检索结果-内蒙古大学图书馆

Conference on Vehicle control and Intelligence (CVCI)

作者： Dongxue Zhang Huiwen Liu Xiaohong Jiao Ting Zhang Hebei Key Laboratory of Industrial Computer Control Engineering Yanshan University Qinhuangdao Hebei Province China School of Vehicle and Mobility Tsinghua University Beijing China

ISBN: (数字)9798331504892

ISBN: (纸本)9798331504908

Navigating the intricate traffic environment, lane-changing has emerged as a frequent and essential driving maneu-ver for intelligent vehicles. However, it is challenging to guarantee the safety of the intelligent vehicle and the trajectory tracking accuracy against the external environment during lane-changing. Considering these challenges to overcome, the model predictive control (MPC)-based trajectory tracking strategy incorporating an autonomous lane-changing mechanism is proposed in this paper. The autonomous lane-changing mechanism considering lane-changing intention is proposed to ensure that the intelligent vehicle generates safe lane-changing decisions and trajectories. Subsequently, the MPC strategy that considers the physical char-acteristics of the intelligent vehicle is proposed to guarantee the accuracy and smoothness of trajectory tracking. The validation of its effectiveness and advantages is established on the PreScan and MATlab/Simulink co-simulation platforms.

关键词： Accuracy Intelligent vehicles Trajectory tracking Navigation Vehicle safety Trajectory MATlab Predictive control

来源：评论

学校读者我要写书评

暂无评论

A switching-based backstepping sliding mode control for space manipulator in presence of gravity variation

引用

High Technology Letters 2021年第4期27卷 454-462页

作者： Liu Fucai Zhao Wenna Meng Lingcong Liu Shuo Key Laboratory of Industrial Computer Control Engineering of Hebei Province Yanshan UniversityQinhuangdao 066004P.R.China Engineering Department University of SheffieldSheffieldUK

A novel switching-based backstepping sliding mode control(SBSMC) scheme is devised for the space manipulator exposed to different *** a view to distinct differences in dynamics properties when the operating conclition of space manipulator changer,the space manipulator can be thought of as a system composed of two subsystems,the ground subsystem and the space *** different types of backstepping sliding mode(BSM) controllers are designed,one is suited for the ground subsystem and the other is for the space *** switching between two subsystems can be implemented automatically when the switching mechanism is triggered,and the controllers for their subsystems experience synchronous *** this way,the space manipulator always has good behaviors in trajectory ***,multi-Lyapunov functions are introduced to prove the stability of this switching *** to simulation results,the method constructed in this research has better performance in control precision and adaptability compared with proportional-derivative(PD) control.

关键词： space manipulator microgravity switching system multi-Lyapunov functions backstepping sliding mode control(BSMC)

来源：评论

学校读者我要写书评

暂无评论

Defect Detection in Solar Panels Based on PV-Flow

Defect Detection in Solar Panels Based on PV-Flow

引用

WRC Symposium on Advanced Robotics and Automation (WRC SARA)

作者： Minghao Niu Jiaqi Li Mengyu Li Yifan Zhao Ying Liu Shuhuan Wen Key Laboratory of Industrial Computer Control Engineering of Hebei Province Key Lab of Intelligent Rehabilitation and Neuroregulation in Hebei Province Engineering Research Center of the Ministry of Education for Intelligent Control System and Intelligent Equipment Yanshan University Qinhuangdao China Yingli Energy Development Co. Baoding China

ISBN: (数字)9798331506100

ISBN: (纸本)9798331506117

With technological advancements, resource utilization has increased, making renewable energy sources like solar power essential. Effective defect detection for solar panels is crucial. However, manual inspection is currently inefficient and machine vision lacks accuracy. In order to improve defect detection in high-resolution images and overcome the limitations of existing methods, we propose an unsupervised deep learning model called PV-Flow, which combines a hybrid attentional mechanism and a multiscale feature extraction module of the flow model. Before defect detection we need to categorize the defects and make a dataset, after observing the features we classify the defects into black spots, broken grids, hidden cracks and fragmentations. The performance of the model while performing defect detection is evaluated by metrics of reconstructed images and visual comparisons. Experiments on real solar panel datasets show that our proposed PV-Flow model is able to accurately identify the location of broken gate defects and show more details, with even the smallest defects clearly labeled and magnified. This suggests that our proposed model is able to detect potential defects earlier, thus reducing production risks and costs. We also conducted comparative experiments to further validate the reliability of the model.

关键词： Deep learning Visualization Accuracy Costs Sensitivity Production Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Energy Efficiency Maximization for Hybrid Access Femtocell Networks via Incentive Mechanism and Power control Strategy

Energy Efficiency Maximization for Hybrid Access Femtocell N...

引用

IEEE International Conference on Cyber Technology in Automation, control, and Intelligent Systems

作者： Xuelin Liu Weimin Wang Zhixin Liu School of control science and engineering Dalian University of Technology Dalian China School of electrical engineering Yanshan University Qinhuangdao China Key Lab of Industrial Computer Control Engineering of Hebei Province Qinhuangdao Hebei Province China

Femtocell network has a great development space in increasing coverage and capacity of wireless network. In order to meet the quality of service (QoS) requirements of MUEs in MBS coverage, we propose a seed channel incentive mechanism in the two-tier femtocell network, where the MBS provides sub-channels to FBSs to motivate them to serve for the MUEs within the MBS coverage. To maximize the energy efficiency of femtocell layer after hybrid access, the optimization problem is modeled. The combined method of worst-case, Dinkelbach and continuous convex approximation is developed to make the optimization problem solvable. In addition, in order to realize the practical application of the proposed scheme, an optimization algorithm combining sub-channel and power allocation is developed. The numerical results show that the proposed algorithm is effective in improving the energy efficiency of the femtocell layer.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamic Multi-Objective Optimization Algorithm for Classification of Decision Variables Based on Objective Monotonicity

SSRN

引用

SSRN 2023年

作者： Wei, Lixin Yang, Qingshuai Guo, Zeyin Institute of Electrical Engineering Yanshan University Hebei Qinhuangdao066004 China Key Lab of Industrial Computer Control Engineering of Hebei Province Yanshan University Hebei Qinhuangdao066004 China

Dynamic multi-objective optimization problems (DMOPs) are prevalent in daily life, and the aim of dealing with DMOPs is to track the moving Pareto Front(PF) and find a series of Pareto Sets (PS) at different moments. Strategies based on decision variable classification improve the performance of multi-objective evolutionary algorithms. However, it has been a challenge to ensure fast and accurate classification. In this study, a decision variable classification method based on objective monotonicity(CDMO) is proposed to reduce the negative effects of inaccurate classification. In addition, a multi-step convergence prediction method and a diversity maintenance strategy are proposed to improve the algorithm performance. The effectiveness of the CDMO algorithm is verified by comparing it with three state-of-the-art DMOEAs on 16 benchmark test problems. The experimental results show that the CDMO algorithm is able to obtain high-quality populations with good convergence and distributivity in a dynamic environment. © 2023, The Authors. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Contextual Multi-Armed Bandit-Based Dynamic Cooperative Link Configuration for AUV in UWASNs With Energy Harvesting

引用

IEEE Transactions on Cognitive Communications and Networking 2025年

作者： Dai, Jun Li, Xinbin Han, Song Yu, Junzhi Liu, Zhixin Yanshan University Key Lab of Industrial Computer Control Engineering of Hebei Province Qinhuangdao066004 China Yanshan University Key Laboratory of Intelligent Rehabilitation and Neuromodulation of Hebei Province Qinhuangdao066004 China Peking University State Key Laboratory for Turbulence and Complex Systems Department of Advanced Manufacturing and Robotics BIC-ESAT College of Engineering Beijing100871 China

This paper investigates the cooperative link configuration problem for Autonomous Underwater Vehicle (AUV) in Underwater Acoustic (UWA) sensor networks with Energy Harvesting (EH), which aims to maximize long-term cumulative capacity by jointly optimizing cooperation relay, AUV transmission power, and relay transmission power. Subject to unknown time-varying Channel State Information (CSI), unpredictable stochastic EH, and variable communication topology caused by AUV mobility, the proposed problem is an unknown dynamic combination decision optimization problem. To resist the change of the dynamic UWA communication topology with unknown time-varying CSI and EH, a novel collaborative contextual multi-armed bandit learning framework is proposed, which allows relay nodes to learn cooperatively and enriches the learning information of relays. Consequently, the proposed learning framework can resist the change of the dynamic UWA communication topology efficiently, thereby achieving the superior link configuration quickly. Besides, a learning-rate adjustment rule for the dynamic UWA communication topology is proposed to adaptively balance the exploration-exploitation, thereby avoiding missing the real superior joint relay-power configuration. Finally, simulation results show the significantly superiority of the proposed scheme. © 2015 IEEE.

关键词： Cooperative communication

来源：评论

学校读者我要写书评

暂无评论

Optimal Time and Power Allocation in Full-Duplex Wireless-Powered Cognitive Radio Networks

Optimal Time and Power Allocation in Full-Duplex Wireless-Po...

引用

IEEE International Conference on Cyber Technology in Automation, control, and Intelligent Systems

作者： Zhenyu Feng Ming Su Meihua Zhou Zhixin Liu School of Electrical Engineering Yanshan University Qinhuangdao China Training Center of Liren College Yanshan University Key Lab of Industrial Computer Control Engineering of Hebei Province Qinhuangdao Hebei Province China

In this paper, we integrate wireless powered communication networks (WPCNs) with cognitive radio networks (CRNs) in order to develop wireless powered CRNs (WP-CRNs). The hybrid access point (HAP) is used to broadcast radio-frequency signals to the devices at the downlink stage, and to receive information from these devices. The HAP has two antennas to achieve full-duplex: one is for downlink wireless power transfer and the other is for receiving uplink information transmission from the users simultaneously in the uplink. In the underlay paradigms. The SUs can harvest energy to transmit data when the interference to primary users (PUs) does not exceed a tolerable threshold. To tackle the above network issues, an optimal resource allocation method is proposed to maximize the secondary system uplink throughput. The optimization problem with respect to time and power allocation is formulated including the constraint of energy causality and interference level. The non-convex problem is transformed into an equivalent convex optimization problem, then the joint optimal power and time allocation (JOPTA) algorithm is presented to determine the optimal solutions. The effectiveness of the proposed algorithm is verified in the simulations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Event-Triggered Robust Model Predictive control for Multi-Agent Systems Under Hybrid Attacks

Event-Triggered Robust Model Predictive Control for Multi-Ag...

引用

Chinese control Conference (CCC)

作者： Yongxin Yin Jianxiong Li Chongyi Gao Yiming Fang Key Lab of Industrial Computer Control Engineering of Hebei Province Yanshan University Qinhuangdao China Department of Electromechanical Engineering Tangshan University Tangshan China

In this paper, the consensus control problem for multi-agent systems (MASs) suffering hybrid attacks is discussed, in which the hybrid attacks include randomly occurring deception attacks on system dynamic behavior and denial-of-service attacks (DoS). An event-triggered robust model predictive control (RMPC) method is presented to achieve the consensus of MASs under hybrid attacks. It can be proved that the consensus errors can be asymptotic with prescribed H ∞ performance, the sufficient condition for stability can be given in terms of linear matrix inequalities (LMIs), and the controller gains are obtained by solving an optimization problem involving some LMIs. Employing the event-triggered mechanism with maximum trigger interval, not only can not only save computation time and facilitate the efficiency of the shared resources but also can effectively be responsible for the negative impact of cyber-attacks on system performance. Finally, simulation results are given to illustrate the validity and effectiveness of the proposed method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Improved Artificial Potential Field Method for Formation control and Obstacle Avoidance of the Multi-Agents Systems

An Improved Artificial Potential Field Method for Formation ...

引用

Chinese Automation Congress (CAC)

作者： Yubiao Yan Jianxiong Li Haibo Dong Chongyi Gao Yiming Fang Key Lab of Industrial Computer Control Engineering of Hebei Province Yanshan University Qinhuangdao China Department of Electromechanical Engineering Tangshan University Tangshan China

Obstacle avoidance is a significant research content in multi-agents formation control. The obstacle avoidance of multi-agents systems is investigated in this paper, and an improved artificial potential field method (IAPF) is proposed to avoid unknown obstacles in multi-agent formation. Aiming at improving the efficiency of formation avoidance and solving the non-reachable and local minima problems, the dynamic sub-target algorithm is proposed. The proposed method enables the multi-agent system (MASs) to avoid obstacles smoothly and quickly and complete formation tasks in complex environments by tracking dynamic sub-target as well, in which the position and motion direction of adjacent agents are taken into account in the selection of a sub-target for the formation efficiency. In addition, a variable potential field range is defined to ensure the safety of the formation. Finally, several simulation results verify the superiority and effectiveness of the proposed approach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Federated Learning With Meta-Layers Training for Privacy-Preserving in Vehicular Consumer Electronics

引用

IEEE Transactions on Consumer Electronics 2024年

作者： Shen, Xiaoyang Li, Haibin Li, Yaqian Zhang, Wenming Alenazi, Mohammed J.F. Agarwal, Kadambri Yanshan University College of Electrical Engineering Hebei Qinhuangdao066000 China Key Laboratory of Industrial Computer Control Engineering of Hebei Province Hebei Qinhuangdao066000 China King Saud University College of Computer and Information Sciences Department of Computer Engineering Riyadh11451 Saudi Arabia ABES Engineering College Department of Computer Science and Engineering Ghaziabad201009 India

Vehicular consumer electronics, such as autonomous vehicles (AVs), need collecting large amounts of private user information, which face the risk of privacy leakage. To protect the privacy of consumers, researchers have proposed to apply federated learning (FL) to privacy-preserving vehicular consumer electronics, that is, leveraging FL for collaborative training of a decision model without exchanging the sensitive information generated by AVs. However, FL generally needs to exchange the gradients of client models periodically with the central server, which can be attacked by adversaries to infer user information. Thereby, it may still face the risk of privacy leakage. To solve that challenge, we put forward a novel FL framework, called FL with Meta-Layers Training (FL-MLT). Instead of exchanging the gradients of the client models, it exchanges, meta-layers with the central servers. Since meta-layers are only a slice of the client models, exchanging them helps protect privacy. On the other hand, they contain meta-knowledge to help the FL training process. In the experiments, we conduct extensive visual classification simulation to evaluate FL-MLT, and the experimental results demonstrate the superior performance of FL-MLT. © 1975-2011 IEEE.

关键词： Federated learning

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：