检索结果-内蒙古大学图书馆

Robust Consensus Tracking control of Uncertain Multi-Agent Systems With Local Disturbance Rejection

IEEE/CAA Journal of Automatica Sinica 2023年第2期10卷 427-438页

作者： Pan Yu Kang-Zhi Liu Xudong Liu Xiaoli Li Min Wu Jinhua She the Faculty of Information Technology and the Beijing Institute of Artificial Intelligence Beijing University of TechnologyBeijing 100124China IEEE the Department of Electrical and Electronic Engineering Chiba UniversityChiba 263-8522Japan the Beijing Aerospace Automatic Control Institute Beijing 100854China the School of Automation China University of GeosciencesWuhan 430074China the School of Engineering Tokyo University of TechnologyHachiojiTokyo 192-0982Japan

In this paper,a new distributed consensus tracking protocol incorporating local disturbance rejection is devised for a multi-agent system with heterogeneous dynamic uncertainties and disturbances over a directed *** is of two-degree-of-freedom ***,a robust distributed controller is designed for consensus tracking,while a local disturbance estimator is designed for each agent without requiring the input channel information of *** condition for asymptotic disturbance rejection is ***,even when the disturbance model is not exactly known,the developed method also provides good disturbance-rejection ***,a robust stabilization condition with less conservativeness is derived for the whole multi-agent ***,a design algorithm is ***,comparisons with the conventional one-degree-of-freedombased distributed disturbance-rejection method for mismatched disturbances and the distributed extended-state observer for matched disturbances validate the developed method.

关键词： Directed graph distributed control disturbance rejection dynamic uncertainties multi-agent systems robust control

来源：评论

学校读者我要写书评

暂无评论

Expression recognition based on convolutional difference contextual feature fusion

Expression recognition based on convolutional difference con...

引用

2022 International Conference on Electronic Information engineering and Computer Science, EIECS 2022

作者： Lu, Shengfu Yang, Chuang Li, Mi Kang, Jiaming Faculty of Information Technology Beijing University of Technology Beijing International Collaboration Base on Brain Informatics and Wisdom Services Engineering Research Center of Intelligent Perception and Autonomous Control Ministry of Education Beijing China Department of Automation Faculty of Information Technology Beijing University of Technology Beijing China Department of Automation Faculty of Information Technology Beijing China

ISBN: (纸本)9781510663312

Facial expression recognition has always been a focus of study in emotion computing. With the aim of solving the problem that previous facial expression recognition studies are susceptible to individual differences and background noise, as well as the loss of facial expression features in deep networks of deep convolutional networks, we propose a facial expression method based on convolutional difference contextual feature fusion. The convolutional difference module can carry out difference operation between emotional image and neutral image in the input image, eliminate individual difference and background noise in expression features and improve the accuracy and generalization of the network. Finally, convolutional difference and contextual features are combined to improve the accuracy of the network further. Experiment results of 4 public facial expression datasets illustrate that compared with the existing facial expression recognition methods, this method has higher accuracy, can extract facial expression features more effectively, and has a better generalization ability. © 2023 SPIE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Optimizing Indoor Vertical Farming with DDPG Reinforcement Learning: Enhancing control of Nutrient Levels, Climate Conditions, and Plant Health 5

Optimizing Indoor Vertical Farming with DDPG Reinforcement L...

引用

5th IEEE International Conference on Technology, Informatics, Management, engineering and Environment, TIME-E 2024

作者： Albert Panggabean, Good Fried Romadhon, Rahmat Lubis, Ramot Joelianto, Endra Institut Teknologi Bandung Doctoral Program in Engineering Physics Bandung Indonesia Institut Teknologi Del Faculty of Informatics and Electrical Engineering Toba Indonesia Institut Teknologi Bandung Engineering Physics Study Program Bandung Indonesia Institut Teknologi Bandung Instrumentation Control and Automation Research Group Bandung Indonesia

ISBN: (纸本)9798350364743

In indoor vertical farming systems, managing dynamic and complex environments poses significant challenges. Traditional control strategies often fall short in adapting to rapid changes in critical parameters such as nutrient levels, climate conditions, and plant health indicators. To address these challenges, this paper presents a novel approach for optimizing indoor vertical farming using Deep Deterministic Policy Gradient (DDPG), a reinforcement learning algorithm well-suited for environments with continuous action spaces. Our study focused on the control and monitoring of key parameters, including nutrient levels (pH and EC), climate conditions (temperature, humidity, light, and CO2 levels), and plant health indicators (biomass accumulation and leaf size structure). By defining a comprehensive state and action space, we simulated an indoor farming environment and trained the DDPG model to maximize crop yield and health. © 2024 IEEE.

关键词： DDPG indoor vertical farming precision agriculture reinforcement learning smart farming

来源：评论

学校读者我要写书评

暂无评论

A Fractional-Order Nonlinear Backstepping controller Design for Current-controlled Maglev System

arXiv

引用

arXiv 2025年

作者： Astekin, Dorukhan Adigüzel, Fatih Yıldız Technical University Electric-Electronic Faculty Department of Control and Automation Engineering İstanbul Turkey

The magnetic levitation system (Maglev) is a nonlinear system by which an object is suspended with no support other than magnetic fields. The main control perspective of the Maglev system is to levitate a steel ball in air by the electromagnetic force. However, the Maglev system has highly nonlinear dynamics which is inconvenient in the sense of sensitive control/regulation of its nonlinear dynamics. In this paper, the nonlinear backstepping controller based on the fractional-order derivative is proposed for the control of the nonlinear current-controlled Maglev system. After, the system dynamics and fractional-order backstepping controller design are given, the asymptotic stability of the closed-loop system is proved by employing the Lyapunov theory. Some computer-based numerical experiments are carried out to show the effectiveness of the proposed controller for the control of Maglev system. © 2025, CC BY.

关键词： Magnetic levitation

来源：评论

学校读者我要写书评

暂无评论

Signal Processing for Acoustic Emission Signature Analysis and Defect Detection 26

Signal Processing for Acoustic Emission Signature Analysis a...

引用

26th International Conference on Digital Signal Processing and its Applications, DSPA 2024

作者： Altay, Yeldos A. Kuzivanov, Dmitry O. Altay, Dinara A. Fedorov, Alexey V. Satbayev University Department of Robotics and Technical Means of Automation Almaty Kazakhstan ITMO University Faculty of Control Systems and Robotics Saint-Petersburg Russia Military Engineering Institute of Radio Electronics and Communications Department of Natural Sciences Almaty Kazakhstan

ISBN: (纸本)9798350361728

This article presents the results of implementing a digital signal processing method for analyzing the acoustic emission (AE) signature and detecting defects such as cracks and pores. The signal processing method is based on a cascade connection of digital high-pass filters and ensures the selection of informative signals and increases the signal-to-interference ratio. In order to control the formation of defects in the process of selective laser melting, the paper presents the results of experimental testing of the cascade filtration method for detecting defects in the internal structure such as cracks and pores. The signal components recorded during the development of defects during the growth of additive manufacturing products were extracted. AE signatures were analyzed and statistical relationships were assessed. The relationship between the parameters of the AE signal and the values of laser radiation power has been identified, which characterizes the process of defect formation. © 2024 IEEE.

关键词： High pass filters

来源：评论

学校读者我要写书评

暂无评论

Amplitude control for an artificial hair cell undergoing an Andronov-Hopf bifurcation

引用

IFAC-PapersOnLine 2023年第1期56卷 181-186页

作者： Hermann Folke Johann Rolf Thomas Meurer Automation and Control Group Faculty of Engineering Kiel University Kaiserstr. 2 D-24143 Kiel Germany

The dynamics of an artificial hair cell is analyzed by considering the bifurcation behavior of a dominant mode model. It is shown that this model undergoes an Andronov-Hopf bifurcation similar to its biological counterpart, i.e., the hair cell in the mammalian cochlea. Consequently, this dynamical behavior is exploited to control the amplitude of the deflection of the artificial hair cell. In particular feedforward control with disturbance injection is designed based on an approximation of the oscillation using an envelope model to achieve a constant deflection amplitude. The approach is evaluated in numerical simulations.

关键词： Bifurcation analysis Andronov-Hopf bifurcation Envelope model Amplitude control Disturbance injection Neuromorphic engineering

来源：评论

学校读者我要写书评

暂无评论

Event-triggered learning of Euler-Lagrange systems: A Koopman operator framework 63

Event-triggered learning of Euler-Lagrange systems: A Koopma...

引用

63rd IEEE Conference on Decision and control, CDC 2024

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

ISBN: (纸本)9798350316339

Euler-Lagrange (EL) systems represent a crucial and large class of dynamical systems, and a precise model of the true system would be beneficial in planning and tracking problems. This work aims to learn an unknown EL system using noisy measurement data to achieve improved data utilization efficiency. Specifically, for the considered EL system, a linear representation of the system is constructed using the Koopman operator, which is further characterized by sample data using Willems' fundamental lemma. Moreover, an event-triggered learning mechanism is proposed to improve data utilization efficiency, and it is designed based on the analysis of the learning error bounds. The effectiveness of the proposed event-triggered learning approach is validated through a manipulator example. © 2024 IEEE.

关键词： Lagrange multipliers

来源：评论

学校读者我要写书评

暂无评论

DriveRP: RAG and Prompt engineering Embodied Parallel Driving in Cyber-Physical-Social Spaces 4

DriveRP: RAG and Prompt Engineering Embodied Parallel Drivin...

引用

4th IEEE International Conference on Digital Twins and Parallel Intelligence, DTPI 2024

作者： Huang, Jun Ma, Hao Zhang, Tengchao Lin, Fei Ma, Siji Wang, Xiao Wang, Fei-Yue Macau University of Science and Technology Faculty of Innovation Engineering China Anhui University School of Artificial Intelligence Hefei China Chinese Academy of Sciences State Key Laboratory for Management and Control of Complex Systems Institute of Automation Beijing China

ISBN: (纸本)9798350349252

In recent years, numerous technological advancements in Artificial Generative Intelligences (AGIs) have demonstrated significant potential to transform the intelligence acquisition mechanisms in connected autonomous vehicles (CAVs). Integrating technologies like ChatGPT into CAVs can enhance human-machine interactions. However, the emergence of such new traffic entities may introduce unforeseen hallucinations and complex risks that surpass our current understanding. To address these challenges, Retrieval-Augmented Generation (RAG) and prompt engineering technologies are being explored to enhance the reliability and safety of autonomous driving systems. RAG retrieves relevant contextual information, such as driving experiences and real-time road network status, from external databases to ensure that foundation models have access to accurate and timely data for informed decision-making. Prompt engineering optimizes the performance of large language models in autonomous driving systems by designing and refining prompts that guide the models' responses, thereby improving their relevance and accuracy in various driving scenarios. Together, these technologies enhance the robustness and trustworthiness of autonomous driving systems. This paper proposes DriveRP, a framework that integrates RAG and prompt engineering within the Descriptive-Predictive-Prescriptive Intelligence framework of Parallel Driving theory. DriveRP aims to enhance the safety and interpretability of autonomous vehicle trajectory planning, decision-making, and motion control, ultimately achieving the "6S"goals. Grounded in Digital Twins and Metaverse-embodied parallel driving theory, DriveRP provides the infrastructure and foundational intelligence for parallel driving with Multi-modal Large Lange Models(MLLMs). Additionally, the paper discusses future trends and potential research directions, focusing on the "6S"goals of parallel driving: Smart, Safe, Secure, Sensitive, Sustainable, and Serviceable. © 2

关键词： Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Adaptive Sensitivity Amplification control with Q-Learning for Cable-Driven Lower-Limb Exoskeletons 42

Adaptive Sensitivity Amplification Control with Q-Learning f...

引用

42nd Chinese control Conference, CCC 2023

作者： Zhong, Linzhen Wang, Xiaodong Gao, Guanbin Xing, Yashan Zhang, Faxiang Kunming University of Science and Technology Faculty of Information Engineering & Automation Kunming650500 China Kunming University of Science & Technology Faculty of Mechanical & Electrical Engineering Kunming650500 China Yunnan International Joint Laboratory of Intelligent Control and Application of Advanced Equipment Kunming650500 China

ISBN: (纸本)9789887581543

This paper proposes a sensitivity amplification control (SAC) based on Q-learning for the cable-driven lower-limb exoskeleton (CDLEX) to guarantee the tracking performance and achieve comfortable human-robot interaction (HRI). There is no requirement for direct measurement of HRI in the SAC scheme, hence the force/torque sensors are avoided. For the purpose of accommodating the uncertainties of the interaction environment, such as the individual gaits and suddenly changing walking trajectories, the Q-learning algorithm is utilized to realize online parameter tuning of SAC. Finally, comparative numerical simulations are included to verify the effectiveness of the control scheme. © 2023 Technical Committee on control Theory, Chinese Association of automation.

关键词： Human robot interaction

来源：评论

学校读者我要写书评

暂无评论

Event-Triggered Moving Block Train Platooning Scheme Under Communication Loss Constraint

Event-Triggered Moving Block Train Platooning Scheme Under C...

引用

Robotics, automation and Artificial Intelligence (RAAI), IEEE International Conference on

作者： Jonathan Chandra Tua A. Tamba Raymond Christian Dept. of Electrical Engineering Center for Control Automation and Systems Engineering Faculty of Engineering Technology Parahyangan Catholic University Bandung Indonesia

ISBN: (数字)9798331520038

ISBN: (纸本)9798331520045

This paper addresses the challenges of efficient coordination and safety assurance of moving block train platooning system. Conventional railway signaling method which relies on static block systems often fail to adapt to high frequency scenarios and thereby limiting the railway system's operational flexibility and scalability. The moving block signaling approach through communication-based train control (CBTC) technology has recently been proposed and viewed as a potential solution alternative to address such limitations. To enhance railway system opearational performance and safety, this paper proposes a control strategy combining sliding mode control (SMC) and event-triggered control (ETC) for a multi-agent system representation of train convoy operating under moving block signaling scheme. The proposed SMC is used to ensure robust tracking and coordination of the train convoy in the presence of inter-train communication loss, while ETC scheme is used to minimize communication and computation overhead in each train by updating the individual train's control actions only when deemed necessary. The proposed approach improves coordination, safety, and resource efficiency within complex, multi-agent train systems. Simulation results demonstrate the effectiveness of the combined control strategy in maintaining inter-train spacing even when data transmission loss/drop occur on several time instances.

关键词： Event detection Simulation Scalability Robot kinematics Block signalling Propagation losses Rail transportation Safety Sliding mode control Multi-agent systems

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：