检索结果-内蒙古大学图书馆

SSRN 2022年

作者： Du, Zhi-Gang Pan, Jeng-Shyang Wang, Xiao-Yang Chu, Shu-Chuan Ni, Shao-Quan School of Transportation and Logistics Southwest Jiaotong University Sichuan Chengdu610031 China College of Computer Science and Engineering Shandong University of Science and Technology Qingdao266590 China National and Local Joint Engineering Lab for Integrated Transportation Intelligence Chengdu610031 China National Engineering Lab of Comprehensive Transportation Big Data Application Technology Chengdu610031 China

Meta-heuristic evolutionary algorithms have been widely used in global optimization problems. Still, the global optimization of meta-heuristic evolutionary algorithms relies on a large number of frequent fitness evaluations, which hinders their application in expensive and time-consuming real-world issues. For example, in a large-scale transportation network, due to the large search space and high computational complexity, the performance of the algorithm is degraded. After years of research, many scholars have proposed the idea of using the Surrogate-assisted model to reduce the number of real evaluations for expensive problems and solve the time-consuming global optimization problem in reality. To solve the high-dimensional and time-consuming problem, in reality, a two-layer Surrogate-assisted Fish Migration Optimization (SA-FMO) is proposed. The global surrogate-assisted model is an accurate fit for the entire search space. The local surrogate-assisted model is to capture the topographic details near the current optimal solution position and improves the accuracy estimation of local optimization. In order to verify the effectiveness of our proposed algorithm, this paper first tests six benchmark functions in 50 dimensions. Finally, The optimization of long and short routes in urban rail transit, also known as the Train Routing Optimization problem, is modeled and optimized using the SA-FMO algorithm to improve operational efficiency and accelerate vehicle turnover in the case of unbalanced passenger flow distribution in urban rail transit interruption surfaces. © 2022, The Authors. All rights reserved.

关键词： Global optimization

来源：评论

学校读者我要写书评

暂无评论

A Surrogate-Assist Quasi-Affine Transformation Evolutionary for Multi-Objective Optimization of Empty Train Deployment on Heavy-Haul Railways

SSRN

引用

SSRN 2023年

作者： Du, Zhi-Gang Pan, Jeng-Shyang Xu, He-Ying Chu, Shu-Chuan Ni, Shao-Quan School of Transportation and Logistics Southwest Jiaotong University Sichuan Chengdu610031 China College of Computer Science and Engineering Shandong University of Science and Technology Qingdao266590 China National and Local Joint Engineering Lab for Integrated Transportation Intelligence Chengdu610031 China National Engineering Lab of Comprehensive Transportation Big Data Application Technology Chengdu610031 China

In recent years, surrogate-assisted evolutionary algorithms have become increasingly popular for solving expensive and time-consuming single-objective and multi-objective problems. However, in multi-objective optimization, the Pareto non-dominated solution set space can quickly become computationally intractable, making it challenging to select which samples to evaluate using the expensive fitness function. In this paper, we propose a novel surrogate-assist QUasi-Affine TRansformation Evolutionary algorithm (SA-QUATRE/MO) for solving multi-objective optimization problems. The SA-QUATRE/MO algorithm uses a radial basis neural network as a surrogate model to improve the speed of the algorithm operation by replacing the expensive fitness evaluation with the surrogate model. To ensure the excellence and diversity of the selected samples while keeping the archived sample space fixed, we propose a technique called Vector Space Sampling, which samples objective points in the current set of non-dominated solutions by dividing several sub-vector spaces. Additionally, we propose an uncertain sample infilling strategy to select samples for real fitness evaluation using a designed uncertainty function. We compare the SA-QUATRE/MO algorithm with three state-of-the-art algorithms for multi-objective problems in the DTLZ, MaF, and ZDT test function suites. Finally, we apply the SA-QUATRE/MO algorithm to solve the optimization problem of the empty train deployment at the loading end of a heavy-haul railway. We build a model based on the S12 section of a certain railway and optimize it using the SA-QUATRE/MO algorithm, demonstrating the effectiveness and practicality of our proposed approach. © 2023, The Authors. All rights reserved.

关键词： Vector spaces

来源：评论

学校读者我要写书评

暂无评论

Takeover Performance and Workload under Varying Automation Levels, Time Budget and Road Curvature

Takeover Performance and Workload under Varying Automation L...

引用

2022 IEEE Asia-Pacific Conference on Image Processing, Electronics and Computers, IPEC 2022

作者： Xu, Chengliang Li, Penghui Li, Yibing Merat, Natasha Lu, Ziwang Guo, Xing Tsinghua University State Key Laboratory of Automotive Safety and Energy School of Vehicle and Mobility Beijing China Beijing Jiaotong University Key Lab. of Transport Industry of Big Data Application Technologies for Comprehensive Transport School of Traffic and Transportation Beijing China University of Leeds Institute for Transport Studies Leeds United Kingdom Beijing Information Science and Technology University School of Mechanical and Electrical Engineering Beijing China

ISBN: (纸本)9781665409025

In SAE Level 2 (L2) and Level 3 (L3) automated driving, drivers are required to take over control from automation when reaching system boundaries. The length of time budget is the vital parameter that needs to be determined to ensure a safe takeover manner. Existing literature on this issue rarely considers potential interactions between time budget and other factors, and a variable time budget seemed to be paradoxical in critical unplanned transitions. To this end, this study investigated drivers' takeover performance and workload under varying automation levels, time budget and road curvature. We employed the operational design domain (ODD) exiting event as the transition scenario where the ego car was about to leave the highway. Results showed that drivers in L3 takeovers performed worse and elicited higher workload than L2 when entering a curved ramp with a limited time budget. Takeovers when entering a curved ramp yielded worse performance and higher workload, as compared to entering a straight ramp. Such detrimental effects caused by loss of situation awareness (SA) and change of road curvature can be mitigated by increasing the length of time budget. All these findings suggest that even in simplified ODD exiting scenarios, the length of time budget should vary according to the state of the driver and the environment. © 2022 IEEE.

关键词： Automation

来源：评论

学校读者我要写书评

暂无评论

A Passenger Transport Network Construction Method Based on Geographical Location

SSRN

引用

SSRN 2023年

作者： Qian, Chen Hao Li, Te Yang, Shengwen Li, Zhiyuan Chang, Zhangjing Chen, Fuze Ye, Yanjun College of Mechanics and Transportation Southwest Forestry University Kunming650000 China School of Transportation and Logistics National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu611756 China

Passenger transportation plays an important role in China's social and economic development in the post-epidemic era. However, little research has been done on the composition of passenger transport networks and the identification of their key nodes. In this paper, we study this topic by using passenger travel information and geographic information after the full liberalization of Yunnan (January), to provide reliable decision-making for public transport operators and controllers to deal with emergencies. A new method is used to compound the passenger transportation network, and the complex network theory is used to conduct empirical research on the comprehensive passenger transportation network. The results show that the integrated passenger transport network has higher accessibility and connectivity and the convenience of passenger travel. Due to the timeliness and dynamics of the passenger transport network, the k-shell method is more effective in identifying the key nodes of the integrated passenger transport network. © 2023, The Authors. All rights reserved.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Freight transportation Structure Adjustment Control with Priority in Energy Consumption in China

SSRN

引用

SSRN 2022年

作者： Zuo, Dajie Liang, Qichen Zhan, Shuguang Huang, Wencheng Yang, Shenglan Wang, Mengyun School of Transportation and Logistics Southwest Jiaotong University Chengdu611756 China National and Local Joint Engineering Laboratory of Comprehensive Intelligent Transportation Southwest Jiaotong University Chengdu611756 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu611756 China Key Laboratory of Comprehensive Transportation of Sichuan Province Southwest Jiaotong University Chengdu611756 China

China has set the goal of controlling the total energy consumption to 6 billion tonnes of standard coal by 2030 in an attempt to avoid an energy crisis. Generally, freight transportation is an energy-intensive industry. Controlling the energy consumption of freight transportation is crucial for achieving energy-saving goals in China. In this study, we establish the annual control model for freight transportation structure adjustment from the perspectives of the target year prediction and the intermediate year controlling to control energy consumption in the freight industry. We solve the model and obtain the annual control plan of freight transportation structure adjustment in China (2021-2030). As per the plan, energy consumption will reach its peak in 2029, with 145 million tonnes of standard coal. Lastly, we proposed a series of reasonable policy recommendations. This study will provide a reference for the sustainable development of transportation in China. © 2022, The Authors. All rights reserved.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Integrated Optimization of Maintenance Window and Train Timetable: An Innovation Modeling Approach and Alternating Direction Method of Multipliers Methods

SSRN

引用

SSRN 2022年

作者： Yang, Haonan Ni, Shaoqun Huo, Haoyang Yang, Yuhua Liu, Su Zhang, Qingpeng Chen, Dingjun School of Transportation and Logistics Southwest Jiaotong University Chengdu610031 China National and Local Joint Engineering Laboratory of Comprehensive Intelligent Transportation Southwest Jiaotong University Chengdu610031 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu610031 China School of Data Science City University of Hong Kong Hong Kong

Train timetable plays an important role in improving passenger service and transportation efficiency. The arrangement of the maintenance window directly affects the quality of maintenance, which interacts with the train timetable and constrains each other. This paper studies the integrated optimization of the maintenance window and train timetable. We abstract creatively the occupation of track capacity by maintenance activity as arc and construct the integrated time-space network of maintenance activities and trains. The headway constraints of different types of arcs are determined by the influences of trains and maintenances, and the original model is converted into a multi-commodity network flow model containing multiple types of arcs. Then we decomposed the problem into two sub-problems: (i) the arrangement of major maintenance activities;(ii) the integrated optimization of the maintenance window and train timetable for fixed maintenance activities. The heuristic algorithms based on VNS and ADMM framework were designed to solve the sub-problems, respectively. The practical case with the data of the Wuhan-Guangzhou Railway is analyzed. The results show that, in the scenario where the speed of the fast and slow trains is 160km/h and 120km/h, respectively, compared with common forms of the maintenance window, the optimized train operation cost is reduced by 21.7% with the completion of all maintenance activities. © 2022, The Authors. All rights reserved.

关键词： Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

Research on Equipment State Correlation Analysis Based on Digital Model of High-speed Railway Public Works Equipment

Research on Equipment State Correlation Analysis Based on Di...

引用

Digital Twins and Parallel Intelligence (DTPI), IEEE International Conference on

作者： Yanhua Wu Ping Li Zhibo Cheng Wenya Xu Chenkun Jin Hairong Dong National Engineering Laboratory of Comprehensive Transportation Big Data Application Technology China Academy of Railway Sciences Corporation Limited Beijing China China Academy of Railway Sciences Corporation Limited Beijing China Beijing Jiaotong University Beijing China

One of the key factors in the safe operation of high-speed railways is the operational status of public works equipment. Constructing the digital model of public works equipment, fusing basic attribute information with detection and monitoring status information, and characterizing the current operating status of public works equipment, will provide more intuitive support for the change law of state change analysis. The correlation analysis between TQI and settlement based on digital model will provide auxiliary decision support for equipment maintenance.

关键词： Analytical models Correlation Digital twin Conferences Maintenance engineering Rail transportation Monitoring

来源：评论

学校读者我要写书评

暂无评论

New parameter-free mobility model: Opportunity priority selection model

arXiv

引用

arXiv 2018年

作者： Liu, Erjian Yan, Xiao-Yong Key Lab. of Integrated Transportation Big Data Application Technology for Transportation Industry Beijing Jiaotong University Beijing100044 China Institute of Transportation System Science and Engineering Beijing Jiaotong University Beijing100044 China Big Data Research Center University of Electronic Science and Technology of China Chengdu611731 China

Predicting human mobility patterns has many practical applications in urban planning, traffic engineering, infectious disease epidemiology, emergency management and location-based services. Developing a universal model capable of accurately predicting the mobility fluxes between locations is a fundamental and challenging problem in regional economics and transportation science. Here, we propose a new parameter-free model named opportunity priority selection model as an alternative in human mobility prediction. The basic assumption of the model is that an individual will select destination locations that present higher opportunity benefits than the location opportunities of the origin and the intervening opportunities between the origin and destination. We use real mobility data collected from a number of cities and countries to demonstrate the predictive ability of this simple model. The results show that the new model offers universal predictions of intracity and intercity mobility patterns that are consistent with real observations, thus suggesting that the proposed model better captures the mechanism underlying human mobility than previous models. Copyright © 2018, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Mitigating Traffic Oscillations in Mixed Traffic Environments Using an Asynchronous Control Framework with Bayesian Optimization

SSRN

引用

SSRN 2024年

作者： Liu, Can Zheng, Fangfang Liu, Henry X. Liu, Xiaobo School of Transportation and Logistics National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu611756 China University of Michigan Transportation Research Institute University of Michigan Ann ArborMI48109 United States

This study presents a comprehensive longitudinal control framework for Connected and Automated Vehicles (CAVs) aimed at smoothing mixed traffic flow. The framework features a hierarchical and asynchronous control architecture that seamlessly integrates Model Predictive Control (MPC) and Proportional-Integral-Derivative (PID) methods, enabling real-time motion control for CAVs. In the MPC model, the desired velocity of downstream traffic is explicitly considered to promote smoother traffic flow. Additionally, a Bayesian optimization-based parameter tuning algorithm is developed for the proposed CAV control architecture, allowing it to dynamically adapt to changing oscillations and improve control performance. To validate the effectiveness of the proposed framework, two simulation experiments are conducted: one for mixed platoons and another for large-scale mixed traffic scenarios. The results demonstrate that the proposed control framework effectively mitigates oscillations and improves traffic flow smoothness while ensuring real-time applicability. Further investigation into large-scale mixed traffic reveals that even at lower CAV penetration rates (e.g., 10%, 20%), the proposed method effectively mitigates oscillations and enhances traffic smoothness. Notably, the performance in scenarios with front and random positioning (FP and EP) significantly outperforms middle and trail positioning (MP and TP), highlighting the influence of CAV distribution on traffic stability and oscillation mitigation. © 2024, The Authors. All rights reserved.

关键词： Predictive control systems

来源：评论

学校读者我要写书评

暂无评论

Fundamental diagram and stability analysis of mixed traffic considering heterogeneous car-following behaviors and platoon factors

引用

Intelligent transportation Infrastructure 2024年第3期3卷

作者： Sun, Zhanbo Yan, Qiruo Liu, Yafei Fu, Zhijian Yang, Lei School of Transportation and Logistics Southwest Jiaotong University Chengdu 611756 China National Engineering Laboratory for Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu 611756 China

With the advancement of connected automated vehicles (CAVs), it is anticipated that mixed traffic environments, where human-driven vehicles (HVs) coexist with CAVs, will become prevalent in the future. The study aims to investigate the impact of heterogeneous car-following behaviors of HVs (e.g. aggressive, normal, and mild driving styles) and platoon factors of CAVs (i.e. platoon intensity and maximum platoon size) on the fundamental diagram and stability of mixed traffic. Firstly, a Markov chain approach is employed to describe the probability distributions of different leader-follower combinations, enabling us to construct a comprehensive mixed traffic model. Subsequently, a general modeling framework based on the mixed traffic model is established to examine the effects of heterogeneous car-following behaviors and platoon factors on the fundamental diagram and stability of mixed traffic. The results from numerical experiments reveal several findings: 1. an increase in the proportion of aggressive driving style enhances both the capacity and stability of mixed traffic;2. larger platoon intensity and maximum platoon size contribute to improved capacity, particularly in scenarios where a large fraction of HVs exhibit aggressive driving behavior;3. platoon intensity has a positive impact on traffic flow stability, while larger maximum platoon size leads to reduced stability;and 4. increasing CAV penetration without considering platoon intensity may lead to reduced stability compared to scenarios with a substantial proportion of aggressive drivers. © 2024 The Author(s).

关键词： connected automated vehicles fundamental diagram heterogeneous car-following behavior Markov chain mixed traffic traffic stability

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：