检索结果-内蒙古大学图书馆

Spreading Dynamics Analysis for railway Networks 1

2nd International Conference on Neural Computing for Advanced Applications, NCAA 2021

作者： Wu, Xingtang Yang, Mingkun Wang, Hongwei Dong, Hairong Lü, Jinhu Song, Haifeng School of Automation Science and Electrical Engineering Beihang University Beijing100191 China The State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University Beijing100044 China National Research Center of Railway Safety Assessment Beijing Jiaotong University Beijing100044 China

ISBN: (数字)9789811651885

ISBN: (纸本)9789811651878

The 2019 Coronavirus Disease (COVID-19), with the characteristics of rapid onset, strong infectivity, fast transmission and wide susceptibility, has quickly swept China since its appearance in Wuhan, Hubei province. COVID-19 spreads among people mainly by movement and close contact. railway plays an important role in transport people national-wide as its essential role in public transportation, which conduced to the spreading of COVID-19 from Hubei province to other provinces in some sense. Inspired by this, this paper collected the data of Trains with Infectors (TwI) reported by the national health commission of the People’s Republic of China. Then the spreading of COVID-19 via railway network with the concept of complex network is analyzed. Results show that nodes with higher centrality tends to provide more TwI, and the closure of Wuhan railway station significantly prevents the spreading of COVID-19. © 2021, Springer Nature Singapore Pte Ltd.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Adaptive Cruise control of Virtual Coupled High-Speed Trains

Adaptive Cruise Control of Virtual Coupled High-Speed Trains

引用

2021 China automation Congress, CAC 2021

作者： Wang, Di Cao, Yuan Su, Shuai State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University The Center of National Railway Intelligent Transportation System Engineering and Technology China Academy of Railway Sciences Beijing China School of Electric and Information Engineering Beijing Jiaotong University Beijing China Frontiers Science Center for Smart High-speed Railway System State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University Beijing China

ISBN: (纸本)9781665426473

The adaptive cruise formation control problem for multiple high-speed trains (MHSTs) with input, speed and minimum tracking distance constraints under virtual coupling (VC) is proposed in this paper. First, the dynamic equation of MHSTs is created based on the law of kinematics. The communication topology is modeled by graph theory. Next, the speed limit, minimum tracking distance with adjacent trains are dealt with by using the ideas of the potential function. The resistance and unknown disturbances are dealt with by using adaptive control. Then, a cruise control protocol for MHSTs to track the expected trajectory is designed. The Lyapunov theory is used to prove the system stability. Finally, numerical experiments are conducted, which illustrates that the control protocol is effective. © 2021 IEEE

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

Train Delay Prediction based on a Multimodal Deep-learning Method

Train Delay Prediction based on a Multimodal Deep-learning M...

引用

2021 China automation Congress, CAC 2021

作者： Chen, Shuai Wu, Xingtang Zhou, Min Yang, Bo Lü, Jinhu Dong, Hairong The State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University Beijing China Department of Dispatch China Railway Beijing Bureau Group Co. Ltd Beijing China School of Automation Science and Electrical Engineering Beihang University Beijing China

ISBN: (纸本)9781665426473

High-speed rail (HSR) trains may suffer delays under emergencies, which will disturb the normal operation of trains and reduce passengers' travel satisfaction. Accurately predicting the delay time can help the dispatchers make advanced rescheduling strategies and thus improve train operation efficiency. Therefore, to quickly and effectively predict the delay time of trains for the HSR network under emergencies, a delay prediction model based on a multi-modal deep learning framework is proposed. The model considers the temporal and spatial characteristics and time-series characteristics of train operation, and then the Transformer and the three-dimensional convolutional neural network (3D CNN) are adopted to independently extract and merge these features. Specifically, the Transformer with the attention mechanism solves the interference mechanism among trains and stations on the delay of the train of interest. At the same time, 3D CNN is used to extract the temporal and spatial data characteristics of trains. Finally, the real operation data of the Beijing railway Administration HSR network is adopted to verify the effectiveness of the proposed model. Results show that compared with the results obtained by other benchmark models, the predicted delays by the proposed model can lower the average absolute error (MAE), and root mean square error (RMSE) by 10% and 12%, specifically. © 2021 IEEE

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Fatigue Detection Based on Multiple Facial Features

Fatigue Detection Based on Multiple Facial Features

引用

Chinese control Conference (CCC)

作者： Shan Luo Qi Song State Key Lab of Rail Traffic Control & Safety School of Electronic and Information Engineering Beijing Jiaotong University Beijing P. R. China School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing P. R. China

There are certain safety risks when people are in the fatigue state in the operating environment such as driving and scheduling. To avoid risk, fatigue detection is necessary. However, due to individual differences, each person has different fatigue features. Even if the same fatigue feature, the individuals differ, the performance level of fatigue feature is also different. In view of these differences, this paper proposes a fatigue detection method based on multi-feature fusion, in which the adaptive threshold model is designed and the fatigue features are normalized to solve the problem of reduced accuracy caused by individual differences, which enables a more comprehensive assessment of individual fatigue status. The EAR (the eye aspect ratio) and the MAR (the mouth aspect ratio) waveforms are calculated based on facial landmarks, the corresponding adaptive threshold models are designed for obtaining facial fatigue features such as opening speed of eyes, blink frequency, yawning, etc. The features of facial expression are calculated by facial landmarks such as MCCD (the sagging degree of the corners of mouth) and ERD (the brow and eye distance ratio). The Xgboost machine learning model and RLDD dataset are used to implement fatigue detection. The developed method does not require the wearing of invasive devices, and the experimental results show that the method can accurately detect the fatigue state with higher accuracy and strong robustness.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Neural Network and Collaborative Computing for Image-based Train Location Data Acquisition 5th

Neural Network and Collaborative Computing for Image-based...

引用

5th Chinese Conference on Swarm intelligence and Cooperative control, CCSICC 2021

作者： Wu, Xiaoqing Song, Haifeng Wang, Peng Cheng, Jianfeng Zhou, Datian Dong, Hairong Beijing Jiaotong University School of Electronic and Information Engineering Beijing100044 China Beihang University School of Electronic and Information Engineering Beijing100191 China China Academy of Railway Sciences Group Co. Ltd. Beijing100044 China Center of National Railway Intelligent Transportation System Engineering and Technology China Academy of Railway Sciences Beijing China State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University Beijing100044 China

ISBN: (纸本)9789811939976

How to improve the performance and safety of the train has long been a question of great interest. The object of this study is to achieve the recognition of train speed and mileage that are provided by the train Driver Machine Interface (DMI) and reduce the time consumed by model training. For recognition part, a Convolutional Neural Network (CNN) and a Connectionist Temporal Classification (CTC) layer have been combined together to achieve an end-to-end recognition. For the part of time-consuming reduction, a collaborative computing was being utilized to offload the training tasks to each edge device. In addition, the process of offloading was modeled with Stochastic Petri Net (SPN). Overall, the recognition accuracy was significantly improved, compared to the traditional Optical Character Recognition (OCR) and CNNs, what is more, the time consumed on model training was also brought down as expect. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Petri nets

来源：评论

学校读者我要写书评

暂无评论

How Far is from Fully Automatic Operation to Unmanned-driving?: Comparison of Operating Resilience of Fully Automatic Operation Systems with Communication Based Train control Systems 31st

How Far is from Fully Automatic Operation to Unmanned-drivin...

引用

31st European safety and Reliability Conference, ESREL 2021

作者： Niu, Ru You, Sifan Wei, Qun State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University Beijing China School of Electronic and Information Engineering Beijing Jiaotong University Beijing China Liuzhou Vocational and Technical College Guangxi China

ISBN: (纸本)9789811820168

Recently, Fully Automatic Operation (FAO) system is so widely used (, especially in China,) that the train with the system is even called "unmanned driving train" in many medias, as FAO system can provide automatic operation for whole journey from outbound to inbound. However, at present FAO system is rarely running in driverless mode, i.e. Grades of automation4 (GoA4) level, in China. In order to look in detail operators’ scruples, this paper, in comparison with the traditional Communication Based Train control (CBTC) system, values the performance of FAO systems under abnormal conditions owing to its obvious advantages under normal circumstances. The study introduces the concept of resilience and a set of system-based metrics to describe impacts of disruptions and evolution of the system performance. The Multi-agents DES models of the train’s operation process are proposed for resilience calculation. The results of the calculation of FAO and CBTC in selected degrade scenarios are compared on the basis of the real layout of a metro line in Beijing. It is held that the lack of autonomous perception and decision-making ability of trains in dynamic uncertain environment is the bottleneck ofFAO system running in GoA4. © ESREL 2021. Published by Research Publishing, Singapore.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Cooperative Relaying for Connected Construction Equipment Networks with Hybrid Hierarchical Proximal Policy Optimization

引用

IEEE Transactions on Communications 2024年

作者： Ning, Pengfei Wang, Hongwei Tang, Tao Zhang, Jie Chen, Changji Niyato, Dusit Richard Yu, F. Beijing Jiaotong University State Key Laboratory of Advanced Rail Autonomous Operation Beijing China Beijing Jiaotong University Collaborative Innovation Center of Railway Traffic Safety Beijing China Nanyang Technological University School of Computer Science and Engineering Singapore Beijing Jiaotong University School of Automation and Intelligence Beijing China Carleton University Department of Systems and Computer Engineering OttawaONK1S 5B6 Canada

The communication network in a tunnel construction site facilitates real-time data exchange, and serves as a backbone for successfully executing construction projects. However, the long and closed spaces, irregular surfaces, and variable topology as tunnel excavation impose rigorous limitations on signal propagation, communication quality and coverage. To alleviate the realistic issues, we introduce a holistic three-phase cooperative relay scheme based on 5G New Radio (NR) vehicle-to-everything (V2X) architecture, which can extend the communication range and enhance network throughput. We theoretically derive the outage probability of the entire cooperative relaying process from source to destination, and quantify the impact of relaying on construction workflow with relay cost. To minimize the outage probability and relay cost, we formulate a cooperative relay strategies optimization problem and transform the solving procedure into a Markov decision process (MDP). We design a hybrid hierarchical proximal policy optimization (HH-PPO) reinforcement learning method to solve the MDP, which consists of two discrete actor networks, two continuous actor networks, and two critic networks. The hybrid structure enables HH-PPO to tackle the mixed action space, and the hierarchical structure enables adaptive and contextual actions generation by integrating the discrete network outputs into the continuous actor network. Simulation results validate the effectiveness of the HH-PPO algorithm with faster convergence speed, and show superior performance in terms of lower, stable outage probability and relay cost satisfaction compared with another benchmark. © 1972-2012 IEEE.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Train safety control Based on Deep Deterministic Policy Gradient with control Barrier Function

Train Safety Control Based on Deep Deterministic Policy Grad...

引用

IEEE International Conference on Networking, Sensing and control

作者： Guoteng Wang Jidong Lv Hongjie Liu Ming Chai Tao Tang Wentao Zhang School of Automation and Intelligence Beijing Jiaotong University Beijing China National Engineering Research Center of Rail Transportation Operation and Control System Beijing Jiaotong University Beijing China State Key Laboratory of Advanced Rail Autonomous Operation Beijing Jiaotong University Beijing China Beijing Zhengshi Environmental Engneering Company Beijing China

ISBN: (数字)9798350365221

ISBN: (纸本)9798350365238

Train Relative Distance Braking Mode (RDBM) has great potential to increase line capacity by enabling shorter following distances based on train-to-train communication in-formation. However, it is difficult for traditional train control methods to ensure avoidance of potential collision risks in RDBM while dealing with the nonlinearity and uncertainty of train dynamics. In this paper, a novel train safety control method combining Deep Deterministic Policy Gradient (DDPG) and control Barrier Function(Cbf)is proposed. Firstly, the safety constraint set for adjacent trains, considering their braking capabilities, is analyzed, and the uncertainty of train dynamics is modeled using a Gaussian process. Secondly, DDPG is used to explore the optimal control strategy under the action of uncertain train dynamics, and CBF provides compensation control input to ensure safety during the learning process. Then, a DDPG-CBF algorithm is presented to achieve efficient safety controller design and implementation. Finally, sufficient numerical simulations demonstrate that, compared with DDPG algorithm alone, the DDPG-CBF algorithm can not only ensure the safe and stable operation of trains, but also learn train control strategies expe-ditiously and accurately under different operating environments, with an average efficiency increase of 38.94 %.

关键词： rails Uncertainty Heuristic algorithms Process control Optimal control Numerical simulation Stability analysis safety Sensors Numerical stability

来源：评论

学校读者我要写书评

暂无评论

A digital-twin-assisted fault diagnosis of railway point machine 1

A digital-twin-assisted fault diagnosis of railway point mac...

引用

1st IEEE International Conference on Digital Twins and Parallel intelligence, DTPI 2021

作者： Zhang, Shiyao Dong, Hairong Maschek, Ulrich Song, Haifeng Technische Universität Dresden Friedrich List Faculty of Transport and Traffic Sciences Dresden Germany Beijing Jiaotong University State Key Laboratory of Rail Traffic Control Safety Beijing China School of Electric and Information Engineering Beijing Jiaotong University Beijing China

ISBN: (纸本)9781665433372

railway point is a critical movable track element in railway infrastructure, its failures mostly cause risks of derailment and collision. railway point machine is used for the switching, locking, and supervising railway point, its maintenance is crucial to guarantee the availability of railway point. With the wide deployment of sensors and the rapid development of digital technology, the pure detection methods cannot meet the current demand for the fault detection and diagnosis of railway point machines. As a way to build a closed loop between the physical object and the virtual model, the digital twin can realize the identification of possible root causes of malfunctions. In this paper, we proposed an extended framework for digital-twin-assisted fault diagnosis of RPM, which supports the realization of the accurate and real-time monitoring and diagnosis of the fault of the railway point machine. This proposed framework is developed based on the three-dimension and five-dimension structure of the digital twin model. In the case study, the predefined failures and a method based on the electric current value and shape for digital-twin-assisted fault diagnosis of RPM are presented. © 2021 IEEE.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

Iterative Learning Based Train Stop control with Initial state Shifts for Urban rail Transit 10

Iterative Learning Based Train Stop Control with Initial Sta...

引用

10th IEEE Data Driven control and Learning Systems Conference, DDCLS 2021

作者： Yu, Ruochuan Tang, Tao Yin, Chenkun Xun, Jing Xi, Jiayi Zheng, Xiaobin State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University Beijing100044 China Advanced Control Systems Laboratory School of Electronic and Information Engineering Beijing Jiaotong University Beijing100044 China Traffic Control Technology Co. Ltd Beijing100070 China Beijing Transport Institute Beijing100073 China

ISBN: (纸本)9781665424233

In this paper, a partitioned terminal iterative learning control (TILC) strategy for urban rail transit with initial state shifts is proposed to solve the accurate stop problem. A supervised machine learning method is used to pre-processing the historical operation data (i.e. the initial speed and the position data pairs in the stopping stage). And for each category the TILC algorithm is applied, realizing the update of the control law in a small range. Simulation results show that the proposed algorithm can achieve the stop accuracy of ±15cm even though the initial state varies over a certain range during the iterations. This meets the general requirement of accurate train stop for urban rail transit (±30cm). © 2021 IEEE.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：