检索结果-内蒙古大学图书馆

An Optimal control-Based Distributed Reinforcement Learning Framework for A Class of Non-Convex Objective Functionals of the Multi-Agent Network

引用

IEEE/CAA Journal of Automatica Sinica 2023年第11期10卷 2081-2093页

作者： Zhe Chen Ning Li Department of Automation Shanghai Jiao Tong UniversityShanghai 200240 Key Laboratory of System Control and Information Processing Ministry of Education of ChinaShanghai 200240 Shanghai Engineering Research Center of Intelligent Control and Management Shanghai 200240China Department of Automation Tsinghua UniversityBeijing 100084China IEEE

This paper studies a novel distributed optimization problem that aims to minimize the sum of the non-convex objective functionals of the multi-agent network under privacy protection, which means that the local objective of each agent is unknown to others. The above problem involves complexity simultaneously in the time and space aspects. Yet existing works about distributed optimization mainly consider privacy protection in the space aspect where the decision variable is a vector with finite dimensions. In contrast, when the time aspect is considered in this paper, the decision variable is a continuous function concerning time. Hence, the minimization of the overall functional belongs to the calculus of variations. Traditional works usually aim to seek the optimal decision function. Due to privacy protection and non-convexity, the Euler-Lagrange equation of the proposed problem is a complicated partial differential ***, we seek the optimal decision derivative function rather than the decision function. This manner can be regarded as seeking the control input for an optimal control problem, for which we propose a centralized reinforcement learning(RL) framework. In the space aspect, we further present a distributed reinforcement learning framework to deal with the impact of privacy protection. Finally, rigorous theoretical analysis and simulation validate the effectiveness of our framework.

关键词： Distributed optimization multi-agent optimal control reinforcement learning(RL)

来源：评论

学校读者我要写书评

暂无评论

Adaptive fault-tolerant control for non-minimum phase hypersonic vehicles based on adaptive dynamic programming

引用

Chinese Journal of Aeronautics 2024年第3期37卷 290-311页

作者： Le WANG Ruiyun QI Bin JIANG State Key Laboratory of Mechanics and Control for Aerospace Structures Nanjing University of Aeronautics and AstronauticsNanjing 210016China College of Automation Engineering Nanjing University of Aeronautics and AstronauticsNanjing 211106China

In this paper,a novel adaptive Fault-Tolerant control(FTC)strategy is proposed for non-minimum phase Hypersonic Vehicles(HSVs)that are affected by actuator faults and parameter *** strategy is based on the output redefinition method and Adaptive Dynamic Programming(ADP).The intelligent FTC scheme consists of two main parts:a basic fault-tolerant and stable controller and an ADP-based supplementary *** the basic FTC part,an output redefinition approach is designed to make zero-dynamics stable with respect to the new ***,Ideal Internal Dynamic(IID)is obtained using an optimal bounded inversion approach,and a tracking controller is designed for the new output to realize output tracking of the nonminimum phase HSV *** the ADP-based compensation control part,an ActionDependent Heuristic Dynamic Programming(ADHDP)adopting an actor-critic learning structure is utilized to further optimize the tracking performance of the HSV control ***,simulation results are provided to verify the effectiveness and efficiency of the proposed FTC algorithm.

关键词： Hypersonic vehicle Fault-tolerant control Non-minimum phase system Adaptive control Nonlinear control Adaptive dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Research on Attack Detection Method for V2V System Based on Multi-dimensional Taylor Series Expansion Framework

引用

IEEE Sensors Journal 2025年第11期25卷 19576-19591页

作者： Wang, Di Wen, Chenglin Liu, Weifeng Shaanxi University of Science and Technology School of Electrical and Control Engineering Xi’an710021 China Guangdong University of Petrochemical Technology Department of Automation Maoming525000 China

Strongly stealthy cyber-attacks in networked vehicle queue (V2V) network environments often manifest themselves as small changes to data, which makes it difficult for existing methods to effectively detect such attacks. Although the initial impact of these attacks is minimal, they are capable of significantly disrupting the system over time. To address this issue, this paper proposes a new data representation model for attack detection, aiming to overcome the limitations of existing detection methods. For subtle and persistent attack features, we present a multi-level data representation framework, which enables effective comparison of attack features at different scales by extracting features at various levels. Through hierarchical processing of features, these subtle changes are revealed at the micro level, thereby enhancing the system’s sensitivity to stealthy attacks. The experimental results show that the method in this paper can effectively detect the covert false data injection (FDI) attacks. Meanwhile, we compared the proposed method with the most recent competing methods, and the results demonstrated that our method has higher detection accuracy and stronger robustness compared with the existing methods (Figure presented). © 2001-2012 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

Stability in Inverse Problem of Determining Two Parameters for the Moore-Gibson-Thompson Equation with Memory Terms

引用

Journal of Systems Science & Complexity 2024年第6期37卷 2368-2389页

作者： FU Songren CHEN Liangbiao ZHANG Ji-Feng Key Laboratory of Systems and Control Academy of Mathematics and Systems ScienceChinese Academy of SciencesBeijing 100190China School of Automation and Electrical Engineering Zhongyuan University of TechnologyZhengzhou 450007China

In this paper,the authors consider the inverse problem for the Moore-Gibson-Thompson equation with a memory term and variable diffusivity,which introduce a sort of delay in the dynamics,producing nonlocal effects in *** H¨older stability of simultaneously determining the spatially varying viscosity coefficient and the source term is obtained by means of the key pointwise Carleman estimate for the Moore-Gibson-Thompson *** the sake of generality in mathematical tools,the analysis of this paper is discussed within the framework of Riemannian geometry.

关键词： Carleman estimate memory term Moore-Gibson-Thompson equation stability Riemannian geometry

来源：评论

学校读者我要写书评

暂无评论

Implementation of a convolutional network for detection of PPE in automotive repair services 6

Implementation of a convolutional network for detection of P...

引用

6th IEEE Symposium on Computers and Informatics, ISCI 2024

作者： Marcus, Álvaro Severo Pinto, Luiz Alberto De Almeida, Gustavo Maia Silva, Amanda Santos Control and Automation Engineering Instituto Federal Do Espírito Santo Serra Brazil

ISBN: (纸本)9798350353853

This study presents a novel application of computer vision technology to enhance safety in the automotive service industry, with a specific focus on the real-time detection of Personal Protective Equipment (PPE) usage. Using a YOLOv8 convolutional neural network, this study analyzes approximately 2,000 high-resolution images from security cameras within automotive repair facilities to detect compliance with safety gear requirements. These environments are characterized by constant artificial lighting and frequent interactions among employees and customers, which introduces complexity in visual data processing. The YOLOv8 model was selected for its proficiency in real-time object detection, facilitating robust and efficient analysis while ensuring that only authorized personnel perform specific tasks. Initial results indicate successful uniform detection, though challenges remain in accurately identifying smaller items like safety glasses and gloves. This underscores the potential of advanced image recognition technologies to substantially enhance workplace safety and operational efficiency across various industries. This study not only demonstrates the system's effectiveness in PPE detection but also sets a foundation for future advancements in smart safety practices within the industrial sector. © 2024 IEEE.

关键词： Automotive industry

来源：评论

学校读者我要写书评

暂无评论

Design Software in Tasks of Algorithmization of Manipulation Robots in Assembly of Parts with a Shaft-Bushing Connection Method

Design Software in Tasks of Algorithmization of Manipulation...

引用

2024 International Russian Smart Industry Conference, SmartIndustryCon 2024

作者： Arkhipov, Maksim V. Malkarov, Artem Yu. Matrosova, Vladlena V. Moscow Polytechnic University Faculty of Mechanical Engineering Department of Automation and Control Moscow Russia

ISBN: (纸本)9798350395044

This article presents developments by its authors: the IndustrialKit library package and the RCWorkspace application based on it. The library allows developers of third-party applications to use the functionality of programming and modeling robotic technological complexes in their products. The object-oriented concept of the package provides opportunities for offline training of manipulation robots in a developed simulation environment, subsequent transfer and launch of programs on real robots, organization of feedback control and obtaining statistical data from industrial equipment - common models of robots and various equipment devices, which is achieved through a unified structure of program modules. The connection of external visual models of production system components - robots, tools and parts - is demonstrated. An example of performing the task of assembling parts with spline joints is also given. © 2024 IEEE.

关键词： Computer software

来源：评论

学校读者我要写书评

暂无评论

State Transition Modeling Method for Optimal Dispatching for Integrated Energy System Based on Cyber-Physical System

引用

Journal of Modern Power Systems and Clean Energy 2024年第5期12卷 1617-1630页

作者： Yi Yang Peng Zhang Can Wang Zhuoli Zhao Loi Lei Lai the Hubei Provincial Key Laboratory for Operation and Control of Cascaded Hydropower Station College of Electrical Engineering and New EnergyChina Three Gorges UniversityYichangChina the Department of Electrical Engineering School of AutomationGuangdong University of TechnologyGuangzhouChina

The traditional energy hub based model has difficulties in clearly describing the state transition and transition conditions of the energy unit in the integrated energy system(IES).Therefore,this study proposes a state transition modeling method for an IES based on a cyber-physical system(CPS)to optimize the state transition of energy unit in the *** method uses the physical,integration,and optimization layers as a three-layer modeling *** physical layer is used to describe the physical models of energy units in the *** the integration layer,the information flow is integrated into the physical model of energy unit in the IES to establish the state transition model,and the transition conditions between different states of the energy unit are *** optimization layer aims to minimize the operating cost of the IES and enables the operating state of energy units to be transferred to the target *** simulations show that,compared with the traditional modeling method,the state transition modeling method based on CPS achieves the observability of the operating state of the energy unit and its state transition in the dispatching cycle,which obtains an optimal state of the energy unit and further reduces the system operating costs.

关键词： Integrated energy system(IES) cyber-physical system(CPS) state transition modeling optimal dispatching

来源：评论

学校读者我要写书评

暂无评论

Data-driven cooperative optimal output regulation for linear discrete-time multi-agent systems by online distributed adaptive internal model approach

引用

Science China(Information Sciences) 2023年第7期66卷 30-45页

作者： Kedi XIE Yi JIANG Xiao YU Weiyao LAN Department of Automation Xiamen University Department of Electrical Engineering City University of Hong Kong Key Laboratory of Control and Navigation(Xiamen University) Fujian Province University

In this study, a data-driven learning algorithm was developed to estimate the optimal distributed cooperative control policy, which solves the cooperative optimal output regulation problem for linear discretetime multi-agent systems. Notably, the dynamics of all the agent systems and exo-system is completely unknown. By combining adaptive dynamic programming with an internal model, a model-free off-policy learning method is proposed to estimate the optimal control gain and the distributed adaptive internal model by only accessing the measurable data of multi-agent systems. Moreover, different from the traditional cooperative adaptive controller design method, a distributed internal model is approximated online. Convergence and stability analyses show that the estimate controller generated by the proposed data-driven learning algorithm converges to the optimal distributed controller. Finally, simulation results verify the effectiveness of the proposed method.

关键词： adaptive dynamic programming cooperative control distributed adaptive internal model multi-agent systems optimal output regulation

来源：评论

学校读者我要写书评

暂无评论

A Discrete-Time Trajectory Tracking controller for an Underactuated Quadrotor UAV 11

A Discrete-Time Trajectory Tracking Controller for an Undera...

引用

11th IEEE International Conference on Systems and control, ICSC 2023

作者： Adigüzel, Fatih Kurtuluş, Kadircan Akbati, Onur Control and Automation Engineering Yildiz Technical University Istanbul Turkey

ISBN: (纸本)9798350304886

In this technical note, the design of a Lyapunov-based trajectory tracking controller is introduced for an underactuated quadrotor unmanned aerial vehicle (QUAV). First, the mathematical dynamics of QUAV are introduced, and then an approximate model is derived using the Euler approximation. Afterward, positive semi-definite Lyapunov functions are introduced for both attitude and position subsystems consid-ering the underactuated structure of the QUAV system. Based on positive semi-definite functions, the discrete-time nonlinear controllers are devised. These designs offer an approach that addresses the complex dynamics of the QUAV by ensuring the asymptotic stability of each subsystem while aiming to achieve the desired performance for the closed-loop system. In conclusion, the numerical simulation works are carried out to demonstrate the viability of the proposed discrete-time controller. © 2023 IEEE.

关键词： Lyapunov functions

来源：评论

学校读者我要写书评

暂无评论

Barrier Lyapunov Function-Based Finite-Time Dynamic Surface control for Output-Constrained Nonstrict-Feedback Systems

引用

Journal of Systems Science & Complexity 2023年第2期36卷 524-539页

作者： YU Jinpeng FU Cheng LIU Jiapeng MA Yumei The College of Automation Qingdao UniversityQingdao 266003China Shandong Key Laboratory of Industrial Control Technology Qingdao UniversityQingdao 266003China The School of Control Science and Engineering Shandong UniversityJinan 250100China

This paper investigates a finite-time tracking problem for the uncertainty nonlinear systems in nonstrict-feedback form,in which the output signal is restricted in a *** on the barrier Lyapunov function and dynamic surface control scheme,a novel adaptive neural controller is proposed by using the finite-time Lyapunov *** the aforementioned literature on finite time tracking control,the violation of system output constraint is avoided by combining the barrier Lyapunov function method with finite-time *** structural characteristics of neural network is introduced to expand the adaptive neural finite-time backstepping method to the uncertainty nonlinear systems in the non-strict ***,the dynamic surface control is introduced to cope with the problem of“explosion of complexity”inherent in conventional backstepping *** is shown that the designed controller can achieve finite-time tracking control and all the variables in the closed-loop system are bounded with output constraint guaranteed form stability analysis and simulation results.

关键词： Adaptive neural network control explosion of complexity finite-time tracking nonstrictfeedback form

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：