检索结果-内蒙古大学图书馆

13th IEEE Data Driven control and Learning systems Conference, DDCLS 2024

作者： Fan, Zhong-Xin Tang, Lintao Li, Shihua Liu, Rongjie School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing210096 China Florida State University Department of Statistics TallahasseeFL32304 United States

ISBN: (纸本)9798350361674

Achieving optimal speed regulation for permanent magnet synchronous motors (PMSMs) remains a challenging task, particularly in selecting the most suitable controller to meet desired objectives. This paper considers the optimal speed tracking problem of PMSMs. We employ a reinforcement learning algorithm to obtain optimal controller with a linear form. The reinforcement learning approach incorporates a critic-actor network structure, which approximates the value function and optimal control, respectively. Specifically, a weight updating method for the critic network is introduced, where the update of the actor network is guided by the critic network. Through data collection and neural network training, dynamic acquisition of the optimal controller gain is achieved. In addition, a novel activation function is implemented in the network, leading to improved control performance concerning dataset size and reduced training time. At final, a real-world PMSM application is presented along with comparisons to demonstrate effectiveness. The desire idea of resulting optimal controllers is not only applicable to linear systems but also capable of approximating arbitrary nonlinear optimal controllers, thus offering practical engineering versatility. © 2024 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Detection of Termite Nests in Dams Using Ground Penetrating Radar Based on Deep Learning 20

Detection of Termite Nests in Dams Using Ground Penetrating ...

引用

20th International Conference on Ground Penetrating Radar, GPR, 2024

作者： Peng, Jiao Xue, Wei Wang, Wenkai Song, Junlei Zhou, Feng Huang, Pengchun Zhang, Zhixuan Zhang, Feng Zhang, Xu Chen, Longjia Sun, Li School of Automation China University of Geosciences Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education China Dam Safety Monitoring and Termite Control Center of Hubei Provincial Department of Water Resources China Key Laboratory of Termite Control Ministry of Water Resources China School of Mechanical Engineering and Electronic Information China University of Geosciences Wuhan China

Termites have always been one of the major hidden dangers to the operational safety of dams. Traditional detection methods such as manual inspection and termite baiting have limitations in terms of efficiency and accuracy. To solve the problems, paper proposes a termite nest detection method based on ground penetrating radar (GPR) and deep learning. First, the simulated GPR data are generated using gprMax software, and the real data are collected using a GPR at several dams. Subsequently, the YOLOv8 deep neural network is employed for termite nest recognition in GPR images. The experimental results show that the proposed model can achieve the mean average precision (mAP) of 0.96 and a detection speed of 53.76 frames per second (FPS). © Published under licence by IOP Publishing Ltd.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Optimal Linear Deception Attacks on Remote State Estimation with Constrained Alarm Rates: A Low-Dimensional Case 63

Optimal Linear Deception Attacks on Remote State Estimation ...

引用

63rd IEEE Conference on Decision and control, CDC 2024

作者： Shang, Jun Zhang, Hanwen Zhou, Jing Chen, Tongwen Tongji University Shanghai Research Institute for Intelligent Autonomous Systems National Key Laboratory of Autonomous Intelligent Unmanned Systems Frontiers Science Center for Intelligent Autonomous Systems Department of Control Science and Engineering Shanghai200092 China University of Science and Technology Beijing Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education School of Automation and Electrical Engineering Beijing100083 China University of Alberta Department of Electrical and Computer Engineering EdmontonABT6G 1H9 Canada

ISBN: (纸本)9798350316339

This study addresses linear attacks on remote state estimation within the context of a constrained alarm rate. Smart sensors, which are equipped with local Kalman filters, transmit innovations instead of raw measurements through a wireless communication network. This transmission is vulnerable to malicious data interception and manipulation by attackers. The aim of this research is to identify the optimal attack strategy that degrades the system performance while adhering to stealthiness constraints. A notable innovation of this paper is the direct association of the attack's stealthiness with the alarm rate, diverging from traditional approaches that rely on the covariance of the innovation or the Kullback-Leibler divergence, which are conventional metrics that have been extensively explored in previous studies. Our findings reveal that the optimal attack strategy exhibits some structural characteristics in systems of low dimensions. The performance of the proposed attack strategy is demonstrated through numerical examples. © 2024 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exponentially convergent distributed Nash equilibrium seeking for constrained aggregative games

引用

Autonomous Intelligent systems 2022年第1期2卷 71-78页

作者： Shu Liang Peng Yi Yiguang Hong Kaixiang Peng Department of Control Science&Engineering Tongji UniversityShanghai200092China Shanghai Research Institute for Intelligent Autonomous Systems Shanghai201210China School of Automation and Electrical Engineering University of Science and Technology BeijingBeijing100083China

Distributed Nash equilibrium seeking of aggregative games is investigated and a continuous-time algorithm is *** algorithm is designed by virtue of projected gradient play dynamics and aggregation tracking dynamics,and is applicable to games with constrained strategy sets and weight-balanced communication *** key feature of our method is that the proposed projected dynamics achieves exponential convergence,whereas such convergence results are only obtained for non-projected dynamics in existing works on distributed optimization and equilibrium *** examples illustrate the effectiveness of our methods.

关键词： Distributed algorithms Aggregative games Projected gradient play Weight-balanced graph Exponential convergence

来源：评论

学校读者我要写书评

暂无评论

Two-Stage Representation Refinement Based on Convex Combination for 3-D Human Poses Estimation

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第12期5卷 6500-6508页

作者： Chen, Luefeng Cao, Wei Zheng, Biao Wu, Min Pedrycz, Witold Hirota, Kaoru China University of Geosciences School of Automation Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Ministry of Education Engineering Research Center of Intelligent Technology for Geo-Exploration Wuhan430074 China University of Alberta Department of Electrical and Computer Engineering EdmontonABT6G 2R3 Canada Macau University of Science and Technology Institute of Systems Engineering Taipa999078 China Istinye University Research Center of Performance and Productivity Analysis Istanbul34010 Turkey Tokyo Institute of Technology Yokohama226-8502 Japan

In the human pose estimation task, on the one hand, 3-D pose always has difficulty in dividing different 2-D poses if the view is limited;on the other hand, it is hard to reduce the lifting ambiguity because of the lack of depth information, it is an important and challenging problem. Therefore, two-stage representation refinement based on the convex combination for 3-D human pose estimation is proposed, in which the two-stage method includes a dense-spatial-temporal convolutional network and a local-to-refine network. The former is applied to determine the features between each video frame;the latter is used to get the different scales of pose details. It aims to address the difficulty of estimating 3-D human pose from 2-D image sequences. In such a way, it can better use the relations between every frame in the sequence of the pose video to produce more accurate results. Finally, we combine the above network with a block called convex combination to help refine the 3-D pose location. We test the proposed approach on both Human3.6m and MPII datasets. The result confirms that our method can achieve better performance than improved CNN supervision, a simple yet effective baseline, and coarse-to-fine volumetric prediction. Besides, a robustness test experiment is carried out for the proposed method while the input is interrupted. The result verifies that our method shows better robustness. © 2024 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A Coalitional MPC Approach to control of Collaborative Vehicle Platoons

引用

IFAC-PapersOnLine 2023年第2期56卷 8518-8523页

作者： P. Chanfreut T. Keijzer J.M. Maestre R.M.G. Ferrari Department of Systems and Automation Engineering University of Seville Spain Department of Mechanical Engineering Eindhoven University of Technology The Netherlands Delft Center for Systems and Control Delft University of Technology The Netherlands

This work presents a coalitional model predictive controller for collaborative vehicle platoons. The overall system is modeled as a string of locally controlled vehicles that can share data through a wireless communication network. The vehicles can dynamically form disjoint groups that coordinate their actions, i.e., the so-called coalitions . The control goals are keeping a desired reference distance between all vehicles while allowing for occasional switching of the communication topology. Likewise, the presented controller promotes a string-stable evolution of the platoon system. Numerical results are provided to illustrate the proposed approach.

关键词： Model predictive control vehicle platoons multi-agent systems string stability

来源：评论

学校读者我要写书评

暂无评论

Competitive Meta-Learning

引用

IEEE/CAA Journal of Automatica Sinica 2023年第9期10卷 1902-1904页

作者： Boxi Weng Jian Sun Gao Huang Fang Deng Gang Wang Jie Chen National Key Laboratory of Autonomous Intelligent Unmanned Systems Beijing Institute of TechnologyBeijing 100081 Beijing Institute of Technology Chongqing Innovation Center Chongqing 401120China School of Automation Tsinghua UniversityBeijing 100084China Department of Control Science and Engineering Tongji UniversityShanghai 201804 National Key Laboratory of Autonomous Intelligent Unmanned Systems Beijing Institute of TechnologyBeijing 100081China IEEE

Dear Editor,This letter is concerned with developing meta-learning models for fast,stable,and effective few-shot learning across tasks over a few training ***,deep and reinforcement learning(RL)is widely used in auton... 详细信息

关键词： robot autonomous concerned

来源：评论

学校读者我要写书评

暂无评论

Uncertainty and its Effect on Optimal Multidrug control of Hemodynamic Variables

Uncertainty and its Effect on Optimal Multidrug Control of H...

引用

American control Conference (ACC)

作者： Teodora Popescu Isabela R. Birs Ghada Ben Othman Erhan Yumuk Marcian Mihai Erwin Hegedus Dana Copot Robin De Keyser Clara M. Ionescu Cristina I. Muresan Department of Automation Technical University of Cluj-Napoca Cluj-Napoca Romania Department of Electromechanics Systems and Metal Engineering Research Group on Dynamical Systems and Control Ghent University Gent Belgium Department of Control and Automation Engineering Istanbul Technical University Maslak Istanbul Turkey

ISBN: (数字)9798350382655

ISBN: (纸本)9798350382662

Computer aided control in biomedical applications is gaining more and more popularity due to numerous research studies that have proven the efficiency of automatic control over manual dosing, which is highly susceptible to human errors. Optimal drug dosing is best achieved using automatic control, which triggers important benefits in terms of both costs and patient side-effects. However, mathematical models for patients are highly susceptible to large modeling uncertainty. A predictive control algorithm is designed in this paper for optimal multidrug control of hemodynamic variables. Improved closed loop performance is obtained compared to similar control strategies, for $\pm 30\%$ modeling uncertainty. The simulation results demonstrate that predictive control is a feasible solution for optimal drug dosing. An analysis of the closed loop performance for significant patient variability shows that controllers tuned using a nominal patient model often fail to achieve desired robustness. To limit the effect of modeling uncertainty, the prediction model should be updated using an online identification tool to extract patient features.

关键词： Drugs Uncertainty Simulation Europe Predictive models Prediction algorithms Mathematical models

来源：评论

学校读者我要写书评

暂无评论

A Robust Path Planning of Messenger UAV for Air-Ground Coordination Under Road Network Constraints

A Robust Path Planning of Messenger UAV for Air-Ground Coord...

引用

2024 IEEE International Conference on Robotics and Biomimetics, ROBIO 2024

作者： Wang, Yuyang Xin, Bin Ding, Yulong Yin, Zhen He, Bin School of Automation Beijing Institute of Technology Beijing100081 China Shanghai Research Institute for Intelligent Autonomous Systems Tongji University Shanghai China National Key Lab of Autonomous Intelligent Unmanned Systems Beijing100081 China Tongji University Department of Control Science and Engineering Shanghai China

ISBN: (纸本)9781665481090

This paper addresses the path planning problem for unmanned aerial vehicle (UAV), where a UAV serves as a messenger to periodically traverse over road-constrained ground vehicles (GVs) to relay information. The GVs may not move on the road network with the velocities agreed with the UAV due to their movement uncertainties. The UAV path planning problem can be formulated as the Dynamic Dubins Traveling Salesman Problem with Uncertain Neighborhood (DDTSPUN). To address the uncertainty in GVs motion, we define robust neighborhoods and corridors and prove that the UAV visiting these areas can revisit GVs reliably, thus transforming DDTSPUN into a Revisit-time-constrained Dubins Traveling Salesman Problem with Neighborhood (RDTSPN). To address the RDTSPN, we propose an online heuristic path planning algorithm. This algorithm incorporates a gradient-based method for visiting robust neighborhoods and a sampling-based search strategy along robust corridors to obtain the Dubins paths of UAV that achieve the robust visit for each GV. Finally, computational experiments demonstrate its advantage over other benchmark algorithms in obtaining the shortest path satisfying UAV curvature constraints, and ensuring robust access to all GVs. © 2024 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

PID control of data-driven patient response with fixed ratio co-administration of drugs for depth of hypnosis

引用

IFAC-PapersOnLine 2024年第7期58卷 222-227页

作者： Clara M. Ionescu Hamed Farbakhsh Cristina Muresan Robin De Keyser Erhan Yumuk Ghada Ben Othman Amani Rayene Ynineb Isabela Birs Dana Copot Martine Neckebroek Ghent University Department of Electromechanics Systems and Metal Engineering Research Group on Dynamical Systems and Control Tech Lane Science Park 125 9052 Zwijnaarde Belgium Technical University of Cluj-Napoca Department of Automation Memorandumului no. 28 Cluj-Napoca 400114 Romania Istanbul Technical University Department of Control and Automation Engineering Systems and Control Istanbul Turkey Ghent University Hospital Department of Anesthesia C. Heymanslaan 10 9000 Ghent Belgium

In this work we make use of knowledge from clinical practice to deliver a trusted environment for feedback control of co-administration of two drugs to induce depth of hypnosis during general anesthesia. The clinical data we have provides valuable insight into the ratio used to determine the Propofol and Remifentanil infusion rates by means of specifying their corresponding effect site concentrations. A feedback closed loop with a fixed parameter PID controller tuned on population dynamics is used. To account the strong variations in gain of the system (patient) we propose an online identification of the dose-effect response from clinical data available during clinical protocol. Theoretical analysis is provided to justify the approach and simulations with real data from patient are given to support the theoretical insight. Limitations of this approach are discussed as to justify why ratio based co-administration is used in practice solely during the induction phase of general anesthesia.

关键词： Closed-Loop control of Anesthesia PID control Depth of Hypnosis Ratio control Model Estimation Data Driven control

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：