedman J, et al. Classification and Regression Trees[M].Monterey, CA: Wadsworth and Brools, 1984.
[8]方匡南，吴见彬，朱建平，等.随机森林方法研究综述[J].统计与信息论坛，2011，26（3）：32-38.
Fang Kuangnan, Wu Jianbin, Zhu Jianping, et al. A Review of Technologies on Random Forests[J]. Statistics & Information Forum, 2011, 26(3): 32-38.
[9]Friedman J H. Greedy Function Approximation: a Gradient Boosting Machine[J]. The Annals of Statistics, 2001, 29(5): 1189-1232.
[10]Chen Tianqi, Guestrin C. XGBoost: a Scalable Tree Boosting System[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Francisco California USA. ACM, 2016: 785-794.
[11]Ke Guolin, Meng Qi, Finley T, et al. LightGBM: a Highly Efficient Gradient Boosting Decision Tree[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. December 4-9, 2017, Long Beach, California, USA. ACM, 2017: 3149-3157.
[12]韩宗垒，徐斌，陈佳.基于神经网络的集装箱船港口作业时间预测模型[J].计算机应用与软件，2021，38（2）：78-84.
Han Zonglei, Xu Bin, Chen Jia. Container Ship Port Operation Time Prediction Model Based on Neural Network[J]. Computer Applications and Software, 2021, 38(2): 78-84.
[13]赵国强，刘亦伟，孙博伦.重载铁路MESH自组网一跳节点空口碰撞算法[J].铁路通信信号工程技术，2022，19（2）：51-54.
Zhao Guoqiang, Liu Yiwei, Sun Bolun.Air Interface Time Slot Collision Probability Algorithm of MESH ad Hoc One-hop Nodes on Heavy-haul Railway[J]. Railway Signalling & Communication Engineering, 2022, 19(2): 51-54.

基于Xgboost的铁路货运装卸作业时间预测

Loading and Unloading Time Estimation Based on Xgboost for Railway Freight Transport

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 5

参考文献

相关文章 6

编辑推荐

Metrics

本文评价

[1]	谢和欢. 基于公网的重载铁路列控系统车-地通信技术研究[J]. 铁路通信信号工程技术, 2024, 21(3): 29-35.
[2]	韩兴邦. 基于北斗的重载铁路列控系统仿真测试系统研究[J]. 铁路通信信号工程技术, 2024, 21(2): 60-66.
[3]	宋宗莹, 王文斌, 刘子扬, 周瑾, 刘永壮. 重载铁路运输大数据分析平台架构设计研究[J]. 铁路通信信号工程技术, 2023, 20(11): 44-49.
[4]	姚胜良, 杨硕, 李继, 马婧雯. 简谈重载铁路道岔转换系统工作状态智能诊断技术[J]. 铁路通信信号工程技术, 2022, 19(5): 17-20.
[5]	马珺杰, 高月明. 铁路货运作业图表系统的设计与实现[J]. 铁路通信信号工程技术, 2022, 19(10): 41-45.
[6]	张利峰, 王春华. 重载铁路移动闭塞计算机联锁系统研究[J]. 铁路通信信号工程技术, 2021, 18(1): 12-18.