数据与决策协同的长江航运多式联运优化研究

doi:10.16097/j.cnki.1009-6744.2026.02.002

交通运输系统工程与信息 ›› 2026, Vol. 26 ›› Issue (2): 11-23.DOI: 10.16097/j.cnki.1009-6744.2026.02.002

数据与决策协同的长江航运多式联运优化研究

王静¹，雷德明²，翟静¹，陈淑楣¹，刘林凡^*3

1. 长江航运发展研究中心，武汉430014；2.武汉理工大学，自动化学院，武汉430070； 3. 华东交通大学，电气与自动化工程学院，南昌330000

收稿日期:2025-11-26 修回日期:2026-01-26 接受日期:2026-02-04 出版日期:2026-04-25 发布日期:2026-04-20
作者简介:王静（1996—），女，湖北咸宁人，中级工程师，博士。
基金资助:
国家自然科学基金(72171054)；江西省教育厅科学技术研究项目(GJJ2400501)。

Optimization of Yangtze River Multimodal Transport Based on Joint Data and Decision-Making

WANG Jing^¹, LEI Deming^², ZHAI Jing^¹, CHEN Shumei^¹, LIU Linfan^*³

1. Yangtze River Shipping Development Research Center, Wuhan 430014, China; 2. School of Automation, Wuhan University of Technology, Wuhan 430070, China; 3. School of Electrical and Automation Engineering, East China Jiaotong University, Nanchang 330000, China

Received:2025-11-26 Revised:2026-01-26 Accepted:2026-02-04 Online:2026-04-25 Published:2026-04-20
Supported by:
National Natural Science Foundation of China (72171054)；Scientific Research Project of the Jiangxi Provincial Department of Education (GJJ2400501)。

摘要/Abstract

摘要： 对长江航运多式联运系统开展协同优化研究，有助于提升航运效率，实现降本增效与低碳发展。本文针对长江航运多源数据质量差与动态决策难的问题，构建融合混合数据预处理与强化学习的两阶段协同优化框架。首先，依据小样本趋势、序列性和统计性数据特征，分别采用灰色预测、插值与均值填补方法进行针对性治理，为后续决策提供高质量输入；进而，基于预处理后的数据，建立以强化学习为核心的动态决策模型，通过12维状态空间与复合奖励函数，实现对路径与方式组合的实时智能优化。基于2019—2024年长江干线实际数据的验证结果显示，该框架相较传统方法，实现社会物流总成本降低16.8%，碳减排成本节约20.16亿元，且收敛更快。实验结果可为在复杂数据环境下，提升长江航运系统效能提供可靠的决策支持。

关键词: 综合交通运输, 协同优化, 数据驱动决策, 长江航运, 灰色预测模型, 强化学习

Abstract: This paper proposes a collaborative optimization method for the Yangtze River multimodal transport system to help improve efficiency while reducing costs and carbon emissions. To address challenges of data quality and dynamic decision making, this study introduces a two-stage collaborative framework with hybrid data preprocessing and reinforcement learning. First, based on the characteristics of small-sample trend data, sequential data, and statistical data, grey prediction, interpolation, and mean imputation methods are respectively used for targeted data governance, that can provide high-quality input for subsequent decision-making. Then, a dynamic decision-making model is developed with reinforcement learning as the core component. The real-time intelligent optimization of path and mode combinations is realized through a 12-dimensional state space and a composite reward function. The proposed method was validated using the actual operational data from 2019 to 2024. The results show that the proposed model reduces total logistics costs by 16.8%, saves RMB 2.016 billion in carbon emissions, and converges faster compared to conventional methods. The experimental results can provide reliable decision support for enhancing the efficiency of the Yangtze River shipping system in complex data environments.

Key words: integrated transportation, collaborative optimization, data-driven decision-making, Yangtze River shipping, grey prediction model, reinforcement learning

中图分类号:

U116.2

王静, 雷德明, 翟静, 陈淑楣, 刘林凡. 数据与决策协同的长江航运多式联运优化研究[J]. 交通运输系统工程与信息, 2026, 26(2): 11-23.

WANG Jing, LEI Deming, ZHAI Jing, CHEN Shumei, LIU Linfan. Optimization of Yangtze River Multimodal Transport Based on Joint Data and Decision-Making[J]. Journal of Transportation Systems Engineering and Information Technology, 2026, 26(2): 11-23.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://www.tseit.org.cn/CN/10.16097/j.cnki.1009-6744.2026.02.002

http://www.tseit.org.cn/CN/Y2026/V26/I2/11

参考文献

[1]Council of Supply Chain Management Professionals. 35th Annual State of Logistics Report[R]. Chicago: CSCMP, 2024.

[2]范煜君，张亚．日本海上能源运输通道安全战略、法律保障及对我国的启示[J]．中国水运，2022, 22(9): 22-24． [FAN Y J, ZHANG Y. Japan's maritime energy transport corridor security strategy, legal safeguards and implications for China[J]. China Water Transport, 2022, 22(9): 22-24.]

[3] NAYAK N, SARMAH S P, JENAMANI M. A shippers' perspective multimodal freight transportation analysis considering shallow-draft inland waterways[J]. Computers & Industrial Engineering, 2024, 187: 109793.

[4]朱孟尧,张培林.基于荆江航道整治工程的水运比较效益研究[J]. 物流技术,2018,37(2): 84-86. [ZHU M Y, ZHANG P L. Study on comparative benefit of waterway transport based on Jingjiang waterway regulation project [J]. Logistics Technology, 2018, 37(2): 84-86.]

[5]李魁梅,郑波.考虑综合运输成本的多式联运路径优化问题[J]. 工业工程, 2020, 23(5): 67-74. [LI K M, ZHENG B. A research on the route optimization of multimodal transport considering comprehensive transport cost[J]. Industrial Engineering, 2020, 23(5): 67 74.]

[6] 刘松,舒文,彭勇,等.双重不确定下应急物资多式联运可靠路径优化[J].交通运输系统工程与信息,2023, 23(1): 58-66. [LIU S, SHU W, PENG Y, et al. Optimization of reliable routes for multimodal transport of emergency supplies under dual uncertainty[J]. Journal of Transportation Systems Engineering and Information Technology, 2023, 23(1): 58-66.]

[7]LU Y P, GAO G. Multi-attribute collaborative optimization for multimodal transportation based on user preferences[J]. Applied Sciences, 2025, 15(10): 5512.

[8]HAN B, CHI Y X, XU Y, et al. Multimodal transport scheme optimization and capacity allocation considering customer classification[J]. IEEE Transactions on Intelligent Transportation Systems, 2025, 26(3): 1-14.

[9] 刘柏阳,刘立刚.灰色预测模型在区域物流成本中的应用研究[J]. 会计之友, 2018, 23: 23-26. [LIU B Y, LIU L G. Application of grey prediction model in regional logistics costs[J]. Friends of Accounting, 2018, 23: 23-26.]

[10] 适越通,秦华,白成昊,等.混合灰色预测模型HGM(1, 1)[J]. 山东理工大学学报(自然科学版), 2022, 36(3): 82-86. [SHI Y T, QIN H, BAI C H, et al. Hybrid grey prediction model HGM(1,1) [J]. Journal of Shandong University of Technology(Natural Science Edition), 2022, 36(3): 82-86.]

[11] 向亚红, 张峰,邓念武,等.基于分形插值与支持向量机混合模型的大坝变形分析[J].中国农村水利水电, 2023(1): 185-188, 193. [XIANG Y H, ZHANG F, DENG N W, et al. Dam deformation analysis based on hybrid model of fractal interpolation and support vector machine [J]. China Rural Water and Hydropower, 2023(1): 185 188, 193.]

[12] 武丹婕.考虑多因素的中欧集装箱多式联运路径选择研究[D]. 南昌: 华东交通大学, 2024. [WU D J. Research on route selection of China-Europe container multimodal transport considering multiple factors[D]. Nanchang: East China Jiaotong University, 2024.]

[13] 余珏,丁一,林国龙.港口集装箱装卸作业的Q-learning 动态定价策略研究[J]. 计算机应用与软件,2018,35 (12): 123-130. [YU J, DING Y, LIN G L. The strategy of dynamic pricing of handling operation for port container based on Q-learning[J]. Computer Applications and Software, 2018, 35(12): 123-130.]

[14] 彭理群,罗明波,卢赫，等.基于Q-learning的定制公交跨区域路径规划研究[J].交通运输系统工程与信息, 2020, 20(1): 104-110. [PENG L Q, LUO M B, LU H, et al. Cross-regional customized bus path planning based on Q-learning[J]. Journal of Transportation Systems Engineering and Information Technology, 2020, 20(1): 104-110.]

[15] 韩忻辰,俞胜平,袁志明,等.基于Q-learning的高速铁路列车动态调度方法[J].控制理论与应用,2021,38 (10): 1511-1521. [HAN X C, YU S P, YUAN Z M, et al. High-speed railway dynamic scheduling based on Q learning method[J]. Control Theory & Applications, 2021, 38(10): 1511-1521.]

数据与决策协同的长江航运多式联运优化研究

Optimization of Yangtze River Multimodal Transport Based on Joint Data and Decision-Making

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	王清斌, 梁瑛昊, 郑建风. 考虑时间不确定的东北亚—欧洲多式联运路径优化[J]. 交通运输系统工程与信息, 2026, 26(2): 1-10.
[2]	黄兆察, 蒋林桥, 王志美, 陈军华, 张星臣. 面向电煤保供的采购成本与铁水联运协同优化方法[J]. 交通运输系统工程与信息, 2026, 26(2): 24-34.
[3]	赵媛, 石柏松, 王丹. 考虑船舶到港延误的班列时刻表优化[J]. 交通运输系统工程与信息, 2026, 26(2): 35-46.
[4]	谷远利, 宇泓儒, 陈龙, 邓社军, 陆文琦. 网联自动驾驶车辆专用车道动态宏微观协同部署方法[J]. 交通运输系统工程与信息, 2026, 26(2): 125-136.
[5]	孙健, 纪裕伟, 于珂伟, 李子豪, 赵昱霖. 融合双注意力机制的快速路协同深度强化学习方法[J]. 交通运输系统工程与信息, 2026, 26(2): 137-147.
[6]	王鑫伟, 许琰, 孙立山. 基于灵活编组策略的列车时刻表与车厢分配协同优化研究[J]. 交通运输系统工程与信息, 2026, 26(2): 221-231.
[7]	吴暖, 林婷, 王晚香. 东北海陆大通道运输网络关键节点识别与抗毁性分析[J]. 交通运输系统工程与信息, 2026, 26(1): 2-10.
[8]	王福建, 马佳豪, 李廷浩, 马东方. 混合交通环境下基于动态决策间隔的强化学习信号控制方法[J]. 交通运输系统工程与信息, 2026, 26(1): 45-54.
[9]	李琼, 林若雪, 汪勇杰, 陈艳. 面向多目标的旅游客运车辆生态驾驶策略优化[J]. 交通运输系统工程与信息, 2026, 26(1): 205-216.
[10]	李小静, 袁静, 秦怡豪. 定制客运动态乘降点与车辆路线联合优化[J]. 交通运输系统工程与信息, 2026, 26(1): 228-238.
[11]	宋丽英, 邓琨琦, 宁武, 宋海涛, 李四维. 进口集装箱堆存决策的两阶段强化学习方法[J]. 交通运输系统工程与信息, 2026, 26(1): 283-294.
[12]	陈德启, 张自设, 张文会, 闫学东, 蒋贤才. 面向高层建筑应急救援的无人机螺旋搜索轨迹控制方法[J]. 交通运输系统工程与信息, 2025, 25(6): 87-100.
[13]	王江锋, 宋之凡, 李云飞, 齐崇楷, 闫学东, 李青山. 面向集中供给与稀疏需求场景的网约车调度优化算法[J]. 交通运输系统工程与信息, 2025, 25(5): 280-290.
[14]	马飞虎, 陈晓燕, 孙翠羽, 田星彤. 高速公路收费站动态车道配置的在线优化方法[J]. 交通运输系统工程与信息, 2025, 25(5): 333-342.
[15]	张鹏, 李兴旺, 姬炳豪, 孙超, 李文权. 路口重复放行的公交与社会车辆协同绿波优化模型[J]. 交通运输系统工程与信息, 2025, 25(4): 53-62.