检索结果-内蒙古大学图书馆

High-speed train positioning based on a combination of Beidou navigation, inertial navigation and an electronic map

Science China(Information Sciences) 2023年第7期66卷 237-252页

作者： Hui YANG Shuai-Qiang DONG Chun-Hua XIE School of Electrical and Automation Engineering East China Jiaotong University Key Laboratory of Advanced Control & Optimization of Jiangxi Province East China Jiaotong University State Key Laboratory of Performance Monitoring Protecting of Rail Transit Infrastructure East China Jiaotong University

To date, the studies on the combination positioning of high-speed trains have made great progress, but the positioning accuracy of these methods is relatively low. Map-matching positioning can improve positioning accuracy, but information transmission is time-consuming. Few studies incorporate it into combination positioning. To solve the problem, this paper proposes a high-speed train positioning method based on combining a Beidou navigation system, an inertial navigation system, and an electronic map. First, the combination positioning problem is transformed into a multi-objective optimization problem, which weights the direction similarity and distance error to form a fitness function and converts the railway line and the maximum error range of each positioning system into constraints. Second, an improved differential evolution algorithm is proposed to solve this problem. By referencing the gray wolf algorithm,the differential evolution algorithm updates individuals by varying toward the direction of multiple optimal values. Then, a new combination positioning algorithm for high-speed trains is proposed. In the simulation,the increase in positioning speed and accuracy is analyzed and validated. Compared to the current algorithms, the proposed algorithm performs better. The proposed method has practical value for improving the reliability and safety of train operations.

关键词： electronic map multi-objective optimization differential evolution algorithm Beidou navigation system high-speed train positioning

来源：评论

学校读者我要写书评

暂无评论

Policy Gradient Adaptive Dynamic Programming for Model-Free Multi-Objective Optimal control

引用

IEEE/CAA Journal of Automatica Sinica 2024年第4期11卷 1060-1062页

作者： Hao Zhang Yan Li Zhuping Wang Yi Ding Huaicheng Yan the Department of Control Science and Engineering Tongji UniversityShanghai 200092China the Key Laboratory of Advanced Control and Optimization for Chemical Processes of Ministry of Education School of Information Science and EngineeringEast China University of Science and TechnologyShanghai 200237China

Dear Editor,In this letter,the multi-objective optimal control problem of nonlinear discrete-time systems is investigated.A data-driven policy gradient algorithm is proposed in which the action-state value function is... 详细信息

关键词： policy gradient Optimal

来源：评论

学校读者我要写书评

暂无评论

Research on Traction optimization control Strategy for 10,000-Ton Heavy Haul Trains 19th

Research on Traction Optimization Control Strategy for 10,00...

引用

19th Annual Conference of China Electrotechnical Society, ACCES 2024

作者： Zhang, Kunpeng Tang, Junjie Yang, Hui School of Electrical and Automation Engineering East China Jiaotong University Nanchang330013 China Jiangxi Provincial Key Laboratory of Advanced Control and Optimization Nanchang330013 China State Key Laboratory of Performance Monitoring and Protecting of Rail Transit Infrastructure Jiangxi Nanchang330013 China

ISBN: (纸本)9789819613823

Aiming at the problems of difficult control of electric traction equipment for heavy haul trains and low accuracy of control models, a distributed fuzzy sliding mode optimization control strategy for heavy haul trains based on a predictive compensation model is proposed. Firstly, based on the complex road condition information of heavy haul railways, a longitudinal dynamics model of heavy haul trains is established. Then, a long short-term memory neural network (LSTM) optimized by the Northern Goshawk optimization (NGO) algorithm is used to predict and compensate the uncertain terms in the model. At the same time, a variable universe fuzzy algorithm (VUF) is used to improve the fast terminal sliding mode controller (FTSM). Finally, the improved controller is combined with the air braking strategy to jointly control the corrected model. The simulation results based on the heavy haul train operation simulation platform and real operation data show that the proposed method can effectively improve the handling stability and safety of 10,000-ton heavy haul trains. © Beijing Paike Culture Commu. Co., Ltd. 2025.

关键词： Traction control

来源：评论

学校读者我要写书评

暂无评论

Accuracy analysis for distributed dynamic state estimation in large-scale systems with a cyclic network graph

引用

Science China(Information Sciences) 2023年第9期66卷 78-93页

作者： Mingyan ZHU Rui WANG Xiaodong MIAO Tianju SUI School of Control Science and Engineering Dalian University of Technology Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education School of Aeronautics and Astronautics Dalian University of Technology Key Laboratory of Advanced Technology for Aerospace Vehicles School of Mechanical and Power Engineering Nanjing Tech University

This paper addresses a distributed dynamic state estimation problem in large-scale systems characterized by a cyclic network graph. The objective is to develop a distributed estimation algorithm for each node to generate local state estimations, based on the coupled measurements and boundary information exchanged with neighboring nodes. Our proposed approach is grounded in the maximum a posteriori(MAP)estimation method, which yields suboptimal results in acyclic network graphs compared with the centralized MAP approach. We extend this approach to systems with a cyclic network graph. Furthermore, we provide an accuracy analysis by deriving bounds for the differences in estimation error covariance and state estimation between the proposed distributed algorithm and the suboptimal centralized MAP method. These bounds apply to a specific category of systems that satisfy certain conditions, including cyclic topology and sparse connections. We demonstrate that these bounds converge asymptotically, with the rate of convergence determined by the loop-free depth of the graph. The loop-free depth of the graph refers to the maximum number of nodes that can be traversed in a cycle without revisiting any node. Finally, we demonstrate the validity of the algorithm through numerical examples.

关键词： distributed state estimation maximum a posteriori estimation cyclic network graph

来源：评论

学校读者我要写书评

暂无评论

Causal reasoning in typical computer vision tasks

引用

Science China(Technological Sciences) 2024年第1期67卷 105-120页

作者： ZHANG KeXuan SUN QiYu ZHAO ChaoQiang TANG Yang Key Laboratory of Advanced Control and Optimization for Chemical Process Ministry of EducationEast China University of Science and TechnologyShanghai 200237China National Key Laboratory of Air based Information Perception and Fusion Luoyang 471000China Luoyang Institute of Electro Optical Equipment of Avic Luoyang 471000China

Deep learning has revolutionized the field of artificial *** on the statistical correlations uncovered by deep learning-based methods,computer vision tasks,such as autonomous driving and robotics,are growing *** being the basis of deep learning,such correlation strongly depends on the distribution of the original data and is susceptible to uncontrolled *** the guidance of prior knowledge,statistical correlations alone cannot correctly reflect the essential causal relations and may even introduce spurious *** a result,researchers are now trying to enhance deep learningbased methods with causal *** theory can model the intrinsic causal structure unaffected by data bias and effectively avoids spurious *** paper aims to comprehensively review the existing causal methods in typical vision and visionlanguage tasks such as semantic segmentation,object detection,and image *** advantages of causality and the approaches for building causal paradigms will be *** roadmaps are also proposed,including facilitating the development of causal theory and its application in other complex scenarios and systems.

关键词： causal reasoning computer vision tasks vision-language tasks semantic segmentation object detection

来源：评论

学校读者我要写书评

暂无评论

Global output feedback adaptive stabilization for systems with long uncertain input delay

引用

Science China(Information Sciences) 2023年第1期66卷 326-327页

作者： Zhuping WANG Jingcheng LIU Chao HUANG Hao ZHANG Huaicheng YAN School of Electronics and Information Engineering Tongji University Key Laboratory of Advanced Control and Optimization for Chemical Process of Ministry of Education East China University of Science and Technology

Dear editor,The uncertain input delay is frequently encountered in engineering control systems. Adaptation is indispensable when the uncertain input delay is significant. In existing delayadaptive controllers [1–6], the actuator state must be measured to achieve global stability. Recently, a logic-based switching delay-adaptive state-feedback controller [7] was proposed to realize global stability without measuring the actuator state.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Prescribed-time distributed localization of multi-agent systems based on local bearing information 43

Prescribed-time distributed localization of multi-agent syst...

引用

43rd Chinese control Conference, CCC 2024

作者： Lv, Yunkai Yan, Huaicheng Rao, Kai Yang, Penghui East China University of Science and Technology Key Laboratory of Advanced Control and Optimization for Chemical Process of Ministry of Education Shanghai200237 China

ISBN: (纸本)9789887581581

This work considers the localizability of multi-agent systems based on local bearing measurement. A novel prescribed-time orientation estimation algorithm is first proposed to guarantee that the local reference frame of the follower agent is aligned with the global one. The orientation estimation algorithm is then applied to the problem of position estimation, and a prescribed-time distributed localization estimation algorithm is deigned. The global convergence is derived based on the cascade system. Some simulation results are provided to prove the effectiveness of the proposed estimation methods. © 2024 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Local bearing information orientation estimation prescribed-time

来源：评论

学校读者我要写书评

暂无评论

Combine deep learning and Bayesian analysis to separate overlapping gravitational wave signals

引用

Science China(Physics,Mechanics & Astronomy) 2025年第5期68卷 205-219页

作者： Cunliang Ma Weiguang Zhou Zhoujian Cao Mingzhen Jia Jiangxi Provincial Key Laboratory of Multidimensional Intelligent Perception and Control Jiangxi University of Science and TechnologyGanzhou 341000China Institute of Applied Mathematics Academy of Mathematics and Systems ScienceChinese Academy of SciencesBeijing 100190China School of Fundamental Physics and Mathematical Sciences Hangzhou Institute for Advanced StudyUCASHangzhou 310024China

Future gravitational wave(GW)observatories,such as the Einstein Telescope,are anticipated to encounter overlapping GW signals,presenting considerable obstacles to GW data processing techniques,including signal identification and parameter *** this letter,we propose a scheme of combining deep learning and Bayesian analysis to disentangle overlapping GW *** deep learning part takes a data-driven approach that employs an encoder-separation-decoder framework which is powerful enough to extract the shape of the signal even when the GW signals completely *** Bayesian analysis part takes the matched filtering technique to extract the amplitude of the GW *** scheme can facilitate the utilization of existing GW detection and parameter estimation methods for future instances of overlapping *** methodology effectively reduces biases in parameter estimation when handling multiple intertwined ***,this marks the first known instance where deep learning has been successfully utilized to disentangle overlapping GW signals.

关键词： gravitational wave separation machine learning Einstein Telescope parameter estimation

来源：评论

学校读者我要写书评

暂无评论

Prediction of Element Component Content Based on Mechanism Analysis and Error Compensation 4

Prediction of Element Component Content Based on Mechanism A...

引用

4th International Conference on Industrial Artificial Intelligence, IAI 2022

作者： Lu, Rongxiu Deng, Biao Ding, Kanghao Yang, Hui Zhu, Jianyong Liu, Hongliang School of Electrical and Automation Engineering East China Jiaotong University Key Laboratory of Advanced Control and Optimization of Jiangxi Province Jiangxi Nanchang330013 China

ISBN: (数字)9781665451208

ISBN: (纸本)9781665451208

To solve the difficulty of rapid and accurate detection of component content in the rare earth extraction process, a component content modeling method combining mechanism model and error compensation model based on just-in-time learning (JITL) was proposed. Considering the different dynamic characteristics of each section, the extraction section is simplified using the segmented-aggregation method, and the mechanism model of the rare earth extraction process based on material balance is established;in view of the error caused by the simplification of the model and the characteristics of some rare earth solutions with color features, the color features of rare earth solution samples are extracted by machine vision technology, and the error compensation model of the mechanism model is established by the just-in-time learning algorithm. Through the experimental verification of the field sample data of the praseodymium/neodymium (Pr/Nd) extraction process, the results show that the modeling method proposed in this paper is suitable for rapid and accurate detection of elemental component content in the rare earth extraction process with ionic color features. © 2022 IEEE.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

A Fault Detection Method and System for Highway Tunnel dome light Based on Improved YOLO with Locatization Loss Function 4

A Fault Detection Method and System for Highway Tunnel dome ...

引用

4th International Conference on Industrial Artificial Intelligence, IAI 2022

作者： Dai, Lizhen Tang, Cailing Yang, Gang Yang, Hui Luo, Jiang Chen, Zhaozhang East China Jiaotong University Key Laboratory of Advanced Control and Optimization of Jiangxi Province School of Electrical and Automation Engineering Jiangxi Nanchang330013 China

ISBN: (数字)9781665451208

ISBN: (纸本)9781665451208

Sufficient light intensity in the tunnel plays an extremely important role in ensuring the safety of driving in the tunnel. Tunnel dome light is the basic facility to ensure tunnel lighting. The traditional fault detection method is manual inspection, and the discovery of the problem is not timely. In this paper, a tunnel dome light fault detection method and system based on video monitoring is proposed. Constructing a tunnel dome light detection data set. The original positioning loss function in YOLOv5 is changed from CIOD_Loss function to SCALoss function, which is composed of side overlap (SO), corner distance (CD) and aspect ratio (AR) loss. So that the network can generate more penalties for low overlap positioning frames, and the network model has better positioning performance and faster convergence speed, it is more suitable for the dense and small target such as tunnel headlight. After improving the model, the recognition accuracy is improved by 13.1 %, and the positioning loss is also reduced. So that it can quickly and accurately locate the target to be detected. Finally, the fault lamp detection model is constructed to locate the specific location of the fault lamp. The experiment shows that the model has good performance, and it can effectively detect the state of tunnel dome light in real time and detect abnormal working conditions. © 2022 IEEE.

关键词： Location

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：