To realize a better automatic train driving operation control strategy for urban rail trains,an automatic train driving method with improved DQN algorithm(classical deep reinforcement learning algorithm)is proposed as...To realize a better automatic train driving operation control strategy for urban rail trains,an automatic train driving method with improved DQN algorithm(classical deep reinforcement learning algorithm)is proposed as a research object.Firstly,the train control model is established by considering the train operation requirements.Secondly,the dueling network and DDQN ideas are introduced to prevent the value function overestimation problem.Finally,the priority experience playback and“restricted speed arrival time”are used to reduce the useless experience utilization.The experiments are carried out to verify the train operation strategy method by simulating the actual line conditions.From the experimental results,the train operation meets the ATO requirements,the energy consumption is 15.75%more energy-efficient than the actual operation,and the algorithm convergence speed is improved by about 37%.The improved DQN method not only enhances the efficiency of the algorithm but also forms a more effective operation strategy than the actual operation,thereby contributing meaningfully to the advancement of automatic train operation intelligence.展开更多
This paper addresses the control design for automatic train operation of high-speed trains with protection constraints.A new resilient nonlinear gain-based feedback control approach is proposed,which is capable of gua...This paper addresses the control design for automatic train operation of high-speed trains with protection constraints.A new resilient nonlinear gain-based feedback control approach is proposed,which is capable of guaranteeing,under some proper non-restrictive initial conditions,the protection constraints control raised by the distance-to-go(moving authority)curve and automatic train protection in practice.A new hyperbolic tangent function-based model is presented to mimic the whole operation process of high-speed trains.The proposed feedback control methods are easily implementable and computationally inexpensive because the presence of only two feedback gains guarantee satisfactory tracking performance and closed-loop stability,no adaptations of unknown parameters,function approximation of unknown nonlinearities,and attenuation of external disturbances in the proposed control strategies.Finally,rigorous proofs and comparative simulation results are given to demonstrate the effectiveness of the proposed approaches.展开更多
East Japan Railway Company(JR East)is aiming to“realize driverless train operation”as one of the key measures to respond to rapid changes in the business environment.Currently,Automatic Train Operation(ATO)equipment...East Japan Railway Company(JR East)is aiming to“realize driverless train operation”as one of the key measures to respond to rapid changes in the business environment.Currently,Automatic Train Operation(ATO)equipment is not installed on the Shinkansen,but there are plans to introduce ATO or driverless operation in the near future.From 2018-2021,the Ministry of Land,Infrastructure,Transport and Tourism(MLIT)held the“ATO Technology Study Group for Railways”in which the concept of technical requirements necessary for driverless operation was discussed.In 2021,JR East conducted the GOA4 demonstration test on the Joetsu Shinkansen.In this test,we were able to confirm the basic functions of Shinkansen vehicles such as automatic departure control,speed control,fixed position stop control,and remote stop control using ATO.We aim to realize unattended operation(GOA4)for deadhead trains between Niigata Station and the Niigata Shinkansen Rolling Stock Center by the end of the 2020 s,and driverless operation(GOA3)for passenger trains of the Joetsu Shinkansen by the mid-2030s and continue to develop the necessary technologies and build systems.展开更多
On the basis of the first jig separation stage, the relational mathematical model related to ash content and the coutent of coal gangue with a density less than 1. 8 g/cm3 is established. With this model, the discharg...On the basis of the first jig separation stage, the relational mathematical model related to ash content and the coutent of coal gangue with a density less than 1. 8 g/cm3 is established. With this model, the discharge rate of reruse can be adjusted automatically and exactly by the conveutional PI regulator.The control stratedes for water capacity, air pressure, and feed capacity of the jig are introduced.Combined with the Expert system technology, jig expert system (JEP) is developed.展开更多
With rapid development of the railway traffic, the moving block signaling system （MBS） method has become more and more important for increasing the track capacity by allowing trains to run in a shorter time-headway ...With rapid development of the railway traffic, the moving block signaling system （MBS） method has become more and more important for increasing the track capacity by allowing trains to run in a shorter time-headway while maintaining the required safety margins. In this framework, the tracking target point of the following train is moving forward with its leading train. This paper focuses on the energy saving tracking control of two successive trains in MBS. Nonlinear programming method is used to optimize the energy-saving speed trajectory of the following train. The real-time location of the leading train could be integrated into the optimization process. Due to simplicity, it can be used for online implementation. The feasibility and effectiveness are verified through simulation. The results show that the new method is efficient on energy saving even when disturbances present.展开更多
为了提高效率,降低培训成本并推广使用计算机来取代管制模拟机中的飞行员席位,采用集成学习的策略来生成飞行员复诵指令。选用5个大规模预训练语言模型进行微调,并使用K折交叉验证来筛选出性能较好的4个模型作为基础模型来构建集成学习...为了提高效率,降低培训成本并推广使用计算机来取代管制模拟机中的飞行员席位,采用集成学习的策略来生成飞行员复诵指令。选用5个大规模预训练语言模型进行微调,并使用K折交叉验证来筛选出性能较好的4个模型作为基础模型来构建集成学习模型。所构建的集成学习模型在管制指令数据集上取得在本领域中的最优效果。在通用的ROUGE(recall-oriented understudy for gisting evaluation)评价标准中,取得R_(OUGE-1)=0.998,R_(OUGE-2)=0.995,R_(OUGE-L)=0.998的最新效果。其中,R_(OUGE-1)关注参考文本与生成文本之间单个单词的匹配度,R_(OUGE-2)则关注两个连续单词的匹配度,R_(OUGE-L)则关注最长公共子序列的匹配度。为了克服通用指标在本领域的局限性,更准确地评估模型性能,针对生成的复诵指令提出一套基于关键词的评价标准。该评价指标准基于管制文本分词后的结果计算各个关键词指标来评估模型的效果。在基于关键词的评价标准下,所构建模型取得整体准确率为0.987的最优效果,对航空器呼号的复诵准确率达到0.998。展开更多
为提高干线铁路的运输效率和能力,欧洲铁路部门开始研究欧洲列控系统(ETCS)应用自动驾驶(ATO)的可行性。通过分析ETCS系统应用自动驾驶(ATO over ETCS)的研究背景和过程,阐述系统架构、工作原理、自动驾驶的功能需求以及系统规范的架构...为提高干线铁路的运输效率和能力,欧洲铁路部门开始研究欧洲列控系统(ETCS)应用自动驾驶(ATO)的可行性。通过分析ETCS系统应用自动驾驶(ATO over ETCS)的研究背景和过程,阐述系统架构、工作原理、自动驾驶的功能需求以及系统规范的架构体系。同时介绍即将投入运营的ETCS系统应用自动驾驶实例,并分析它们的结构和基本原理。展开更多
为提高高速铁路运输效率和自动化程度,根据珠三角城际铁路CTCS2+ATO列控系统的运用经验,提出高速铁路引入自动驾驶(ATO)的方案。方案采用CTCS+ATO系统结构,根据系统配置分为CTCS+ATO-PFC(Partial Function Configuration)和CTCS+ATO-FFC...为提高高速铁路运输效率和自动化程度,根据珠三角城际铁路CTCS2+ATO列控系统的运用经验,提出高速铁路引入自动驾驶(ATO)的方案。方案采用CTCS+ATO系统结构,根据系统配置分为CTCS+ATO-PFC(Partial Function Configuration)和CTCS+ATO-FFC(Full Function Configuration)两个等级。分别对每个等级的系统功能、地面和车载设备配置进行定义,并提出系统分级实施方案。CTCS+ATO列控系统方案综合考虑我国列控系统的现状和发展方向,为我国高速铁路引入自动驾驶提供参考依据。展开更多
文摘To realize a better automatic train driving operation control strategy for urban rail trains,an automatic train driving method with improved DQN algorithm(classical deep reinforcement learning algorithm)is proposed as a research object.Firstly,the train control model is established by considering the train operation requirements.Secondly,the dueling network and DDQN ideas are introduced to prevent the value function overestimation problem.Finally,the priority experience playback and“restricted speed arrival time”are used to reduce the useless experience utilization.The experiments are carried out to verify the train operation strategy method by simulating the actual line conditions.From the experimental results,the train operation meets the ATO requirements,the energy consumption is 15.75%more energy-efficient than the actual operation,and the algorithm convergence speed is improved by about 37%.The improved DQN method not only enhances the efficiency of the algorithm but also forms a more effective operation strategy than the actual operation,thereby contributing meaningfully to the advancement of automatic train operation intelligence.
基金supported jointly by the National Natural Science Foundation of China(61703033,61790573)Beijing Natural Science Foundation(4192046)+1 种基金Fundamental Research Funds for Central Universities(2018JBZ002)State Key Laboratory of Rail Traffic Control and Safety(RCS2018ZT013),Beijing Jiaotong University
文摘This paper addresses the control design for automatic train operation of high-speed trains with protection constraints.A new resilient nonlinear gain-based feedback control approach is proposed,which is capable of guaranteeing,under some proper non-restrictive initial conditions,the protection constraints control raised by the distance-to-go(moving authority)curve and automatic train protection in practice.A new hyperbolic tangent function-based model is presented to mimic the whole operation process of high-speed trains.The proposed feedback control methods are easily implementable and computationally inexpensive because the presence of only two feedback gains guarantee satisfactory tracking performance and closed-loop stability,no adaptations of unknown parameters,function approximation of unknown nonlinearities,and attenuation of external disturbances in the proposed control strategies.Finally,rigorous proofs and comparative simulation results are given to demonstrate the effectiveness of the proposed approaches.
文摘East Japan Railway Company(JR East)is aiming to“realize driverless train operation”as one of the key measures to respond to rapid changes in the business environment.Currently,Automatic Train Operation(ATO)equipment is not installed on the Shinkansen,but there are plans to introduce ATO or driverless operation in the near future.From 2018-2021,the Ministry of Land,Infrastructure,Transport and Tourism(MLIT)held the“ATO Technology Study Group for Railways”in which the concept of technical requirements necessary for driverless operation was discussed.In 2021,JR East conducted the GOA4 demonstration test on the Joetsu Shinkansen.In this test,we were able to confirm the basic functions of Shinkansen vehicles such as automatic departure control,speed control,fixed position stop control,and remote stop control using ATO.We aim to realize unattended operation(GOA4)for deadhead trains between Niigata Station and the Niigata Shinkansen Rolling Stock Center by the end of the 2020 s,and driverless operation(GOA3)for passenger trains of the Joetsu Shinkansen by the mid-2030s and continue to develop the necessary technologies and build systems.
文摘On the basis of the first jig separation stage, the relational mathematical model related to ash content and the coutent of coal gangue with a density less than 1. 8 g/cm3 is established. With this model, the discharge rate of reruse can be adjusted automatically and exactly by the conveutional PI regulator.The control stratedes for water capacity, air pressure, and feed capacity of the jig are introduced.Combined with the Expert system technology, jig expert system (JEP) is developed.
文摘With rapid development of the railway traffic, the moving block signaling system （MBS） method has become more and more important for increasing the track capacity by allowing trains to run in a shorter time-headway while maintaining the required safety margins. In this framework, the tracking target point of the following train is moving forward with its leading train. This paper focuses on the energy saving tracking control of two successive trains in MBS. Nonlinear programming method is used to optimize the energy-saving speed trajectory of the following train. The real-time location of the leading train could be integrated into the optimization process. Due to simplicity, it can be used for online implementation. The feasibility and effectiveness are verified through simulation. The results show that the new method is efficient on energy saving even when disturbances present.
文摘为了提高效率,降低培训成本并推广使用计算机来取代管制模拟机中的飞行员席位,采用集成学习的策略来生成飞行员复诵指令。选用5个大规模预训练语言模型进行微调,并使用K折交叉验证来筛选出性能较好的4个模型作为基础模型来构建集成学习模型。所构建的集成学习模型在管制指令数据集上取得在本领域中的最优效果。在通用的ROUGE(recall-oriented understudy for gisting evaluation)评价标准中,取得R_(OUGE-1)=0.998,R_(OUGE-2)=0.995,R_(OUGE-L)=0.998的最新效果。其中,R_(OUGE-1)关注参考文本与生成文本之间单个单词的匹配度,R_(OUGE-2)则关注两个连续单词的匹配度,R_(OUGE-L)则关注最长公共子序列的匹配度。为了克服通用指标在本领域的局限性,更准确地评估模型性能,针对生成的复诵指令提出一套基于关键词的评价标准。该评价指标准基于管制文本分词后的结果计算各个关键词指标来评估模型的效果。在基于关键词的评价标准下,所构建模型取得整体准确率为0.987的最优效果,对航空器呼号的复诵准确率达到0.998。
文摘为提高干线铁路的运输效率和能力,欧洲铁路部门开始研究欧洲列控系统(ETCS)应用自动驾驶(ATO)的可行性。通过分析ETCS系统应用自动驾驶(ATO over ETCS)的研究背景和过程,阐述系统架构、工作原理、自动驾驶的功能需求以及系统规范的架构体系。同时介绍即将投入运营的ETCS系统应用自动驾驶实例,并分析它们的结构和基本原理。
文摘为提高高速铁路运输效率和自动化程度,根据珠三角城际铁路CTCS2+ATO列控系统的运用经验,提出高速铁路引入自动驾驶(ATO)的方案。方案采用CTCS+ATO系统结构,根据系统配置分为CTCS+ATO-PFC(Partial Function Configuration)和CTCS+ATO-FFC(Full Function Configuration)两个等级。分别对每个等级的系统功能、地面和车载设备配置进行定义,并提出系统分级实施方案。CTCS+ATO列控系统方案综合考虑我国列控系统的现状和发展方向,为我国高速铁路引入自动驾驶提供参考依据。
