检索结果-内蒙古大学图书馆

Balanced prioritized experience replay in off-policy reinforcement learning

Neural Computing and Applications 2024年第25期36卷 15721-15737页

作者： Lou, Zhouwei Wang, Yiye Shan, Shuo Zhang, Kanjian Wei, Haikun Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing210096 China School of Automation Southeast University Nanjing210096 China

In Off-Policy reinforcement learning (RL), the experience imbalance problem can affect learning performance. The experience imbalance problem refers to the phenomenon that the experiences obtained by the agent during the learning process are unevenly distributed in the state space, resulting in the agent’s inability to accurately estimate the value of each potential state. This problem is typically caused by environments with high-dimensional state and action spaces, as well as the exploration–exploitation mechanism inherent in RL. This article proposes a balanced prioritized experience replay (BPER) algorithm based on experience rarity. First, an evaluation metric to quantify experience rarity is defined. Then, the sampling priority of each experience is calculated according to this metric. Finally, prioritized experience replay is performed according to the sampling priority. BPER increases the sampling frequency of high-rarity experiences and decreases the sampling frequency of low-rarity experiences, enabling the agent to learn more comprehensive knowledge. We evaluate BPER on a series of MuJoCo continuous control tasks. Experimental results show that BPER can effectively improve the learning performance while mitigating the impact of the experience imbalance problem. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

IGBT Temperature Field Monitoring Based on Reduced-order Model

引用

CES Transactions on Electrical Machines and Systems 2023年第2期7卷 129-136页

作者： Ziyu Zhou Yi Su Xu Zhang Chengde Tong Ping Zheng Mingjun Zhu School of Electrical Engineering&Automation Harbin Institute of TechnologyHarbin 150001China IEEE Flight control department Xi'an Flight Automatic Control Research InstituteXi'an 710076China

With the rapid development of the world economy,IGBT has been widely used in motor drive and electric energy *** order to timely detect the fatigue damage of IGBT,it is necessary to monitor the junction temperature of *** order to realize the fast calculation of IGBT junction temperature,a finite element method of IGBT temperature field reduction is proposed in this ***,the finite element calculation process of IGBT temperature field is introduced and the linear equations of finite element calculation of temperature field are *** field data of different working conditions are obtained by finite element simulation to form the sample *** the covariance matrix of the sample space is constructed,whose proper orthogonal decomposition and modal extraction are carried *** basis vector space is selected to complete the low dimensional expression of temperature vector inside and outside the sample ***,the reduced-order model of temperature field finite element is obtained and *** results of the reduced order model are compared with those of the finite element method,and the performance of the reduced-order model is evaluated from two aspects of accuracy and rapidity.

关键词： IGBT Junction temperature Proper orthogonal decomposition Reduced-order model

来源：评论

学校读者我要写书评

暂无评论

Spatial Coordination of Multiple Nonholonomic Agents With Sensory Connectivity Maintenance

引用

IEEE Transactions on Systems, Man, and Cybernetics: Systems 2025年第5期55卷 3425-3435页

作者： Chen, Xi Chen, Meimin Zhu, Lijun Chai, Li Wuhan University of Science and Technology Engineering Research Center of Metallurgical Automation and Measurement Technology Wuhan430081 China Shandong Huayu University of Technology School of Electrical Engineering Shandong253034 China School of Artificial Intelligence and Automation Wuhan430074 China Zhejiang University College of Control Science and Engineering Hangzhou310027 China

This article aims to propose a general control strategy for coordination of multiple nonholonomic agents in three dimensional space. For real-world applications, since the field sensor equipped on the mobile agents for local information detection and estimation has some limited detecting range, it is necessary to guarantee that the nearby agents must stay within this range of the onboard sensor. This is called sensory connectivity maintenance. A function termed as coordination function with sensory connectivity maintenance (CFSCM) is defined to describe the performances of the coordination as well as the sensory connectivity status between the agents. Then, a general control strategy is designed based on the proposed CFSCM for spatial coordination of multiple nonholonomic agents with sensory connectivity maintenance. Moreover, the applications of the proposed control strategy for formation with omnidirectional sensors and flocking with directional sensors are shown, respectively. Finally, some numerical examples are conducted to validate the theoretical analysis. © 2013 IEEE.

关键词： Maintenance Robot sensing systems Kinematics Vectors Electronic mail Aerospace electronics Three-dimensional displays System dynamics Robot kinematics Multi-agent systems

来源：评论

学校读者我要写书评

暂无评论

Adaptive Iterative Learning control for Nonlinear Multiagent Systems With Initial Error Compensation

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第8期5卷 4192-4201页

作者： Li, Zhiqiang Zhou, Qi Liu, Yang Ren, Hongru Li, Hongyi Guangdong University of Technology School of Automation and Guangdong-Hong Kong Joint Laboratory for Intelligent Decision and Cooperative Control Guangzhou510006 China Qingdao University of Science and Technology School of Automation and Electronics Engineering Qingdao266061 China

In this article, the consensus tracking problem of neural network (NN)-based adaptive iterative learning control (AILC) scheme is investigated for the nonlinear multiagent systems (MASs) with repetitive control tasks. To achieve the better tracking performance, the NN is developed to iteratively learn the uncertain nonlinearity. Meanwhile, the gradient descent algorithm is utilized to train NN weights, which is different from the traditional method based on \sigma-modification. For initial error problems of AILC, an initial error compensation method is developed to deal with the initial consensus tracking error. During the AILC design using the dynamic surface control technique, an auxiliary control signal is introduced to handle the residual term. Then, the boundedness of all signals and the iterative convergence of tracking errors are analyzed by the Lyapunov theory. Final, a simulation of the multimanipulators is provided to validate the effectiveness of the proposed control algorithm. © 2020 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Terminal Configuration Principles for Achieving Various Electromagnetic Integration Units with Flexible Multilayer Foil Technique

引用

IEEE Electromagnetic Compatibility Magazine 2023年第2期12卷 47-61页

作者： Jiang, Shiqi Wang, Panbao Wang, Wei Liu, Yitao Xu, Dianguo School of Electrical Engineering and Automation Harbin Institute of Technology Harbin150001 China Shenzhen University College of Mechatronics and Control Engineering Shenzhen518060 China

Owing to the greater integration capability, flexible multilayer foil (FMLF) technique has a great potential to promote the evolution of passive integration techniques. To understand the mechanism of this technique is essential for its applications and popularization. To this end, this paper reveals the fundamentals and terminal configuration principles to realize various functional electromagnetic integration units with FMLF technique. A regular FMLF winding is taken as the research object, from theoretical analyses on the associated distributed electromagnetic component (DEMC) circuits, the lumped electromagnetic component (LEMC) circuits with different terminal configuration modes are derived. Moreover, A FMLF winding prototype is built for experimental verifications. The LEMC circuits are demonstrated through the comparative analyses between practically measured and LTspice based simulated impedances or port characteristics. © 2021 IEEE.

关键词： Timing circuits

来源：评论

学校读者我要写书评

暂无评论

Human Cognitive Learning in Shared control via Differential Game With Bounded Rationality and Incomplete Information

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第10期5卷 5141-5152页

作者： Wu, Huai-Ning Jiang, Xiao-Yan Wang, Mi Beihang University Science and Technology on Aircraft Control Laboratory School of Automation Science and Electrical Engineering Beijing100191 China Hangzhou International Innovation Institute of Beihang University Hangzhou311115 China Beihang University School of Automation Science and Electrical Engineering Beijing100191 China

Since human beings are of limited reasoning ability as well as the machines do not usually know human intentions, how to learn human cognitive levels in shared control to enhance the machines’ intelligence is a challenging issue. In this study, this issue is addressed in the context of human–machine shared control for a class of human-in-the-loop (HiTL) systems based on a differential game with bounded rationality and incomplete information. Initially, we formulate the human–machine shared control problem as a two-player nonzero-sum linear quadratic dynamic game (LQDG), where the weighting matrix of the cost function representing the human intention is unknown for the machine. To model the human bounded rationality, the level-k (LK) approach is employed to set up the LK control policies of two players performing the corresponding steps of strategic thinking. To infer the human intention, an online adaptive inverse optimal control (IOC) algorithm is then developed by using the system state data, so that the control policies of different cognitive levels can be computed. In addition, a reinforcement learning method is proposed for the machine to identify the distribution of the human cognitive levels while providing a proactive collaborative control to assist the human in a probabilistic switching way. Finally, simulation results on a cooperative shared control driver assistance system (DAS) illustrate the efficacy of the proposed approach. © 2024 IEEE.

关键词： Game theory

来源：评论

学校读者我要写书评

暂无评论

Curve-Suppression-Based Event-Triggered Mechanisms for Quasi-Synchronization of Fuzzy Delayed Neural Networks on Time Scales

引用

IEEE Transactions on Systems, Man, and Cybernetics: Systems 2025年第5期55卷 3174-3187页

作者： Wan, Peng Zhou, Yufeng Zeng, Zhigang Lai, Jingang Wuhan University of Science and Technology School of Artificial Intelligence and Automation Engineering Research Center of Metallurgical Automation and Measurement Technology Wuhan430081 China Huazhong University of Science and Technology School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent control of Education Ministry of China Wuhan430074 China

The vast majority of published event-triggered mechanisms (ETMs) are constructed based on measurement errors, which introduces a problem naturally that they are updated when the measurement errors exceed the thresholds although the current obtained sampling states can make systems converge well. With this problem in mind, we redesign ETMs for quasi-synchronization of T-S fuzzy neural networks (FNNs) with time delays on time scales. First, a novel ETM is designed for continuous-time FNNs with time-varying delays to achieve quasi-synchronization, with which synchronization errors is suppressed to globally exponentially converge to a ball. Second, we introduce the ETM for continuous-time FNNs to discrete-time FNNs, owing to the existence of discrete-time states, the Lypunov function of synchronization errors run over the exponentially decay curve, but it can be suppressed to evolve under another exponentially decay curve. Third, for FNNs on time scales with constant and time-varying delays, we estimate the forward jump operator of the Lyapunov functions and design ETMs to guarantee that the Lypunov functions evolve under the exponentially decay curves, so quasi-synchronization can be achieved. Last but not least, we prove that Zeno behavior will not happen and four numerical examples are introduced to verify the validity and the superiority of the proposed ETMs in reducing information transmission. © 2013 IEEE.

关键词： Continuous time systems

来源：评论

学校读者我要写书评

暂无评论

Sliding mode active disturbance rejection control for uncalibrated visual servoing

引用

International Journal of Systems, control and Communications 2025年第2期16卷 133-151页

作者： Pu, Cuiping Wu, Yi Ren, Jie Ran, Chenyang College of Mechanical and Electrical Engineering Kunming University Kunming China School of Information and Control Engineering China University of Mining and Technology Xuzhou China Department of Automation Shanghai Jiao Tong University Shanghai China

A sliding mode control algorithm based on a linear extended state observer is proposed to address the multi-source uncertainty of uncalibrated visual servoing in robotic arms. Uncertainty, nonlinearity, coupling, external disturbances, etc. are considered as total disturbances. The linear expansion state observer is designed to observe the total disturbance and compensate for it. This enhances the system’s anti-interference ability. The outer loop adopts sliding mode control law as state feedback. It suppresses the observation errors of the observer and ensures the stability of the system. Sliding mode control based on linear extended observer does not depend on specific tasks and system configurations. It provides a unified design framework for solving the problem of uncalibrated visual servoing. Through numerical simulations of three different disturbance cases, it was compared with PI linear extended state observer and linear active disturbance rejection to verify its good dynamic performance and disturbance rejection performance. Copyright © 2025 Inderscience Enterprises Ltd.

关键词： Robotic arms

来源：评论

学校读者我要写书评

暂无评论

Iron ore pellets measurement using deep learning based on YOLACT

引用

Neural Computing and Applications 2024年第24期36卷 14909-14924页

作者： Santos, Caio Mario Carletti Vilela de Almeida, Ricardo Valadao, Carlos Torturella Cuadros, Marco Antonio de Souza Leite Almeida, Gustavo Maia de Postgradude Program of Control and Automation Engineering Federal Institute of Espírito Santo Avenida dos Sabiás Espirito Santo Serra29166-630 Brazil

The thermal efficiency for the pelletizing process is intrinsically linked to the diameter and humidity of the iron ore pellets, so that the sensing of the granulometric range in the formation of the pellets becomes essential to the flow of the pelletizing process in the steel industry;this paper presents the assembly of a computer vision system for the detection and segmentation of pellets aiming at the automation of the granulometric measurement, following its formation in the pelletizing disk, using the instance segmentation method to verify whether the particle granulometric distribution (PSD) is adequate for "real-time" applications. The system calculates the normal distribution of the diameter in millimeters, evaluating the normal curve and the standard deviation of the segmented pellets, using a deep neural network based on the You Only Look At CoefficienTs (YOLACT) network, adding speed and precision in the granulometric analysis. In the sample sets, the need for adjustment factors inherent to the pelletizing process became evident. This led to the establishment of the computer vision system, termed the Volumetric Correction Factor (VCF) and Visual Overlay Factor (VOF). The VCF is utilized to estimate the volume of pellets within the pelletizing disk during operation, while the VOF adjusts the millimeter-per-pixel (mpp) ratio. The results of the measurement system proved to be efficient in real-time granulometric measurement. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Pelletizing

来源：评论

学校读者我要写书评

暂无评论

BeltLineNet: A Shape-Prior-Guided Lightweight Network for Real-Time Deviation Detection in Circular Pipe Conveyors

引用

IEEE Sensors Journal 2025年第11期25卷 20024-20036页

作者： Zhao, Long Su, Jinhui Zhong, Yusheng Xie, Weiwei Su, Jinya Chen, Xisong Chen, Congyan Li, Shihua Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education School of Automation Nanjing210096 China Fujian Longking Intelligent Conveying Engineering Co. Ltd Longyan China

Belt deviation in circular pipe conveyor systems could lead to material spillage, environmental contamination, reduced efficiency, and accelerated belt wear. Real-time belt deviation detection is crucial for ensuring safe and efficient operation. However, existing methods, primarily developed for flat-belt systems, heavily rely on distinct belt-background semantics, making them unsuitable for circular conveyors where indistinct target features, motion blur, and occlusions pose significant challenges. To address these issues, we reformulate the deviation detection task as an object detection problem, proposing BeltLineNet, a lightweight, real-time deviation detection network specifically designed for circular pipe conveyors. Our method integrates explicit feature learning with a coarse-to-fine global feature fusion mechanism, enhancing belt line representation under complex conditions. Additionally, a shape-prior loss strategy is introduced to improve supervision during training, ensuring more accurate detection of elongated targets. The model is also optimized for real-time deployment through layer-adaptive pruning, achieving a balance between accuracy and computational efficiency. Extensive comparative experiments involving 8 state-of-the-art (SOTA) feature extraction networks and 6 feature enhancement strategies on a self-collected dataset under industrial conditions demonstrate that BeltLineNet surpasses SOTA feature extraction and fusion networks, improving average precision (AP) by 8.23% before pruning and 6.33% after pruning. © 2001-2012 IEEE.

关键词： Belt conveyors

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：