检索结果-内蒙古大学图书馆

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

Trajectory Optimization of Manipulator for Loading and Unloading the Ladle Nozzle Based on Decomposition Multi-Objective Improved Whale Optimization Algorithm

Trajectory Optimization of Manipulator for Loading and Unloa...

引用

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

作者： Dongliang Zhao Yiming Fang Chen Yang Jingliang Xin Key Lab of Industrial Computer Control Engineering Yanshan University Qinhuangdao Hebei Province China Engineering Research Center of the Education Ministry for Intelligent Control System and Intelligent Equipment Yanshan University Qinhuangdao Hebei Province China Hebei Iron and Steel Group Tangshan Hebei Province China

In recent years, industrial manipulators are widely used in factories. To solve the problems of low efficiency and high joint jitter in ladle nozzle loading and unloading, a new trajectory optimization method is proposed. Firstly, a manipulator model is established on the base of mechanical construction and parameters of KR1000L750. And the 3-5-3 segmented polynomial interpolation approach is used to design the trajectory. Then a trajectory optimization model is proposed based on time and impact as optimization objectives. Secondly, the traditional whale optimization algorithm is improved by introducing a nonlinear adaptive convergence factor to balance the exploration and development of the algorithm. The improved algorithm has also added a new search mechanism during the exploration phase. To reduce the waste of exploration resources, the information on the current optimal solution is added by the Cauchy mutation method. Then, a decomposition-based multi-objective improved whale optimization algorithm (DMOIWOA) is proposed. The algorithm combines a penalty-based boundary intersection approach with the improved whale optimization algorithm. Six representative optimization algorithms are selected for comparison on the test functions. The DMOIWOA has evident superiority in convergence and distribution. Finally, the algorithm is applied to the trajectory optimization model to obtain a better Pareto front. In conclusion, the DMOIWOA can reasonably optimize the manipulator trajectory, improving the manipulator operation efficiency and reducing the manipulator jitter.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improved Lightweight YOLOv5 Based on GhostNet and Its Application in Target Board Detection for Ladle Nozzle Positioning

Improved Lightweight YOLOv5 Based on GhostNet and Its Applic...

引用

第43届中国控制会议

作者： Fengfei Si Yiming Fang Hao Ju Dongliang Zhao Jingliang Xin Key Lab of Industrial Computer Control Engineering of Hebei Province Yanshan University Engineering Research Center of the Education Ministry for Intelligent Control System and Intelligent Equipment Yanshan University Tangshan Branch HBIS Company Limited

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

The detection of the target board of ladle nozzle positioning is the basis of automatic loading and unloading of ladle nozzle by ladle robot in continuous casting. Due to the complex situation of high temperature, dust, backlight and so on, the target board of ladle nozzle positioning is prone to false detection or low detection accuracy, and it is difficult to take into account the contradiction between rapidity and detection accuracy. Therefore, this paper proposes an improved lightweight algorithm GVP-YOLOv5(YOLOv5 with GhostNet, VoVGSCSP and Pruning), which takes into account both detection accuracy and rapidity, to detect the target board for ladle nozzle positioning. Firstly, Ghost module is used to improve the backbone network of YOLOv5 as the backbone feature extraction network to reduce the number of parameters and calculation of the backbone. Then in the neck, the GSConv module is used to design a thin neck structure, which can ensure the multi-scale feature fusion capability and further reduce the complexity of the network. Finally, the model pruning technology is used to prune the whole model, and the channels with small scaling factor are removed to compress the model to the greatest extent, so as to meet the requirements of industrial field application deployment. The experimental results show that the lightweight GVP-YOLOv5 algorithm proposed in this paper can complete the real-time detection of the target board in complex industrial scenarios. Compared with the original YOLOv5s algorithm, the number of parameters in the model is reduced by 82.6%, and the size of the model is significantly reduced to 19.4%. At the same time, the detection accuracy is maintained at more than 95% on mAP@50:95 and the detection speed is effectively improved.

关键词： Target board detection Ladle nozzle positioning YOLOv5 lightweight GhostNet thin neck structure channel pruning

来源：评论

学校读者我要写书评

暂无评论

Rollover Prevention control for Autonomous Vehicles with High Centers of Gravity Considering Input Saturation

Rollover Prevention Control for Autonomous Vehicles with Hig...

引用

第43届中国控制会议

作者： Linying Lu Ting Zhang Lin Qi Jiayi Fang Xiaohong Jiao School of Electrical Engineering Yanshan University Key Lab of Industrial Computer Control Engineering of Hebei Province Yanshan University School of Vehicle and Mobility Tsinghua University School of Mechanical Engineering Beijing Institute of Technology

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

A fixed-time terminal sliding mode control(FTSMC) strategy based on extended state observer for cooperative control of rollover prevention and trajectory tracking is proposed to enable the high-center-of-gravity autonomous vehicles to ensure tracking performance and prevent rollover. The FTSMC allows the errors to converge globally to a predefined arbitrarily small set centered at zero in a fixed time and then exponentially converge to zero while weakening the influence of input saturation on the controller by compensating the auxiliary system of input saturation. Simulation comparisons with existing results verify the effectiveness and advantages of the designed strategy under the MATlab/Simulink environment.

关键词： Autonomous Vehicles Fixed-time Rollover Prevention Input Saturation

来源：评论

学校读者我要写书评

暂无评论

Configuration Synthesis of Weakly Coupled Parallel Hip Exoskeletons With Large Workspace

引用

Journal of Mechanisms and Robotics 2025年第7期17卷 074502页

作者： Xu, Jilong Liu, Fucai Engineering Research Center of the Ministry of Education for Intelligent Control System and Intelligent Equipment Yanshan University Qinhuangdao 066004 China Key Lab of Industrial Computer Control of Heibei Province Yanshan University Qinhuangdao 066004 China

To address the issues of strong motion coupling, high control difficulty, and insufficient degrees-of-freedom (DoFs) in existing bio-syncretic parallel hip exoskeletons, a design scheme characterized by weak coupling is proposed. A configuration synthesis method for weakly coupled parallel hip exoskeletons is introduced by deriving the conditions that the transmission wrench screws (TWSs) in each limb must satisfy. Furthermore, to tackle the problem of limited workspace in parallel hip exoskeletons, a design method aimed at increasing the operational workspace is presented. By applying the proposed methods to the configuration synthesis of the hip exoskeleton, several weakly coupled configurations with expanded workspaces are generated. Finally, the correctness and effectiveness of the proposed methods are validated through case analyses.

关键词： weakly coupled hip exoskeleton configuration synthesis parallel robots Screws mechanism synthesis and analysis wearable devices parallel mechanism Exoskeleton devices workspace mechanisms and robots

来源：评论

学校读者我要写书评

暂无评论

An Improved Model Predictive control of Wave Energy Converters Based on Weighted Optimization of Objective Function

SSRN

引用

SSRN 2023年

作者： Wang, Zhenchun Wang, Nianguo School of Electrical Engineering Yanshan University Qinhuangdao066004 China Key Lab of Industrial Computer Control Engineering of Hebei Province Yanshan University Qinhuangdao066004 China

This paper investigates the model predictive control (MPC) of a point-absorption sea wave energy converter (WEC). The dynamic model and information about upcoming waves serve as the foundation for MPC implementation, but building the plant model and forecasting waves will invariably introduce errors. As a result of this fact and the multi-step predictive optimization feature of MPC, a novel objective function based on the weighting factor is adopted in the MPC design, which has the following benefits: First, the weighting factor penalizes the objective function with errors at various steps in time, which can limit the adverse effects of uncertainties on the controller. Second, the weighting factor can better constrain the float displacement, ensuring the device’s safe operation. In addition, the weighting factor is optimized offline using a genetic algorithm, and its value changes depending on the sea state. The simulation results show the effectiveness of the proposed MPC strategy. © 2023, The Authors. All rights reserved.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

Distributed Fault-Tolerant Secondary control For Dc Microgrids Against False Data Injection Attacks

SSRN

引用

SSRN 2022年

作者： Xie, Zongkui Wu, Zhongqiang Key Lab of Industrial Computer Control Engineering of Hebei Province Yanshan University Qinhuangdao066004 China

This paper focuses on the issue of unknown false data injection attacks (FDIA) of controllers in DC microgrid, and proposes a distributed fault-tolerant secondary controller for DC microgrid to ensure that the control objectives of voltage regulation and current sharing can be achieved when the system is subject to FDIA. Firstly, the secondary control problem in DC microgrid with FDIA is transformed into a first-order leader-following multi-agent system fault-tolerant consensus problem, and the impact of FDIA signals on the microgrid system is analyzed. Then, a distributed extended state observer (DESO) is designed based on the derived multi-agent system, which observes the injected FDIA signals using the relative output error of each distributed generators and its neighbours. Further, based on the observed FDIA signals, a fault-tolerant secondary controller is designed to eliminate the adverse effects of the attack signals on the system. Particularly, the stability analyses for the designed DESO and secondary controller prove that the control system is global asymptotically stable. Finally, the effectiveness and superiority of the proposed fault-tolerant secondary control method for DC microgrids with FDIA are verified by simulation analyses of four cases. © 2022, The Authors. All rights reserved.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Fully Distributed Adaptive Finite Time Fault-Tolerant control for Multi-Agent Systems with Actuator Faults

Fully Distributed Adaptive Finite Time Fault-Tolerant Contro...

引用

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

作者： Xiaoqi Wang Yiming Fang Miao Xu Zhichao Lei Key Labpratory of Industrial Computer Control Engineering Yanshan University Qinhuangdao Hebei Province China Engineering Research Center of the Education Ministry for Intelligent Control System and Intelligent Equipment Yanshan University Qinhuangdao Hebei Province China

For a class of second-order nonlinear leader-following multi-agent systems with actuator faults and integral quadratic constraints (IQCs) of followers, a fully distributed adaptive consensus control algorithm based on improved PID sliding mode is designed. The algorithm only requires local topology information but no global information. According to Lyapunov stability theory, it is demonstrated that multi-agent systems can converge to the vicinity near equilibrium points within a finite time. Finally, the feasibility of the control algorithm proposed in this paper is verified by numerical simulation of multi-agent systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fast 3d-Graph Convolutional Networks for Skeleton-Based Action Recognition

SSRN

引用

SSRN 2022年

作者： Zhang, Guohao Wen, Shuhuan Li, Jiaqi Che, Haijun Department of Key Lab of Industrial Computer Control Engineering of Hebei Province Yanshan University Qinhuangdao066004 China

Research on human action recognition based on skeleton has received a lot of attention. But most of the research focuses on improving the generalization ability of the model, while ignoring significant efficiency issues. This leads to the development of heavy models with poor scalability and cost-effectiveness in practical use. In this paper, we investigate the under-studied but practically critical recognition model efficiency problem. To this end, we present a new Fast Recognition Distillation (FRD) model learning strategy. Specifically, FRD trains a lightweight recognition neural network structure that can be quickly executed at low computational cost. It can be achieved by effectively disseminating the identification probability information of the teacher network to the lightweight network. We call the probability information of the teacher network as soft-target, and FRD can learn more potential information from soft-target. In addition, we also used a special loss function for soft-target. Through the FRD network, while basically maintaining the recognition accuracy, we minimized the network structure. Extensive experiments on the two large-scale datasets, NTU-RGBD and Kinetics-Skeleton, demonstrate that our model (FRD) is more lightweight and refined than other models. Therefore, our model FRD is very practical. © 2022, The Authors. All rights reserved.

关键词： Distillation

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：