检索结果-内蒙古大学图书馆

Heterogeneous multi-player imitation learning

Control Theory and Technology 2023年第3期21卷 281-291页

作者： Bosen Lian Wenqian Xue Frank L.Lewis Department of Electrical and Computer Engineering Auburn UniversityAuburnAL 36849USA State Key Laboratory of Synthetical Automation for Process Industries and International Joint Research Laboratory of Integrated Automation Northeastern UniversityShenyang 110819LiaoningChina UTA Research Institute University of Texas at Arlington(UTA)Fort WorthTX 76118USA

This paper studies imitation learning in nonlinear multi-player game systems with heterogeneous control input *** propose a model-free data-driven inverse reinforcement learning(RL)algorithm for a leaner to find the cost functions of a N-player Nash expert system given the expert's states and control *** allows us to address the imitation learning problem without prior knowledge of the expert's system *** achieve this,we provide a basic model-based algorithm that is built upon RL and inverse optimal *** serves as the foundation for our final model-free inverse RL algorithm which is implemented via neural network-based value function *** analysis and simulation examples verify the methods.

关键词： Imitation learning Inverse reinforcement learning Heterogeneous multi-player games Data-driven model-free control

来源：评论

学校读者我要写书评

暂无评论

PID-F Controlled LFC in a Two-Area Power System with Renewable Integration Using Metaheuristic Approaches

PID-F Controlled LFC in a Two-Area Power System with Renewab...

引用

2024 IEEE Global Energy Conference, GEC 2024

作者： Can, Özay Izci, Davut Ekinci, Serdar Ghandour, Raymond Salman, Mohammad Department of Electronics and Automation Recep Tayyip Erdogan University Rize Turkey Department of Computer Engineering Batman University Batman Turkey College of Engineering and Technology American University of the Middle East Kuwait

ISBN: (纸本)9798331532611

As a result of the rising usage of renewable energy sources (RES) and the altering load profile, it is becoming increasingly difficult to strike a balance between production and demand. This is because renewable energy sources are becoming more prevalent. For this reason, it is of the utmost importance to put the process of load frequency control (LFC) into action. Taking this into consideration, the objective of this study is to optimize the adjustment of the parameters of the proportional-integral-derivative with filter (PID-F) controller for the LFC process in a two-area power system that consists of photovoltaic (PV) panels and wind energy systems simultaneously. During the past few years, a number of innovative algorithms have been developed. These algorithms include the mountain gazelle optimizer (MGO), the hippopotamus optimizer (HO), and the puma optimizer (PO). The parameters of the PID-F controller were determined with the help of these algorithms, which were applied accordingly. The findings of the simulation reveal that all three algorithms managed to achieve results that were successful and comparable to one another in the LFC process. These results were attained by all three algorithms. ©2024 IEEE.

关键词： Wind power

来源：评论

学校读者我要写书评

暂无评论

Comparison of the applicability of spatio-temporal fusion algorithms in the sanjiang confluence area of yibin city 6

Comparison of the applicability of spatio-temporal fusion al...

引用

6th International Conference on Geoscience and Remote Sensing Mapping, GRSM 2024

作者： Zhang, Yuanyang Zhao, Liangjun Ning, Feng Wang, Yinqing School of Computer Science and Engineering Sichuan University of Science and Engineering Yibin644000 China Sichuan Key Provincial Research Base of Intelligent Tourism Yibin644000 China School of Automation and Information Engineering Sichuan University of Science and Engineering Yibin644000 China

ISBN: (纸本)9781510688018

Obtaining high-quality remote sensing images is crucial for ecological environment monitoring in the Yangtze River basin and for the protection and development of the regions along the river. Currently, due to the challenges faced by satellite remote sensing instruments in simultaneously acquiring high spatial and temporal resolution data, spatio-temporal fusion technology is one of the main methods to address data gaps and the difficulty of obtaining high-quality data. This study uses a portion of the Sanjiang Confluence area in Yibin City as the experimental area, selecting Landsat and MODIS data as data sources. Four spatio-temporal fusion algorithms (STARFM, FSDAF, ISTRUM, FSDAF2.0) are employed to achieve the spatio-temporal fusion of Landsat and MODIS data, analyzing the applicability of these four algorithms in the Yibin area. The results indicate that the ISTRUM algorithm has the smallest overall error compared to the actual images, with a high degree of restoration for spatial and spectral information, yielding the best predictive fusion results and demonstrating good applicability in areas with high heterogeneity. © 2025 SPIE.

关键词： Landsat

来源：评论

学校读者我要写书评

暂无评论

Fully integrated Windows framework for source localization with MNE Python and FreeSurfer

引用

Current Directions in Biomedical engineering 2023年第1期9卷 371-374页

作者： Oppermann, Hannes Wulf, Simon Komosar, Milana Haueisen, Jens Haueisen, Jens Department of Computer Science and Automation Institute of Biomedical Engineering and Informatics Technische Universität Ilmenau Ilmenau Germany Department of Neurology Biomagnetic Center University Hospital Jena Jena Germany

There is a variety of software packages, toolboxes, or libraries for the analysis and processing of neurophysiological data such as EEG and MEG. Many of these solutions provide algorithms for both, sensor-space analysis and sourcespace analysis. Especially with the solutions that run on Windows machines, it is noticeable that the step of the volume model generation is usually not included, since the state-ofthe- art software for this (FreeSurfer) is a Unix-based software and thus not available forWindows machines. Therefore, our goal was to develop a fully-integrated software solution for Windows machines, accessing all processing steps already implemented in an existing toolbox and using FreeSurfer in the same system. Due to its widespread use, we chose MNE Python as the basis for our fully integrated software solution. We used the Windows Subsystem for Linux to create a virtual Linux kernel for the FreeSurfer installation. To demonstrate the workflow, the libeep, and AutoReject libraries have been added. A 64-channel EEG recording during right-hand movement (ME) and imagination (MI) was used to test the implemented workflow. The developed framework consists of several modules within Python, mainly using existing scripts and functions. The library libeep was integrated to read the EEG data with the '.cnt', eeprope format. AutoReject was used to automatically interpolate detected bad channels or to reject complete epochs. FreeSurfer was successfully integrated and customized Python scripts enabled the communication between MNE Python on a Windows machine and FreeSurfer on a virtual Linux kernel. With the above-mentioned EEG dataset, we performed source reconstruction and were able to show ERD/S patterns for both, ME and MI. Our new, fullyintegrated software framework can be used on Windows machines to perform a complete process of source reconstruction. © 2023 the author(s), published by Walter de Gruyter Berlin/Boston.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Study on optimization of multi-UAV nucleic acid sample delivery paths in large cities under the influence of epidemic environment

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第6期14卷 7593-7620页

作者： Han, Yuhang Xiang, Hongyu Cao, Jianing Yang, Xiaohua Pan, Nan Huang, Linhai Mechanical Engineering Faculty of Civil Aviation and Aeronautics Kunming University of Science and Technology Yunnan China Computer Science and Technology Metrology Center Yunnan Power Grid Co. Ltd. Yunnan China Computer Science and Technology Faculty of Information Engineering and Automation Kunming University of Science and Technology Yunnan China

In the context of global novel coronavirus infection, we studied the distribution problem of nucleic acid samples, which are medical supplies with high urgency. A multi-UAV delivery model of nucleic acid samples with time windows and a UAV (Unmanned Aerial Vehicle) dynamics model for multiple distribution centers is established by considering UAVs’ impact cost and trajectory cost. The Golden Eagle optimization algorithm (SGDCV-GEO) based on gradient optimization and Corsi variation is proposed to solve the model by introducing gradient optimization and Corsi variation strategy in the Golden Eagle optimization algorithm. Performance evaluation by optimizing test functions, Friedman and Nemenyi test compared with Golden Jackal Optimization (GJO), Hunter-Prey Optimization (HPO), Pelican Optimization Algorithm (POA), Reptile Search Algorithm (RSA) and Golden Eagle Optimization (GEO), the convergence performance of SGDCV-GEO algorithm was demonstrated. Further, the improved RRT (Rapidly-exploring Random Trees) algorithm is used in the UAV path planning, and the pruning process and logistic chaotic mapping strategy are introduced in the path generation method. Finally, simulation experiments are conducted based on 8 hospitals and 50 randomly selected communities in the Pudong district of Shanghai, southern China. The experimental results show that the developed algorithm can effectively reduce the delivery cost and total delivery time compared with simulated annealing algorithm (SA), crow search algorithm (CSA), particle swarm algorithm (PSO), and taboo search algorithm (TS), and the developed algorithm has good uniformity, robustness, and high convergence accuracy, which can be effectively applied to the multi-UAV nucleic acid sample delivery path optimization in large cities under the influence of an epidemic environment. © 2023, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Study on Full Bridge LLC Resonant Converter Based on LADRC in Marine DC Power Supply System 5

Study on Full Bridge LLC Resonant Converter Based on LADRC i...

引用

5th International Conference on Power and Energy Technology, ICPET 2023

作者： Li, Xiangfeng Zhan, Shengqiang Guo, Fang Liao, Hui Zhuang, Zidan Foshan University School of Mechatronic Engineering and Automation Foshan China School of Electrical and Computer Engineering Guangzhou Vocational College of Technology & Business Guangzhou China

ISBN: (纸本)9798350339673

In this paper, we investigate the use of a full bridge LLC resonant converter with linear active disturbance rejection control to improve the power density, conversion efficiency, and voltage regulation rate of marine DC power supply. To balance the design difficulty and accuracy of the LADRC scheme, the system order is reduced from three to two. The design process for third-order line expansion state observer and linear state error feedback is also derived. Meanwhile, the LESO's stability is evaluated by investigating the convergence of the observational error. To verify the effectiveness of the LADRC scheme, Simulations and experiments are conducted in the paper, the results demonstrated that the marine dc power achieves faster transient response speed and smaller output ripple when using the LADRC scheme instead of a PI controller. © 2023 IEEE.

关键词： full-bridge LLC resonant converter line expansion state observer linear active disturbance rejection control marine DC power supply

来源：评论

学校读者我要写书评

暂无评论

Parallel Implementation of the CCSDS Turbo Decoder on GPU

引用

China Communications 2024年第10期21卷 70-77页

作者： Liu Zhanxian Liu Rongke Zhang Haijun Wang Ning Sun Lei Wang Jianquan School of Computer&Communication Engineering University of Science and Technology BeijingBeijing 100083China School of Electronic and Information Engineering Beihang UniversityBeijing 100191China Beijing Engineering and Technology Research Center for Convergence Networks and Ubiquitous Services Institute of Artificial IntelligenceUniversity of Science and Technology BeijingBeijing 100083China School of Information Engineering Zhengzhou UniversityZhengzhou 450001China School of Automation and Electrical Engineering University of Science and Technology BeijingBeijing 100083China

This paper presents a software turbo decoder on graphics processing units(GPU).Unlike previous works,the proposed decoding architecture for turbo codes mainly focuses on the Consultative Committee for Space Data Systems(CCSDS)***,the information frame lengths of the CCSDS turbo codes are not suitable for flexible sub-frame parallelism *** mitigate this issue,we propose a padding method that inserts several bits before the information frame *** obtain low-latency performance and high resource utilization,two-level intra-frame parallelisms and an efficient data structure are *** presented Max-Log-Map decoder can be adopted to decode the Long Term Evolution(LTE)turbo codes with only small *** proposed CCSDS turbo decoder at 10 iterations on NVIDIA RTX3070 achieves about 150 Mbps and 50Mbps throughputs for the code rates 1/6 and 1/2,respectively.

关键词： CCSDS CUDA GPU parallel decoding turbo codes

来源：评论

学校读者我要写书评

暂无评论

Semi-global weighted output average tracking of discrete-time heterogeneous multi-agent systems subject to input saturation and external disturbances

引用

Control Theory and Technology 2023年第3期21卷 315-333页

作者： Qilin Song Yuanlong Li Yijing Xie Zongli Lin Department of Automation Shanghai Jiao Tong UniversityShanghai 200240China Department of Electrical Engineering University of Texas at ArlingtonArlington 76019TXUSA Charles L.Brown Department of Electrical and Computer Engineering University of VirginiaCharlottesville 22904-4743VAUSA

In this paper,we revisit the semi-global weighted output average tracking problem for a discrete-time multi-agent system subject to input saturation and external *** multi-agent system consists of multiple heterogeneous linear systems as leader agents and multiple heterogeneous linear systems as follower *** design both the state feedback and output feedback control protocols for each follower *** particular,a distributed state observer is designed for each follower agent that estimates the state of each leader *** the output feedback case,state observer is also designed for each follower agent to estimate its own *** these estimates,we design low gain-based distributed control protocols,parameterized in a scalar low gain *** is shown that,for any bounded set of the initial conditions,these control protocols cause the follower agents to track the weighted average of the outputs of the leader agents as long as the value of the low gain parameter is tuned sufficiently *** results illustrate the validity of the theoretical results.

关键词： Distributed average tracking Input saturation Low gain feedback Heterogeneous multi-agent systems Output regulation

来源：评论

学校读者我要写书评

暂无评论

Distributed Control for a Microgrid Cluster: Implementation and Experimental Validation 24

Distributed Control for a Microgrid Cluster: Implementation ...

引用

24th EEEIC International Conference on Environment and Electrical engineering and 8th I and CPS Industrial and Commercial Power Systems Europe, EEEIC/I and CPS Europe 2024

作者： Carrasco-Gonzalez, David Sarrias-Mena, Raúl Horrillo-Quintero, Pablo Hosseini, Ehsan Llorens-Iborra, Francisco Fernández-Ramírez, Luis M. University of Cadiz Suret Research Group Department of Electrical Engineering Algeciras Spain University of Cadiz Suret Research Group Department of Engineering in Automation Electronics and Computer Architecture and Networks Algeciras Spain

ISBN: (纸本)9798350355185

In response to growing energy demands and concerns about climate change, microgrid clusters (MGCs) are gaining widespread attention. Their ability to integrate technologies for energy consumption, generation, and storage in AC, DC or a compound of both offer a high degree of flexibility and resiliency. This research introduces a new control strategy for an MGC composed of two MGs interconnected to a local grid via a point of common coupling. The first one is a DC MG comprising an ultracapacitor (UC), wind turbine (WT), DC loads and hydrogen system. The second is an AC MG with a battery bank, AC loads and photovoltaic (PV) generator. The control strategy employs local controllers for each device and distributed control via two control agents, coordinating the power distribution among the energy storage systems (ESSs) of the MGC. This system is tested and validated on a real-time experimental setup, using two Raspberry Pi microcontrollers and an OPAL-RT unit, under different working conditions. The results obtained in this work show that the control strategy implemented in the MGC works correctly. © 2024 IEEE.

关键词： Windmill

来源：评论

学校读者我要写书评

暂无评论

A New Method for One-Pedal Driving With Fuzzy-Based Efficiency-Optimization Algorithm

A New Method for One-Pedal Driving With Fuzzy-Based Efficien...

引用

2025 IEEE International Conference on Mechatronics, ICM 2025

作者： Heydrich, Marius Hammer, Tim Mitsching, Thomas Ivanov, Valentin Technische Universitä t Ilmenau Dept. of Computer Science and Automation Ilmenau Germany Technische Universitä t Ilmenau Dept. of Mechanical Engineering Ilmenau Germany

ISBN: (纸本)9798331533892

This paper presents a case study on adaptive one pedal driving for a battery electric sport utility vehicle with in wheel based rear-wheel drive that is able to adjust the drive pedal curve automatically. In addition, a fuzzy logic observes the state of the electric machines to adapt the motor torque to the most efficient region. The control method was tested in a co-simulation using a validated vehicle model and a driver-in-the-loop strategy. Within the experiments, an improvement in energy recovery of up to 4.8 % was achieved compared to the classic brake blending. In addition, the total number of brake pedal applications is ten times lower, which translates into less driving stress and greater driving comfort, especially on long distance trips, proving the effectiveness of the controller. © 2025 IEEE.

关键词： Vehicle wheels

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：