检索结果-内蒙古大学图书馆

A Data-Based Feedback Relearning Algorithm for Uncertain Nonlinear Systems

IEEE/CAA Journal of Automatica Sinica 2023年第5期10卷 1288-1303页

作者： Chaoxu Mu Yong Zhang Guangbin Cai Ruijun Liu Changyin Sun the School of Electrical and Information Engineering Tianjin UniversityTianjin 300072China the College of Missile Engineering Rocket Force University of EngineeringXi’an 710025China the School of Computer and Information Engineering Beijing Technology and Business UniversityBeijing 100048China the School of Automation Southeast UniversityNanjing 210096China

In this paper,a data-based feedback relearning algorithm is proposed for the robust control problem of uncertain nonlinear *** by the classical on-policy and off-policy algorithms of reinforcement learning,the online feedback relearning(FR)algorithm is developed where the collected data includes the influence of disturbance *** FR algorithm has better adaptability to environmental changes(such as the control channel disturbances)compared with the off-policy algorithm,and has higher computational efficiency and better convergence performance compared with the on-policy *** processing based on experience replay technology is used for great data efficiency and convergence *** experiments are presented to illustrate convergence stability,optimality and algorithmic performance of FR algorithm by comparison.

关键词： Data episodes experience replay neural networks reinforcement learning(RL) uncertain systems

来源：评论

学校读者我要写书评

暂无评论

IMPROVED LIGHTWEIGHT MULTISCALE FINGER VEIN RECOGNITION FOR VISION TRANSFORMER

UPB Scientific Bulletin, Series C: Electrical Engineering an...

引用

UPB Scientific Bulletin, Series C: Electrical engineering and Computer Science 2024年第2期86卷 285-296页

作者： Tao, Zhiyong Gao, Yajing Lin, Sen School of Electronic and Information Engineering Liaoning Technical University Liaoning Huludao125105 China School of Automation and Electrical Engineering Shenyang Ligong University Liaoning Shenyang110159 China

Finger vein recognition methods suffer from ignoring local information, complexity and slow recognition speed when applying Transformer architecture. In this paper, an improved visual transformer multi-scale finger vein recognition method is proposed. Specifically, the network backbone adopts the improved visual transformer architecture and grouped convolutional structure. The improved vision transformer architecture can extend the global features of an image while simultaneously reducing the computational cost-effectively. Group convolution realizes low-cost multi-scale image feature extraction. The experiment showed that the method proposed in this paper has a recognition accuracy of 99.86%, which is more suitable for industrial deployment than other state-of-the-art works. © 2024, Politechnica University of Bucharest. All rights reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Symmetry-informed reinforcement learning and its application to low-level attitude control of quadrotors

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第3期5卷 1147-1161页

作者： Huang, Junchang Zeng, Weifeng Xiong, Hao Noack, Bernd R. Hu, Gang Liu, Shugao Xu, Yuchen Cao, Huanhui School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen Shenzhen518055 China School of Civil and Environmental Engineering Harbin Institute of Technology Shenzhen Shenzhen518055 China

Symmetry is ubiquitous in nature, physics, and mathematics. However, a classical symmetry-Agnostic reinforcement learning (RL) approach cannot guarantee to respect symmetry. Researchers have shown that if the symmetry of a system cannot be respected, the performance of a symmetry-AgnosticRL approach can be inhibited. To this end, this article develops a generally applicable neural network (NN) module with symmetry that can enforce the symmetry of a system to be *** on theNNmodulewith symmetry, this article proposes a symmetry-informed model-based RL (MBRL) approach that respects symmetry and improves data efficiency. The symmetry-informed MBRL approach is applied to the attitude control of a quadrotor in simulation to evaluate the effectiveness of the approach. The simulation results show that the data efficiency of the symmetry-informedMBRLapproach is much superior to that of a symmetry-Agnostic MBRL approach. An NN module with symmetry can respect the symmetry of a quadrotor while a naive NN cannot enforce the symmetry of a quadrotor to be respected. Impact Statement-Symmetry is ubiquitous in nature and has been used in physics and mathematics to help make models tractable for *** ReinforcementLearning (RL) has achieved success in ATARI, GO, robots, and flow control in recent years, RL cannot guarantee to satisfy symmetry. Researchers have shown that for a system with symmetry, the performance of RL is limited without forcing symmetry to be respected. This paper develops a generally applicable Neural Network (NN) module with symmetry to achieve an NN-based model that enforces symmetry to be respected. A symmetry-informed Model-Based RL (MBRL) approach that satisfies symmetry is established based on the NN module with symmetry. This paper paves a way for integrating ubiquitous symmetry into MBRL to improve the performance of MBRL in learning and deployment and improves the feasibility of deploying RL in the real world. © 2023 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Sliding-mode-based preassigned-time control of a class of memristor chaotic systems

引用

Chinese Physics B 2024年第11期33卷 161-166页

作者： Jinrong Fan Qiang Lai Qiming Wang Leimin Wang College of Computer Science South-Central Minzu UniversityWuhan 430074China School of Electrical and Automation Engineering East China Jiaotong UniversityNanchang 330013China School of Automation China University of GeosciencesWuhan 430074China

This paper addresses the preassigned-time chaos control problem of memristor chaotic systems with time *** the introduction of memristor,the presented models are nonlinear systems with chaotic ***,the TS fuzzy method is adopted to describe the chaotic ***,a sliding-model-based control approach is proposed to achieve the preassigned-time stabilization of the presented models,where the upper bound of stabilization time can be arbitrarily specified in ***,simulation results demonstrate the validity of presented control approach and theoretic results.

关键词： memristor chaotic system TS fuzzy method preassigned-time stabilization sliding-mode control

来源：评论

学校读者我要写书评

暂无评论

Carrier Phase Synchronization Based on Circulating Current Identification for Distributed Inverters

引用

IEEE Transactions on Power Electronics 2025年第8期40卷 10433-10442页

作者： Zhang, Jiakang Zhou, Dehong Zou, Jianxiao Liu, Xin Zhang, Hong Shen, Zewei School of Automation Engineering Chengdu611731 China UESTC Shenzhen Institute for Advanced Study Chengdu611731 China

Distributed parallel inverters are a promising solution for large power systems due to their flexibility and reliability. However, the distributed control mode often causes carrier phase desynchronization among the control units, leading to adverse effects on high-frequency harmonics and power loss. To address this issue, this article proposes a carrier phase synchronization (CPS) method for distributed parallel inverters, leveraging circulating current identification. In the proposed scheme, circulating currents in parallel inverters directly influence high-frequency harmonics and carry carrier phase information. The peak amplitude of these currents is used to identify the CPS point and adaptively adjust the carrier phase difference. The proposed strategy leverages existing circulating currents to achieve CPS in parallel inverters, eliminating the need for additional synchronization hardware. Consequently, this solution not only reduces system costs and size but also enables CPS-based multifunctionality, such as power quality optimization and common mode reduction. Finally, both simulation and experimental results are provided to validate the effectiveness of the proposed CPS method and the associated analysis. © 1986-2012 IEEE.

关键词： Inverters Synchronization Voltage Harmonic analysis Accuracy Renewable energy sources Hardware Costs Training Topology

来源：评论

学校读者我要写书评

暂无评论

Adaptive composite anti-disturbance control for heavy haul trains

引用

Transportation Safety and Environment 2024年第1期6卷 75-82页

作者： Longsheng Chen Hui Yang School of Electrical and Automation Engineering East China Jiaotong UniversityNanchang 33013JiangxiChina School of Aircraft Engineering Nanchang Hangkong UniversityNanchang 330063JiangxiChina

In this paper,an adaptive composite anti-disturbance control of heavy haul trains(HHTs)is ***,the mechanical principle and characteristics of couplers are analysed and the longitudinal multi-particles nonlinear dynamic model of HHTs is established,which can satisfy that the forces of vehicles in different positions are ***,a radial basis function network(RBFNN)is employed to approximate the uncertainties of HHTs,and a nonlinear disturbance observer(NDO)is constructed to estimate the approximation error and external *** indicate and improve the approximation accuracy,a serial-parallel identification model of HHTs is constructed to generate a prediction error,and an adaptive composite anti-disturbance control scheme is developed,where the prediction error and tracking error are employed to update RBFNN weights and an auxiliary variable of ***,the feasibility and effectiveness of the proposed control scheme are demonstrated through the Lyapunov theory and simulation experiments.

关键词： heavy haul train(HHT) radial basis function neural network nonlinear disturbance observer(NDO) serial-parallel identification model composite anti-disturbance control

来源：评论

学校读者我要写书评

暂无评论

Evaluation method and optimization strategies of resilience for air&space defense system of systems based on kill network theory and improved self-information quantity

引用

Defence Technology（防务技术） 2023年第3期21卷 219-239页

作者： Qi Han Bo Pang Sen Li Ning Li Peng-song Guo Cheng-li Fan Wei-min Li Air Defense and Antimissile School Air Force Engineering UniversityXi’an710051China Graduate School Air Force Engineering UniversityXi’an710051China Information and Navigation School Air Force Engineering UniversityXi’an710077China School of Automation Science and Engineering Xi'an Jiaotong UniversityXi'an710049China

Resilience of air&space defense system of systems(SoSs)is critical to national air defense ***,the research on it is still *** this study,the resilience of air&space defense SoSs is firstly defined and the kill network theory is established by combining super network and kill chain *** cases of the SoSs are considered:(a)The kill chains are relatively homogenous;(b)The kill chains are relatively ***,two capability assessment methods,which are based on the number of kill chains and improved self-information quantity,respectively,are *** improved self-information quantity modeled based on nodes and edges can achieve qualitative and quantitative assessment of the combat capability by using linguistic Pythagorean fuzzy ***,a resilient evaluation index consisting of risk response,survivability,and quick recovery is proposed ***,network models for regional air defense and anti-missile SoSs are established respectively,and the resilience measurement results are verified and analyzed under different attack and recovery strategies,and the optimization strategies are also *** proposed theory and method can meet different demands to evaluate combat capability and optimize resilience of various types of air&space defense and similar SoSs.

关键词： network optimization theory

来源：评论

学校读者我要写书评

暂无评论

A method for recognizing facial expression intensity based on facial muscle variations

引用

Multimedia Tools and Applications 2025年第18期84卷 19087-19116页

作者： Zhang, Yukun Fei, Zixiang Li, Xia Zhou, Wenju Fei, Minrui The School of Mechatronic Engineering and Automation Shanghai University Shanghai200444 China The School of Computer Engineering and Science Shanghai University Shanghai200444 China The Shanghai Jiaotong University Shanghai200240 China

Expression intensity recognition is a research problem in the field of computer vision and pattern recognition, which can be understood as the salience, or intensity, of an expression. Existing techniques for expression intensity recognition find it difficult to capture the texture features of expressions, which results in low recognition accuracy. Therefore, this paper proposes a method for recognizing expression intensity based on facial muscle changes to address this issue. This method captures texture motion information of facial muscles using optical flow, determining the motion regions and static regions of facial texture based on optical flow magnitude. The movement areas of facial expressions are set as salient regions, and the intensity of emotions is classified based on the variation rate of muscles within these regions. The proposed algorithm exhibits good recognition accuracy on publicly available datasets such as CK +, MMI, and datasets collected from real scenarios, including those involving elderly individuals. The average recognition accuracy reaches 82.7%. The proposed algorithm demonstrates a strong ability to recognize the intensity of facial expressions. This study provides technical support for the development of a real-time mood monitoring system. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

A Walk Primitive with Double Support for Biped Robots

引用

Journal of Bionic engineering 2025年第1期22卷 133-143页

作者： Guoshuai Liu Zhiguo Lu Zhongqing Li Jin Xuan Aizun Liu School of Mechanical Engineering and Automation Northeastern UniversityShenyang110819China Aerospace Times FeiHong Technology Company Limited OrganizationBeijing100094China

Walking is the basic locomotion pattern for bipedal *** walking pattern is widely generated using the linear inverted pendulum *** linear inverted pendulum motion of each support period can be designed as a walk primitive to be connected to form a walking trajectory.A novel method of integrating double support phase into the walk primitive was proposed in this *** method describes the generation of walking patterns using walk primitives with double support,specifically for lateral plane including walking in place,walking for lateral,and walking initiation,and for sagittal plane including fixed step length walking,variable step length walking,and walking *** to walk primitives without double support phase,those with double support phase reduce the maximum speed required by the robot and eliminate the need to adjust foothold for achieving continuous *** performance of the proposed method is validated by simulations and experiments on Neubot,a position-controlled biped robot.

关键词： Biped robot Linear inverted pendulum Walk primitive Double support

来源：评论

学校读者我要写书评

暂无评论

Dynamic Performances of a Double-Layer Vibration Isolation System:Nonlinear Modeling and Experimental Validation

引用

International Journal of Mechanical System Dynamics 2025年第1期5卷 113-128页

作者： Chao Zheng Jin Gao Jianchao Liu Xin Xue School of Mechanical Engineering and Automation Institute of Metal Rubber&Vibration NoiseFuzhou UniversityFuzhouChina

This work aims to identify ways to achieve dynamic performances of a novel double-layer vibration isolation system(DL-VIS)capable of achieving multi-directional isolation and extreme environmental adaptability.A forward modeling approach applicable to complex systems has been developed and analyses of nonlinear dynamic characteristics under different working conditions are ***,by integrating with constitutive models in terms of individual elastic elements and the connective relationships within the structure,multidirectional constitutive models for isolation devices are ***,the decomposition of linear and nonlinear stiffness components in different directions is performed using the Taylor expansion ***,the dynamic response under sinusoidal sweep frequency loading is obtained using the related stiffnesses in the dynamic model and adopting the extended harmonic balance *** effects of stiffness,damping,and a nonlinear stiffness gradient on the DL-VIS response are thoroughly ***,the vibration isolation performance and nonlinear dynamics under different working conditions are examined,and the proposed dynamic model is experimentally *** results indicate that the response of DL-VIS varies significantly under different working conditions,particularly under overload *** nonlinear characteristics lead to wide-band instability near the natural frequency and excellent vibration attenuation performance in multiple *** theoretical model agrees well with the experimental results in the nonresonant region and near the first resonant peak,which proves the prediction accuracy in the low-frequency *** findings provide robust theoretical and technical support for the design and performance optimization of isolation systems.

关键词： double-layer vibration isolation system dynamic model experimental validation harmonic balance method nonlinear

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：