A Reinforcement Learning-Based Pantograph Control Strategy for Improving Current Collection Quality in High-Speed Railways

受电弓 强化学习 悬链线 计算机科学 最大化 火车 功率(物理) 增强学习 模拟 工程类 人工智能 数学优化 地图学 量子力学 结构工程 机械工程 数学 物理 地理
作者
Hui Wang,Zhiwei Han,Wenqiang Liu,Yan‐Bo Wu
出处
期刊:IEEE transactions on neural networks and learning systems [Institute of Electrical and Electronics Engineers]
卷期号:35 (5): 5915-5928 被引量:13
标识
DOI:10.1109/tnnls.2022.3219814
摘要

In high-speed railways, the pantograph-catenary system (PCS) is a critical subsystem of the train power supply system. In particular, when the double-PCS (DPCS) is in operation, the passing of the leading pantograph (LP) causes the contact force of the trailing pantograph (TP) to fluctuate violently, affecting the power collection quality of the electric multiple units (EMUs). The actively controlled pantograph is the most promising technique for reducing the pantograph-catenary contact force (PCCF) fluctuation and improving the current collection quality. Based on the Nash equilibrium framework, this study proposes a multiagent reinforcement learning (MARL) algorithm for active pantograph control called cooperative proximity policy optimization (Coo-PPO). In the algorithm implementation, the heterogeneous agents play a unique role in a cooperative environment guided by the global value function. Then, a novel reward propagation channel is proposed to reveal implicit associations between agents. Furthermore, a curriculum learning approach is adopted to strike a balance between reward maximization and rational movement patterns. An existing MARL algorithm and a traditional control strategy are compared in the same scenario to validate the proposed control strategy's performance. The experimental results show that the Coo-PPO algorithm obtains more rewards, significantly suppresses the fluctuation in PCCF (up to 41.55%), and dramatically decreases the TP's offline rate (up to 10.77%). This study adopts MARL technology for the first time to address the coordinated control of double pantographs in DPCS.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
54132123完成签到,获得积分10
刚刚
1秒前
上官若男应助XuChen采纳,获得10
1秒前
1秒前
英姑应助科研通管家采纳,获得10
1秒前
1秒前
大个应助科研通管家采纳,获得30
2秒前
脑洞疼应助科研通管家采纳,获得10
2秒前
完美世界应助科研通管家采纳,获得10
2秒前
2秒前
无花果应助科研通管家采纳,获得10
2秒前
大模型应助科研通管家采纳,获得10
2秒前
英俊的铭应助科研通管家采纳,获得10
2秒前
2秒前
小二郎应助科研通管家采纳,获得10
2秒前
赘婿应助科研通管家采纳,获得10
2秒前
我是老大应助科研通管家采纳,获得10
2秒前
JamesPei应助科研通管家采纳,获得10
2秒前
Jasper应助科研通管家采纳,获得10
2秒前
科研通AI5应助科研通管家采纳,获得10
2秒前
ying应助zhencheng采纳,获得10
2秒前
小二郎应助科研通管家采纳,获得10
2秒前
2秒前
科目三应助科研通管家采纳,获得10
2秒前
Hello应助科研通管家采纳,获得10
3秒前
Leon应助科研通管家采纳,获得20
3秒前
今后应助科研通管家采纳,获得10
3秒前
3秒前
3秒前
3秒前
焦糖栗子怪完成签到,获得积分10
3秒前
蒋50完成签到,获得积分10
5秒前
5秒前
和平港湾发布了新的文献求助10
5秒前
独特的紫蓝完成签到,获得积分10
5秒前
6秒前
6秒前
admin发布了新的文献求助10
6秒前
科研通AI5应助lll采纳,获得10
7秒前
7秒前
高分求助中
Continuum thermodynamics and material modelling 3000
Production Logging: Theoretical and Interpretive Elements 2700
Healthcare Finance: Modern Financial Analysis for Accelerating Biomedical Innovation 2000
Population Genetics 1000
Unseen Mendieta: The Unpublished Works of Ana Mendieta 1000
Theory of Block Polymer Self-Assembly 750
지식생태학: 생태학, 죽은 지식을 깨우다 700
热门求助领域 (近24小时)
化学 医学 材料科学 生物 工程类 有机化学 生物化学 纳米技术 内科学 物理 化学工程 计算机科学 复合材料 基因 遗传学 物理化学 催化作用 细胞生物学 免疫学 电极
热门帖子
关注 科研通微信公众号,转发送积分 3494642
求助须知:如何正确求助?哪些是违规求助? 3080022
关于积分的说明 9162200
捐赠科研通 2773078
什么是DOI,文献DOI怎么找? 1521777
邀请新用户注册赠送积分活动 705540
科研通“疑难数据库(出版商)”最低求助积分说明 702919