Research on operation optimization of heavy-haul combined trains in long and steep downhill sections based on reinforcement learning

WANG Jianhua; WANG Chunyi; ZENG Zhou; WANG Cong; WANG Qingyuan; YANG Hang

doi:10.13890/j.issn.1000-128X.2023.06.017

您当前的位置：

首页 >

文章列表页 >

Research on operation optimization of heavy-haul combined trains in long and steep downhill sections based on reinforcement learning

Intelligent Technology | 更新时间：2024-08-02

- Research on operation optimization of heavy-haul combined trains in long and steep downhill sections based on reinforcement learning
- Electric Drive for Locomotives Issue 6, Pages: 139-146(2023)
- 作者机构：
  
  1.国能朔黄铁路发展有限责任公司，河北肃宁　062350
  2.西南交通大学电气工程学院，四川成都;611756
- 作者简介：
- 基金信息：
- DOI：10.13890/j.issn.1000-128X.2023.06.017
  CLC： U292.92⁺1
- Published：10 November 2023，
  
  Received：09 September 2022，
  
  Revised：26 October 2023，
- 稿件说明：
扫描看全文
王建华, 王春毅, 曾周, 等. 基于强化学习的重载组合列车长大下坡操纵优化研究[J]. 机车电传动, 2023(6): 139-146.

WANG Jianhua, WANG Chunyi, ZENG Zhou, et al. Research on operation optimization of heavy-haul combined trains in long and steep downhill sections based on reinforcement learning[J]. Electric drive for locomotives,2023(6): 139-146.
王建华, 王春毅, 曾周, 等. 基于强化学习的重载组合列车长大下坡操纵优化研究[J]. 机车电传动, 2023(6): 139-146. DOI： 10.13890/j.issn.1000-128X.2023.06.017.

WANG Jianhua, WANG Chunyi, ZENG Zhou, et al. Research on operation optimization of heavy-haul combined trains in long and steep downhill sections based on reinforcement learning[J]. Electric drive for locomotives,2023(6): 139-146. DOI： 10.13890/j.issn.1000-128X.2023.06.017.

摘要

针对2万t重载组合列车在长大下坡区段列车纵向冲动大，以及连续循环空气制动操纵困难的问题，文章基于数据驱动算法，设计了一种适用于长编组重载组合列车的长大下坡区段操纵优化方法。该方法考虑了不同列车间、同一列车不同制动系统状态间空气制动特性的差异，利用神经网络对列车在不同操作状态下的空气制动性能变化规律进行学习，得到空气制动力预测模型；而后基于强化学习设计重载组合列车操纵优化算法，以速度跟随性为目标建立奖励函数，考虑列车牵引/电制动特性、列车管制动及缓解时间、限速、运行平稳性等约束条件，应用强化学习方法开展重载组合列车长大下坡操纵策略优化。基于实车数据验证空气制动仿真模型与操纵优化算法的可行性与合理性。结果表明，文章建立的空气制动力预测模型对列车运行中空气制动系统性能具有良好的预测作用，优化操纵控制策略相较于司机驾驶能够有效地减小列车运行中的纵向冲动与最大车钩力，保障列车运行安全。

Abstract

To mitigate longitudinal impulse and address challenge posed by continuous air braking operations in long and steep downhill sections for 20 000-ton heavy haul combined trains

this paper proposes an approach for operation optimization of such trains featuring a long formation in such sections based on a data-driven algorithm. An air braking force prediction model was developed based on neural network learning focusing on the variation rules of air braking performance across different operating states

to incorporate differences in air braking characteristics across different trains and varied braking system states on same trains. Then

an operation optimization algorithm was designed

establishing a reward function that prioritized speed following features

based on reinforcement learning. This algorithm incorporated constraints including train traction/electric braking characteristics

braking application and release times of train pipes

speed limits

and operational smoothness

to optimize the operation strategy for heavy-haul combined trains in long and steep downhill sections by reinforcement learning. The proposed air braking simulation model and operation optimization algorithm were verified using data collected from operation of real trains

confirming their feasibility and rationality. The results show the effectiveness of the proposed air braking force prediction model in predicting performance of air braking systems on running trains. Compared to manual driving

the optimized operation strategy plays an effective role in reducing longitudinal impulse and maximum coupler force to ensure the safety during train operation.

关键词

重载组合列车空气制动长大下坡神经网络强化学习重载铁路

Keywords

heavy-haul combined trainair brakinglong and steep downhillneural networkreinforcement learningheavy-haul rallway

references

蒋立干. 不同操作模式下重载列车长大下坡道曲线地段行车性能分析[D]. 北京: 北京交通大学, 2017.

JIANG Ligan. Analysis on the operation performance of heavy haul trains under different operating modes[D]. Beijing: Beijing Jiaotong University, 2017.

魏玉晓, 李宵寅. 铁路长大下坡道列车周期制动参数的分析及应用[J]. 铁道运输与经济, 2017, 39(10): 67-72.

WEI Yuxiao, LI Xiaoyin. Analysis and application of train cycle braking parameters on the long steep descending grade[J]. Railway transport and economy, 2017, 39(10): 67-72.

KHMELNITSKY E. On an optimal control problem of train operation[J]. IEEE transactions on automatic control, 2000, 45(7): 1257-1266.

LIU Rongfang, GOLOVITCHER I M. Energy-efficient operation of rail vehicles[J]. Transportation research part A: policy and practice, 2003, 37(10): 917-932.

BAI Baoxue, XIAO Zhuang, WANG Qingyuan, et al. Multi-objective trajectory optimization for freight trains based on quadratic programming[J]. Transportation research record, 2020, 2674(11): 466-477.

王悉. 基于机器学习的重载列车智能驾驶方法研究[D]. 北京: 北京交通大学, 2017.

WANG Xi. Machine learning based intelligent operation methods for heavy haul train[D]. Beijing: Beijing Jiaotong University, 2017.

孙中央, 王长明. 长大下坡道区段开行重载列车的安全问题[J]. 铁道机车车辆, 2009, 29(1): 4-7.

SUN Zhongyang, WANG Changming. Security problems of operation heavy haul trains on the long heavy down grade[J]. Railway locomotive & car, 2009, 29(1): 4-7.

王自力. 列车节能运行优化操纵的研究[J]. 西南交通大学学报, 1994, 29(3): 275-280.

WANG Zili. An optimal operating method of train running for saving energy[J]. Journal of southwest Jiaotong university, 1994, 29(3): 275-280.

陈清, 王自力. 机车动力制动对操纵方式及限制坡度的影响[J]. 西南交通大学学报, 2005, 40(4): 448-452.

CHEN Qing, WANG Zili. Influences of locomotive dynamic brake on brake operation and limiting grade[J]. Journal of southwest Jiaotong university, 2005, 40(4): 448-452.

耿志修, 李学峰, 张波. 大秦线重载列车运行仿真计算研究[J]. 中国铁道科学, 2008, 29(2): 88-93.

GENG Zhixiu, LI Xuefeng, ZHANG Bo. Simulation study of heavy haul train operation on Datong—Qinhuangdao railway[J]. China railway science, 2008, 29(2): 88-93.

张波. 重载组合列车牵引及制动系统的试验与仿真研究[D]. 北京: 中国铁道科学研究院, 2009.

ZHANG Bo. Test and simulation study on traction and brake system of combined heavy haul train[D]. Beijing: China Academy of Railway Sciences, 2009.

魏伟, 王强. 坡道上重载列车纵向冲动研究[J]. 振动与冲击, 2014, 33(5): 143-148.

WEI Wei, WANG Qiang. Influence of train brake on longitudinal impulse of a heavy haul train passing through a ramp[J]. Journal of vibration and shock, 2014, 33(5): 143-148.

刘嘉, 杨相健, 罗世辉, 等. 朔黄铁路重载列车线路适应性仿真研究[J]. 振动、测试与诊断, 2020, 40(4): 673-679.

LIU Jia, YANG Xiangjian, LUO Shihui, et al. Heavy-haul-train line adaptability simulation of Shuohuang railway[J]. Journal of vibration, measurement and diagnosis, 2020, 40(4): 673-679.

温军刚. 朔黄铁路两万吨重载列车平稳操纵优化方案[J]. 中国高新科技, 2019(6): 58-60.

WEN Jungang. An optimal scheme of smooth operation of the 20,000-ton heavy haul train of Shuohuang railway[J]. China high-tech, 2019(6): 58-60.

魏伟, 张益铭. 2万吨重载组合列车操纵优化研究[J]. 铁道机车车辆, 2021, 41(4): 35-40.

WEI Wei, ZHANG Yiming. Operating optimization study of 20,000-ton heavy haul combined train[J]. Railway locomotive & car, 2021, 41(4): 35-40.

Views

下载量

CSCD

CNKI被引量

Alert me when the article has been cited

提交

Tools

Publicity Resources

Research on the influence of quantity of 20 000-ton heavy-haul train wagons on longitudinal impulse

A study on the influence of communication state of wireless coupling system on heavy haul train and its operation

Nonlinear compensation-based self-positioning method for rail transit train

Research on strong and weak evaluation method of air brake for intelligent driving heavy haul train

A Method of Determining Blocking Voltage of SiC MOSFET Based on the Neural Network Predict Model

Related Author

WANG Kaiyun

CHEN Zhe

RAN Xiangrui

HU Xiaoyu

ZENG Zhou

WEI Wei

AN Erjing

ZHU Jichao

Related Institution

CRRC Zhuzhou Locomotive Co., Ltd.

State Key Laboratory of Rail Transit Vehicle System, Southwest Jiaotong University

Rolling Stock Branch, CHN ENERGY Shuohuang Railway Development Co., Ltd., Suning

CHN ENERGY Baoshen Railway Group Co., Ltd.

Vehicle Development Department, CRRC Taiyuan Co., Ltd.

⁰