检索结果-内蒙古大学图书馆

PSMFNet:Lightweight Partial Separation and Multiscale Fusion Network for Image Super-Resolution

Computers, Materials & Continua 2024年第10期81卷 1491-1509页

作者： Shuai Cao Jianan Liang Yongjun Cao Jinglun Huang Zhishu Yang Institute of Intelligent Manufacturing GDASGuangdong Key Laboratory of Modern Control TechnologyGuangzhou510030China School of Mechanical&Automotive Engineering South China University of TechnologyGuangzhou511442China Faculty of Information Engineering and Automation Kunming University of Science and TechnologyKunming650500China School of Faculty of Intelligent Manufacturing Wuyi UniversityJiangmen529020China

The employment of deep convolutional neural networks has recently contributed to significant progress in single image super-resolution(SISR)***,the high computational demands of most SR techniques hinder their applicability to edge devices,despite their satisfactory reconstruction *** methods commonly use standard convolutions,which increase the convolutional operation cost of the *** this paper,a lightweight Partial Separation and Multiscale Fusion Network(PSMFNet)is proposed to alleviate this ***,this paper introduces partial convolution(PConv),which reduces the redundant convolution operations throughout the model by separating some of the features of an image while retaining features useful for image ***,it is worth noting that the existing methods have not fully utilized the rich feature information,leading to information loss,which reduces the ability to learn feature *** by self-attention,this paper develops a multiscale feature fusion block(MFFB),which can better utilize the non-local features of an *** can learn long-range dependencies from the spatial dimension and extract features from the channel dimension,thereby obtaining more comprehensive and rich feature *** the role of the MFFB is to capture rich global features,this paper further introduces an efficient inverted residual block(EIRB)to supplement the local feature extraction ability of PSMFNet.A comprehensive analysis of the experimental results shows that PSMFNet maintains a better performance with fewer parameters than the state-of-the-art models.

关键词： Deep learning single image super-resolution lightweight network multiscale fusion

来源：评论

学校读者我要写书评

暂无评论

The Rotary Flexible Joint – A Holistic View from Modeling and control to Observer Design and Experiments

引用

IFAC-PapersOnLine 2023年第2期56卷 7567-7572页

作者： Simon Helling Thomas Meurer Automation and Control Group Faculty of Engineering Kiel University

A two degrees of freedom (2DOF) control for a lab-scale vertically-mounted rotary flexible joint is addressed to realize a benchmark example for nonlinear control education and experimentation. To this end, the mathematical model is derived based on the Euler-Lagrange equations. Further insight into the model is given by addressing the relationship between the two translational springs and their approximation as a single torsion spring. The model is known to be differentially flat, which facilitates a feedforward control design by means of the flat parameterization. Furthermore, a state-feedback controller is introduced to stabilize the desired trajectory. State information is reconstructed using a Luenberger-type observer. Both the state-feedback controller and the Luenberger-type observer are designed based on a linear time-varying (LTV) approximation obtained using a linearization around the flat state parameterization of the system. The 2DOF design is illustrated using experimental results.

关键词： Nonlinear control feedback control feedforward control observers pole assignment

来源：评论

学校读者我要写书评

暂无评论

Stability and bifurcation analysis of delayed tri-trophic food chain model in poisoned environment with fear effect and additional food

Stability and bifurcation analysis of delayed tri-trophic fo...

引用

作者： Ramasamy, Sivasamy Banjerdpongchai, David Park, PooGyeon Center of Excellence in Intelligent Control Automation of Process Systems Department of Electrical Engineering Faculty of Engineering Chulalongkorn University Bangkok Thailand Department of Electrical Engineering Pohang University of Science and Technology Pohang Korea Republic of

One of the most important goals of theoretical ecologists is to find a strategy for controlling the chaos in ecological models to maintain healthy ecosystems. We investigate the influence of fear and the supply of additional food to predators in a delayed tri-trophic food chain model, where interference among the species is determined by Holling type-II functional response. The proposed model incorporates the fact that the growth rates of prey and middle predators are decreased due to the fear of middle and special predators, respectively. The additional food is supplied to both predators by either nature or external agencies. Furthermore, the poisoned prey in the predator's environment is taken into account. In the proposed model, we use two time delays: one for the growth term of the middle predator and another for the gestation delay of the special predator. We determine the conditions for the existence of ecologically feasible equilibrium points and their local and global stability. In addition, we establish the conditions for the existence of Hopf bifurcation around interior equilibrium to seek periodic behavior in nondelayed and delayed models. Numerical investigations are performed to justify the proposed theoretical findings through phase portraits, time series of solutions, and bifurcation diagrams. We observe that the chaotic dynamics of a tri-trophic food chain model can be controlled by the proper choice of the fear effect and by supplying additional food parameters. As a result, our findings provide more ecological insights into the dynamics of the delayed tri-trophic food chain model with the fear effect and additional food supply. © 2023 John Wiley & Sons, Ltd.

关键词： Hopf bifurcation

来源：评论

学校读者我要写书评

暂无评论

Augmented Reality Application in Digital automation Laboratory

Augmented Reality Application in Digital Automation Laborato...

引用

2023 International Symposium on Electrical and Electronics engineering, ISEE 2023

作者： Khang, Nguyen Trong Tran, Ngoc-Huy Phan, Nguyen-Phuc-Quoc VNU-HCM Faculty of Electrical & Electronics Engineering Department of Control & Automation Ho Chi Minh City Viet Nam

ISBN: (纸本)9798350315486

Traditional automation engineering education using physical training equipment while quite effective, suffers from several limitations in the case there is no equipment access, which can be due to many reasons such as social distancing or financial difficulties. This article proposes a solution to overcome these limitations with the combinational use of mixed reality (MR), which helps the student get used to training equipment they have no access to, and augmented reality (AR), which brings intuitive visualization into real equipment practice. © 2023 IEEE.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Two-Degree-of-Freedom Feedback Loop Factorization controller for Oscillating Plant with Uncertain Time Delay and Astatism Using Structured Singular Value

Two-Degree-of-Freedom Feedback Loop Factorization Controller...

引用

2024 International Conference on control, automation and Diagnosis, ICCAD 2024

作者： Dlapa, Marek Tomas Bata University In Zlin Faculty of Applied Informatics Department of Automation and Control Engineering Nad Stranemi 4511 Zlin760 05 Czech Republic

ISBN: (纸本)9798350361025

Application of Robust control Toolbox for Time Delay Systems implemented in the Matlab system to the oscillating plant with uncertain time delay and astatism using the D-K iteration and algebraic approach. The algebraic approach combines the structured singular value, algebraic theory and algorithm of global optimization solving remaining issues in structured singular value framework. The algorithm for global optimization can be alternated with direct search methods such as Nelder-Mead simplex method giving solutions for problems with one local extreme. As a global optimization method, Differential Migration is used proving to be reliable in solving this type of problems. The D-K iteration represents a standard method in the structured singular value theory. The results obtained from the D-K iteration are compared with the algebraic approach. © 2024 IEEE.

关键词： Global optimization

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Group Formation control of Cyber-Physical Systems via Distributed Cloud Computing

IEEE Transactions on Industrial Cyber-Physical Systems

引用

IEEE Transactions on Industrial Cyber-Physical Systems 2025年 3卷 341-350页

作者： Ren, Hongru Long, Yinren Li, Hongyi Huang, Tingwen Guangdong University of Technology School of Automation Guangdong-Hong Kong Joint Laboratory for Intelligent Decision and Cooperative Control Guangdong Provincial Key Laboratory for Intelligent Decision and Cooperative Control Guangzhou510006 China Southwest University College of Electronic and Information Engineering Chongqing400715 China Shenzhen University of Advanced Technology Faculty of Computer Science and Control Engineering Shenzhen518055 China

This paper investigates the group formation control problem for cyber-physical systems (CPSs) with random communication constraints. The distributed cloud computing system is constructed to divide agents into groups and establish communication between agents. A data-driven predictive control strategy is proposed by combining networked predictive control and model-free adaptive control method. The desired group formation control performance can be achieved and the three-channel random communication constraints of CPSs are actively compensated. Thisstrategy does not require the system model and relies solely on the system's I/O data for adaptive learning. Further analyses concludes the conditions for simultaneous reach stability and group formation of the closed-loop CPSs using the data-driven predictive control strategy. The effectiveness of the proposed strategy is validated by simulation results. © 2023 IEEE.

关键词： Distributed cloud

来源：评论

学校读者我要写书评

暂无评论

Safety-Critical Randomized Event-Triggered Learning of Gaussian Process With Applications to Data-Driven Predictive control

引用

IEEE Transactions on Automatic control 2024年第6期70卷 3920-3935页

作者： Zheng, Kaikai Shi, Dawei Shi, Yang Beijing Institute of Technology MIIT Key Laboratory of Servo Motion System Drive and Control School of Automation Beijing100081 China University of Victoria Department of Mechanical Engineering Faculty of Engineering VictoriaBCV8N 3P6 Canada

Safety and data efficiency are important concerns in data-driven control, especially for nonlinear systems with unknown dynamics and subject to disturbances. In this work, we consider a class of control-affine nonlinear systems with partially unknown dynamics and aim to introduce an event-triggered learning-based control approach with guaranteed safety and improved data utilization efficiency. Specifically, a randomized learning approach is employed to evaluate the safety of state trajectories by defining and estimating its confidence interval, with data from a multisample of randomly generated state trajectories. Using the proposed randomized learning algorithm, a nominal trajectory with a high probability safety guarantee is designed, thus ensuring the disturbed system states to remain within a pre-specified range around the nominal trajectory with a sufficiently high probability. Through removing irrelevant data, a local prediction model around the nominal trajectory is learned with satisfactory precision, and is updated online using an event-triggered learning strategy. Based on the learned model, an efficient data-driven predictive controller is designed to force the system states to evolve within the vicinity of the designed safety nominal trajectory. The effectiveness of the proposed event-triggered learning and data-driven control approaches is validated through comprehensive simulation studies. © 1963-2012 IEEE.

关键词： Predictive control systems

来源：评论

学校读者我要写书评

暂无评论

Design of Supervisory Model Predictive control for HVAC Systems and Two Zones with Consideration of Energy Efficiency and Thermal Comfort 23

Design of Supervisory Model Predictive Control for HVAC Syst...

引用

23rd International Conference on control, automation and Systems, ICCAS 2023

作者： Srisurapanon, Panithan Banjerdpongchai, David Chulalongkorn University Center of Excellence in Intelligent Control Automation for Process Systems Faculty of Engineering Department of Electrical Engineering Pathumwan Bangkok10330 Thailand

ISBN: (纸本)9788993215274

This paper presents the design of supervisory model predictive control for HVAC systems and two zones. The supervisory control (SC) is designed to find the optimal reference temperature of each zone. The design criteria consist of the total operating cost (TOC) and the thermal comfort cost (TCC). Then, the model predictive control (MPC) is designed to track the optimal reference signals. When SC and MPC are designed for two zones simultaneously, they are referred to centralized SC and centralized MPC. On the other hand, when SC and MPC are designed for two zones separately, they referred to decentralized SC and decentralized MPC. We then compare the results between the decentralized control and the centralized control. The trade-off curve shows that the performance of centralized control is better than that of decentralized control. In particular, centralized MPC improves the performance in tracking reference signals. Furthermore, TOC of centralized control is lower than that of decentralized control. It can be concluded that the centralized control is appropriate for two zones in terms of the tracking of reference and the electrical charge. © 2023 ICROS.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

A Multi-party Asymmetric Self-play Algorithm and Its Application in Multi-USV Adversarial Game Simulations 24

A Multi-party Asymmetric Self-play Algorithm and Its Applica...

引用

2024 International Conference on Machine Learning, Pattern Recognition and automation engineering, MLPRAE 2024

作者： Rao, Jinjun Wang, Cong Liu, Mei Lei, Jingtao Giernacki, Wojciech Department of Precision Mechanical Engineering School of Mechatronic Engineering and Automation Shanghai University China Institute of Robotics and Machine Intelligence Faculty of Automatic Control Robotics and Electrical Engineering Poznan University of Technology Poland

ISBN: (纸本)9798400709876

Aiming at the problem that the combination of self-play (SP) and deep reinforcement learning (DRL) only involves two-party games and the policy learning of each party is limited, a multi-party asymmetric self-play algorithm (MASP) is proposed. Firstly, by improving the ELO scoring system, the ELO scoring takes into account each party of the unmanned surface vehicle (USV) clusters, and the imbalance of the number of USV clusters, so that the frequency of exchanging strategies of all USV clusters in the confrontation process is equal. Secondly, it ensures that USV clusters have a balanced combat ability, and at the same time ensures that the combat ability of all parties is strong and weak and the gap is not too wide. In addition, the parameters are dynamically set to reduce the update frequency of the policy of the stronger party. The experimental results show that the MASP can make the USV clusters learn more effective policies, have a shorter game time, and obtain higher rewards and ELO scores in the simple 2v2 adversarial game scenario and the three-party game scenario of a warship escort mission. © 2024 ACM.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Target Capturing in an Ellipsoidal Region for a Swarm of Double Integrator Agents

引用

IEEE/CAA Journal of Automatica Sinica 2022年第5期9卷 801-811页

作者： Antonio Bono Luigi D'Alfonso Giuseppe Fedele Veysel Gazi IEEE Department of Informatics ModelingElectronics and Systems EngineeringUniversity of CalabriaRende 87036Italy Dept.Electrical and Electronics Eng. Faculty of EngineeringMarmara UniversityIstanbul 34722 Department of Control and Automation Engineering Faculty of Electrical and Electronics EngineeringYildiz Technical UniversityEsenler 34220Turkey

In this paper we focus on the target capturing problem for a swarm of agents modelled as double integrators in any finite space *** agent knows the relative position of the target and has only an estimation of its velocity and *** that the estimation errors are bounded by some known values,it is possible to design a control law that ensures that agents enter a user-defined ellipsoidal ring around the moving *** know the relative position of the other members whose distance is smaller than a common detection ***,in the case of no uncertainty about target data and homogeneous agents,we show how the swarm can reach a static configuration around the moving *** simulations are reported to show the effectiveness of the proposed strategy.

关键词： Agents-based systems cooperative control swarms target-capturing

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：