基于施工天窗日的重载铁路货运量预测

doi:10.3969/j.issn.1673-4440.2025.01.004

铁路通信信号工程技术 ›› 2025, Vol. 22 ›› Issue (1): 28-34,83.DOI: 10.3969/j.issn.1673-4440.2025.01.004

基于施工天窗日的重载铁路货运量预测

周瑾^1，2，刘子扬^1，2，刘永壮^1，2，马锐^1，2

1．北京全路通信信号研究设计院集团有限公司，北京 100070；
2．列车自主运行智能控制铁路行业工程研究中心, 北京 100070

收稿日期:2024-01-27 修回日期:2024-10-10 出版日期:2025-01-25 发布日期:2025-01-25
通讯作者: 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:
国家重点研发计划资助项目（2023YFB3907300）；中国神华能源股份有限公司科研项目（SHGF-22-02）

Prediction of Heavy-Haul Railway Freight Volume Considering Days of Track Possession for Construction Purposes

Zhou Jin^{1, 2}, Liu Ziyang^{1, 2}, Liu Yongzhuang^{1, 2}, Ma Rui^{1, 2}#br#

#br#

1. CRSC Research & Design Institute Group Co., Ltd., Beijing 100070, China；
2. Engineering Research Center of Railway Industry of Intelligent and Autonomous Train Control, Beijing 100070, China

Received:2024-01-27 Revised:2024-10-10 Online:2025-01-25 Published:2025-01-25

摘要/Abstract

摘要： 货运量是重载铁路运输日常管理最重要的指标之一，基于重载铁路运输大数据分析平台，针对重载铁路货运生产调度中每日货运量预测的问题，考虑不同线路施工天窗对货运量的影响，构建基于LSTM的货运量预测模型。建立某厂矿铁路集团、子公司货运量预测数据集，基于施工天窗信息特点对LSTM模型进行改造，通过训练与调参，算法在真实数据集上比ARIMA、原生LSTM、GRU等模型效果提升明显，能较好解决日货运量数据波动大和非平稳性突出的问题。模型效果验证后在综合调度信息系统上线，根据新增数据每日进行推算和展示，减轻了货运统计分析人员的工作负担。

关键词: 重载铁路, 货运量, 长短记忆模型, 施工天窗

Abstract: Freight volume is one of the most important indicators for the daily management of heavy-haul railway transport. Using the big data analysis platform for heavy-haul railways, this paper addresses the issue of daily freight volume prediction in the freight transport production and dispatching activities of heavy-haul railways. Considering the impact of track possession for construction purposes on freight volume for different railway lines, it establishes a freight volume prediction model based on LSTM. Using the freight-volume prediction datasets established for a certain railway group company in the mining industry and its subsidiary companies, this paper also modifies the LSTM model by leveraging the information and characteristics of track possession for construction purposes. Through training and parameter adjustment, the proposed model achieves significant performance improvements compared with such models as ARIMA, original LSTM and GRU when tested on the real datasets. It can effectively address the challenges of large fluctuation and notable instability in daily freight volume data. After effectiveness verification, the proposed model is deployed in the comprehensive dispatching information system. It performs daily calculations and displays result updates based on additional data, thereby reducing the workload of freight statistics analysts.

Key words: , heavy-haul railway, freight volume, LSTM, track possession for construction purposes

中图分类号:

U249.1⁺3

周瑾, 刘子扬, 刘永壮, 马锐. 基于施工天窗日的重载铁路货运量预测[J]. 铁路通信信号工程技术, 2025, 22(1): 28-34,83.

Zhou Jin, Liu Ziyang, Liu Yongzhuang, Ma Rui. Prediction of Heavy-Haul Railway Freight Volume Considering Days of Track Possession for Construction Purposes[J]. Railway Signalling & Communication Engineering, 2025, 22(1): 28-34,83.

图/表 5

参考文献

[1]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.
[2]倪继娜，张巍，张栋.大秦铁路煤炭运输需求分析与预测[J].铁道货运，2020，38（1）：49-54.
Ni Jina, Zhang Wei, Zhang Dong. A Study on the Analysis and Forecast of Coal Transportation Demand on Datong-Qinhuangdao Railway[J]. Railway Freight Transport, 2020, 38(1): 49-54.
[3]何西健.胶州铁路物流中心运量预测研究[J].铁道运输与经济，2020，42（7）：97-102.
He Xijian. Freight Volume Forecast of Jiaozhou Railway Logistics Center[J]. Railway Transport and Economy, 2020, 42(7): 97-102.
[4]余姣姣.基于SVM的铁路货运站装车数预测[J].物流技术，2019，38（3）：38-42.
Yu Jiaojiao. Prediction on Car Loading Quantities of Railway Freight Stations Based on SVM[J]. Logistics Technology, 2019, 38(3): 38-42.
[5]陈鹏芳，孟建军，李德仓，等.基于改进LSSVM模型的区域铁路货运量预测[J].铁道运输与经济，2022，44（2）：59-65.
Chen Pengfang, Meng Jianjun, Li Decang, et al. Forecast of Regional Railway Freight Volume Based on Improved LSSVM Model[J]. Railway Transport and Economy, 2022, 44(2): 59-65.
[6]张英贵，杨蕙瑜，雷定猷.基于组合输入ES-GA-BP的中欧班列货运量预测[J].深圳大学学报(理工版)，2022，39（2）：168-176.
Zhang Yinggui, Yang Huiyu, Lei Dingyou. Freight Volume Forecast of China Railway Express Based on ES-GA-BP with Combined Input[J]. Journal of Shenzhen University (Science and Engineering), 2022, 39(2): 168-176.
[7]程肇兰，张小强，梁越.基于LSTM网络的铁路货运量预测[J].铁道学报，2020，42（11）：15-21.
Cheng Zhaolan, Zhang Xiaoqiang, Liang Yue. Railway Freight Volume Prediction Based on LSTM Network[J]. Journal of the China Railway Society, 2020, 42(11): 15-21.
[8]谭雪，张小强.基于GRU深度网络的铁路短期货运量预测[J].铁道学报，2020，42（12）：28-35.
Tan Xue, Zhang Xiaoqiang. GRU Deep Neural Network Based Short-Term Railway Freight Demand Forecasting[J]. Journal of the China Railway Society, 2020, 42(12): 28-35.
[9]郭洪鹏，刘斌，肖尧.基于Bi-LSTM网络的铁路短期货运量预测研究[J].铁道货运，2022，40（2）：52-58.
Guo Hongpeng, Liu Bin, Xiao Yao. Short-Term Railway Freight Volume Prediction Based on Bi-LSTM Network[J]. Railway Freight Transport, 2022, 40(2): 52-58.
[10]杨丽，吴雨茜，王俊丽，等.循环神经网络研究综述[J].计算机应用，2018，38（Z2）：1-6，26.
Yang Li, Wu Yuxi, Wang Junli, et al. Research on Recurrent Neural Network[J]. Journal of Computer Applications, 2018, 38(Z2): 1-6, 26.
[11] Hochreiter S, Schmidhuber J. Long Short-Term Memory[J]. Neural Computation, 1997(9): 1735-1780.
[12] Chung J, Gulcehre C, Cho K, et al. Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling[EB/OL]. 2014: 1412.3555.https://arxiv.org/abs/1412.3555v1
[13] Sutskever I, Vinyals O, Le Q V. Sequence to Sequence Learning with Neural Networks[J]. Advances in Neural Information Processing Systems, 2014(4): 3104-3112.
[14] Kim T, Kim J, Tae Y, et al. Reversible Instance Normalization for Accurate Time-Series Forecasting Against Distribution Shift[C]. International Conference on Learning Representations, 2022.
[15]刘秋成.铁路货运增量调度指挥优化对策[J].铁道货运，2020，38（9）：1-5，11.
Liu Qiucheng. Strategy of Optimizing Traffic Control in Freight Traffic Volume Increase[J]. Railway Freight Transport, 2020, 38(9): 1-5, 11.
[16]谢玉霞.铁路局调度日计划协同编制过程建模研究[J].铁道运输与经济，2015，37（1）：22-28.
Xie Yuxia. Study on Process Modeling of Coordinative Drawing in Daily Shift Traffic Plan by Railway Administration[J]. Railway Transport and Economy, 2015, 37(1): 22-28.
[17]汤银英，朱星龙，李龙.基于SARIMA模型的铁路月度客运量预测[J].交通运输工程与信息学报，2019，17（1）：25-32.
Tang Yinying, Zhu Xinglong, Li Long. Monthly Railway Passenger Traffic Volume Forecasting Based on SARIMA Model[J]. Journal of Transportation Engineering and Information, 2019, 17(1): 25-32.
[18]汤兆平，孙剑萍，杜相，等.基于ARIMA模型的N铁路局管内物流需求预测研究[J].经济问题探索，2014（7）：76-81.
Tang Zhaoping, Sun Jianping, Du Xiang, et al. Research on Forecasting Logistics Demand in N Railway Bureau Based on ARIMA Model[J]. Inquiry into Economic Issues, 2014(7): 76-81.
[19]章敏敏，徐和平，王晓洁，等.谷歌TensorFlow机器学习框架及应用[J].微型机与应用，2017，36（10）：58-60.
Zhang Minmin, Xu Heping, Wang Xiaojie, et al. Application of Google TensorFlow Machine Learning Framework[J]. Microcomputer & Its Applications, 2017, 36(10): 58-60.
[20]刘磊，徐效宁，李辉，等.车站站名与电务设备相关数据的关联性研究[J].铁路通信信号工程技术，2023，20（5）：1-5，20.
Liu Lei, Xu Xiaoning, Li Hui, et al. Study on Association between Railway Station Name and Signaling Equipment Data[J]. Railway Signalling & Communication Engineering, 2023, 20(5): 1-5, 20.

基于施工天窗日的重载铁路货运量预测

Prediction of Heavy-Haul Railway Freight Volume Considering Days of Track Possession for Construction Purposes

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 9

编辑推荐

Metrics

本文评价

[1]	张万强. 基于群组运行控制的列车追踪间隔时间计算方法[J]. 铁路通信信号工程技术, 2025, 22(2): 24-31.
[2]	谢生智. 基于北斗的重载铁路列控系统临时限速系统方案安全性分析[J]. 铁路通信信号工程技术, 2025, 22(1): 44-50,140.
[3]	阳晋. 基于模态分析法的群组列车牵引供电系统并联谐振频率研究[J]. 铁路通信信号工程技术, 2024, 21(5): 1-7.
[4]	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.
[5]	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.
[6]	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.
[7]	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.
[8]	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.
[9]	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.