检索结果-内蒙古大学图书馆

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

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

An LCOR model for suppressing cascading failure in weighted complex networks

引用

Chinese Physics B 2013年第5期22卷 626-631页

作者：陈世明庞少鹏邹小群 School of Electrical and Electronic Engineering East China Jiaotong University Key Laboratory of Advanced Control & Optimization of Jiangxi Province

Based on the relationship between capacity and load, cascading failure on weighted complex networks is investigated, and a load-capacity optimal relationship （LCOR） model is proposed in this paper. Compared with three other kinds of load- capacity linear or non-linear relationship models in model networks as well as a number of real-world weighted networks including the railway network, the airports network and the metro network, the LCOR model is shown to have the best robustness against cascading failure with less cost. Furthermore, theoretical analysis and computational method of its cost threshold are provided to validate the effectiveness of the LCOR model. The results show that the LCOR model is effective for designing real-world networks with high robustness and less cost against cascading failure.

关键词： cascading failure load-capacity optimal relationship model robustness cost

来源：评论

学校读者我要写书评

暂无评论

Prediction of component content in rare earth extraction process based on ESNs-Adaboost

引用

IFAC-PapersOnLine 2018年第21期51卷 42-47页

作者： Hui, Yang Shuli, Liu Rongxiu, Lu Jianyong, Zhu College of electrical and automation engineering East China Jiaotong University Nanchang China Key Laboratory for advanced control and optimization of Jiangxi Province Nanchang China

Aiming at the problem that the component content of elements in REEP (rare earth extraction process) is difficult to detect, a modeling method for component content in REEP based on ESNs-Adaboost is proposed. It uses ESN (echo state network) with fast training speed and high stability to establish multiple identification model of REEP. And then combined with the improved Adaboost algorithm, multiple models are integrated into a final ESNs-Adaboost model of component content of REEP according to the combination rule. The improved Adaboost algorithm has an advantage that its threshold can be adjusted adaptively with the training error. By collecting data from CePr/Nd extraction process, the simulation results show that the proposed method has high prediction accuracy, strong generalization ability, good robustness and better performance than single ESN model, which can meet the requirements of rapid detection of component content in extraction field. © 2018

关键词： Adaptive boosting Extraction Forecasting Rare earths Echo state networks Extraction process Generalization ability Model prediction Multiple identifications Prediction accuracy Rare earth extraction Rare earth extraction process

来源：评论

学校读者我要写书评

暂无评论

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

引用

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

Color Constancy of Rare-Earth Solution Image with Adaptive Parameter

引用

IFAC-PapersOnLine 2018年第21期51卷 295-300页

作者： Yang, Hui Zhang, Xuqian Liu, Zhixin Lu, Rongxiu Tan, Chang Zhu, Jianyong College of Electrical and Automation Engineering East China Jiaotong University Nanchang Jiangxi330013 China Key Laboratory of Advanced Control and Optimization of Jiangxi Province NanchangJiangxi330013 China Jiangxi Golden Century Advanced Materials Co. Ltd NanchangJiangxi330013 China

It is known that the color of the rare earth solution image varies with the illumination condition due to the rugged environment of rare earth extraction industry and attenuation of lights, which makes soft-sensing model for rare earth element content based on the color characteristics of the rare earth solution have larger error. An unsupervised color correction algorithm with adaptive optimization of parameters for rare earth solution is proposed in this paper. Such an algorithm can realize proper color correction of rare earth solution by using Genetic Algorithm (GA) based Grey Edge algorithm. The GA based Grey Edge algorithm can handle the issue of parameter adaptive optimization caused by the rare earth solution change with the different illumination and extraction tank, and reduce the error between the designated area of the image and the designated area of the standard image. The simulation shows the effectiveness of the proposed algorithm. © 2018

关键词： Edge detection Color Color computer graphics Extraction Gallium Genetic algorithms Image processing Parameter estimation Rare earths adaptive Adaptive optimization Color characteristics Color constancy Grey Edge Illumination conditions Rare earth extraction Rugged environments

来源：评论

学校读者我要写书评

暂无评论

Hydrodynamics of heterogeneous particle swarms in gas-liquid-solid stirred tanks with free surface studied by DEM-VOF

引用

Powder Technology 2025年 462卷

作者： E, Dianyu Wen, Yingming Wu, Yiliu Li, Jing Sun, Weifu Liu, Yonggang Chen, Chao Cui, Jiaxin Qiu, Yinxuan Jiangxi Provincial Key Laboratory of Particle Technology Jiangxi University of Science and Technology Nanchang330013 China Research Centre for Intelligent Mineral Processing & Metallurgy International Institute for Innovation Jiangxi University of Science and Technology Nanchang330013 China ARC Research Hub for Smart Process Design and Control Department of Chemical and Biological Engineering Monash University VIC3800 Australia School of Civil Engineering Southeast University Nanjing211189 China Advanced Technology Research Institute Beijing Institute of Technology Jinan250307 China Faculty of Materials Metallurgy and Chemistry Jiangxi University of Science and Technology Ganzhou341000 China Xinyu Iron and Steel Group Co. Ltd Xinyu338001 China College of Materials Science and Engineering Taiyuan University of Technology Taiyuan030024 China School of Chemical Engineering The University of Queensland QLD4072 Australia

Stirred tanks play a pivotal role in material blending, yet there is still a lack of data on inner complex blending mechanism, especially involving heterogeneous particle swarm with different shape combinations. This study extensively develops the DEM-VOF model, in which different drag force models are applied based on the identification of particle shapes. It aims to provide an insight into the blending system dynamics of heterogeneous particle swarms through seven arranged particle schemes building upon three different shapes. The results show that the oblate-prolate ellipsoid particle scheme has the optimal suspension performance, but demonstrates high power consumption. The addition of spherical particles into the oblate-prolate ellipsoid particle scheme has significant effect on particle suspension, fluid flow and the evolution of free surface, while contributes to a reduction in power consumption. This study presents an analysis of the hydrodynamics and optimization of blending systems involving heterogeneous particle swarms in stirred tanks. © 2025 Elsevier B.V.

关键词： Flow of gases

来源：评论

学校读者我要写书评

暂无评论

Asymptotic state estimation for linear systems with sensor and actuator faults

引用

Science China(Information Sciences) 2019年第11期62卷 106-120页

作者： Chun-Hua XIE Hui YANG Dianhui WANG Zhe LI School of Electrical and Automation Engineering East China Jiaotong University Key Laboratory of Advanced Control & Optimization of Jiangxi Province Department of Computer Science and Information Technology La Trobe University College of Electrical and Information Engineering Hunan University

This paper investigates the asymptotic state estimation problem for linear systems with sensor and actuator faults, where the faults are modeled via multiple modes. For the case of sensor faults, we first introduce a new notion of detectability, i.e., detectability of system against sensor faults. The notion helps to address the question of whether it is possible to asymptotically estimate the system state by using the control input and system output, irrespective of which mode the system is in and what values the fault signals are.A necessary and sufficient condition for the system to be detectable against sensor faults is given, and then two switched observers are proposed for asymptotic state estimation with the help of maximin strategy. For the system with ? fault modes, we provide the explicit form of the switched observer, which is based on a bank of ?(?+1)/2 Luenberger-like or sliding-mode observers. Furthermore, extensions to the case of sensor and actuator faults are further studied. Finally, a simulation example of a reduced-order aircraft system is provided to show the effectiveness of the proposed approaches.

关键词： asymptotic state estimation observer linear systems sensor faults actuator faults

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

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

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：