检索结果-内蒙古大学图书馆

第41届中国控制会议

作者： Fuchun Liu Bin Li Haixing Deng Ming Zeng School of Automation Science and Engineering South China University of Technology Key Laboratory of Autonomous Systems and Networked ControlMinistry of Education Unmanned Aerial Vehicle Systems Engineering Technology Research Center of Guangdong

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

The Ultrasonic scalpel has good medical characteristics and is widely used in the medical *** the core component of the ultrasonic scalpel system,the ultrasonic transducer usually needs to control its power for good cutting ***,the mathematical model of the ultrasonic transducer is complex and easily influenced by the load and ***,it is challenging to design a power controller that satisfies all situations with different temperatures and *** this paper,we will analyze the equivalent model of the ultrasonic transducer and simplify the controlled object ***,an ADRC controller,which has the advantage of placing less emphasis on the mathematical model and compensating for the disturbances,will be ***,the performance of the ADRC control system will be tested according to a simulation experiment.

关键词： ultrasonic transducer power control ADRC first-order system

来源：评论

学校读者我要写书评

暂无评论

Coordinated control of Deformation and Flight for Morphing Aircraft via Meta-Learning and Coupled State-Dependent Riccati Equations

arXiv

引用

arXiv 2025年

作者： Che, Hao-Chi Wu, Huai-Ning School of Automation Science and Electrical Engineering Beihang University Beijing China The Science and Technology on Aircraft Control Laboratory School of Automation Science and Electrical Engineering Beihang University Beijing100191 China The Hangzhou International Innovation Institute Beihang University Hangzhou311115 China

In this paper, the coordinated control problem of deformation and flight for morphing aircraft (MA) is studied by using meta-learning (ML) and coupled state-dependent Riccati equations (CSDREs). Our method is built on two principal observations that dynamic models of MA under varying morphing conditions share a morphing condition independent representation function and that the specific morphing condition part lies in a set of linear coefficients. To that end, the domain adversarially invariant meta-learning (DAIML) is employed to learn the shared representation with offline flight data. Based on the learned representation function, the coordinated control of the deformation and flight for MA is formulated as a non-cooperative differential game. The state-dependent feedback control solutions can be derived by addressing a pair of CSDREs. For this purpose, Lyapunov iterations are extended to obtain the positive semidefinite (definite) stabilizing solutions of the CSDREs, and the convergence proof of the proposed algorithm is provided. Finally, a simulation study is carried out to validate the efficacy of the developed coordinated game control strategies. Copyright © 2025, The Authors. All rights reserved.

关键词： Riccati equations

来源：评论

学校读者我要写书评

暂无评论

Effect of center-offset arc pole shoe shapes on torque ripple and eddy-current loss of consequent pole rotor

Effect of center-offset arc pole shoe shapes on torque rippl...

引用

CSAA/IET International Conference on Aircraft Utility Systems (AUS 2024)

作者： Haien Li Liang Yan Xiaoshuai Liu Pengjie Xiang Xinghua He Nannan Du Yang Xuxu School of Automation Science and Electrical Engineering Science and Technology on Aircraft Control Laboratory Beihang University Beijing People's Republic of China

ISBN: (数字)9781837242108

Traditional consequent pole motor has the advantages of less magnetic costs, small magnetic resistance and strong inductance. It is widely studied in the design of the electrical propulsion system. However, it has the problem of uneven distribution of air gap magnetic flux density. It is locally distributed by square waves, causing the high-level harmonic problem, increasing the torque pulse and vortex loss of the motor. This paper show the design principles of the center-offset arc pole. And the limited element simulation of the motor of different eccentric spacing. The results show that compared with the consequent pole, increasing the center-offset distance can reduce the torque ripple and vortex loss.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Ground-to-Air Force Deployment Based on Multi-Objective Evolutionary Algorithm with Game Mechanism 2

Research on Ground-to-Air Force Deployment Based on Multi-Ob...

引用

2nd International Conference on Artificial Intelligence and automation control, AIAC 2024

作者： Gong, Hua Fu, Yanke Zhang, Yong Xu, Ke School of Science Shenyang Ligong University Shenyang110159 China Liaoning Key Laboratory of Intelligent Optimization and Control for Ordnance Industry Shenyang110159 China School of Automation and Electrical Engineering Shenyang Ligong University Shenyang110159 China National Key Laboratory of Electromagnetic Space Security China

ISBN: (纸本)9798331529147

In order to achieve effective protection of assets within defensive bases in a complex air combat environment, this article explores the issue of troop deployment with the coordination of multiple types of weapons. Considering the atmospheric transmission characteristics of laser weapons and the electromagnetic interference characteristics of missiles, a multi-objective optimization model has been established to collaboratively optimize the importance of protection, the success rate of protection, and the cost of weapons. To address this model, we propose a multi-objective evolutionary algorithm (MOEA) improved by a competitive-cooperative two-stage game mechanism (GM-MOEA). By introducing multiple individual evaluation metrics, the algorithm enhances the convergence speed of the objective function and the quality of solutions while balancing the diversity and convergence of the population and improving the uniformity and coverage of the Pareto front. © 2024 IEEE.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Lightweight Deep Driver Distraction Recognition Network

Lightweight Deep Driver Distraction Recognition Network

引用

IEEE International Conference on Information Communication and Signal Processing (ICICSP)

作者： Yutian Wu Yaqi Yin Jiaying Wu Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing China School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing China School of Electrical and Control Engineering North China University of Technology Beijing China

ISBN: (数字)9798350355895

ISBN: (纸本)9798350355901

When the driver shifts his attention away from the driving task and performs behaviors unrelated to driving, it is very easy to slow down the driver's perception ability and cause decision delays. Therefore, timely and accurate identification of driver distraction and issuing of alerts can help improve driving safety. Due to the diverse representations of driver distraction behaviors, it is difficult to collect an dataset which contains all kinds of driver distraction actions to train deep neural networks. This paper proposed an attention-based deep driver distraction recognition neural network DDDNet, which is trained by contrastive learning method to learn to judge complex driving distraction behaviors. Besides, in order to meet the requirement of high processing speed and recognition accuracy, on the basis of the lightweight feature extraction network MobileNetV2, DDDNet proposed to add a three-dimensional channel attention module to strengthen the effective feature. Experimental results show the DDDNet is able to identify a variety of distracting behaviors which it has not met before, with high recognition accuracy of 87.12% and real-time processing speed of 140fps.

关键词： Accuracy Image recognition Contrastive learning Streaming media Signal processing Feature extraction Vectors Real-time systems Safety Driver behavior

来源：评论

学校读者我要写书评

暂无评论

Distributed estimation-based output consensus control of heterogeneous leader-follower systems with antagonistic interactions

引用

science China(Information sciences) 2023年第3期66卷 305-306页

作者： Yanzhi WU Qingpeng LIANG Yiyi ZHAO Jiangping HU Linying XIANG School of Electrical Engineering Southwest Jiaotong University School of Information Science and Technology Southwest Jiaotong University School of Business Administration Southwestern University of Finance and Economics School of Automation Engineering University of Electronic Science and Technology of China School of Control Engineering Northeastern University at Qinhuangdao

Dear editor, This study addresses an output bipartite consensus problem for leader-follower heterogeneous multi-agent systems,and thus further generalizes the results in [1, 2]. The main contributions include three aspects.(i) Novel distributed estimation schemes are introduced to estimate the unavailable information of the leader.(ii) Owing to the unknown system matrix of the leader,

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dense Small Object Tracking via DeepSort Integrated with YOLOv.X-based Detection

Dense Small Object Tracking via DeepSort Integrated with YOL...

引用

International Conference on control, automation and Information sciences (ICCAIS)

作者： Mengfan Zhang Weifeng Liu Xingyu Xia School of Electrical and Control Engineering Shaanxi University of Science and Technology Xi'an China School of Automation Hangzhou Dianzi University Hangzhou China

ISBN: (数字)9798331542047

ISBN: (纸本)9798331542054

In order to address the problem of incomplete feature extraction, missed tracking, and incorrect tracking in dense small object tracking tasks, This paper proposes a DeepSort method based on YOLOv.X for input detection. This method uses YOLOv5 as the detection input for DeepSort to obtain more complete detection box information for dense small objects; Then, the feature extraction and fusion parts in YOLOv5 are reused to replace the appearance feature extraction network in DeepSort, improving the algorithm's performance in extracting features from dense small objects; On this basis, the CIoU algorithm is used as a measure of the correlation between unmatched detection boxes and unmatched prediction boxes during the tracking process to avoid unnecessary trajectory loss. The experimental results show that compared with the original DeepSort tracking algorithm, the improved algorithm improved the MOTA index by 3.6%, the MOTP index by 2.9%, and reduced the error ID conversion index by 269 times.

关键词： YOLO Correlation automation Feature extraction Prediction algorithms Loss measurement Trajectory Indexes Object tracking Data mining

来源：评论

学校读者我要写书评

暂无评论

Doppler Measurement-Based Positioning and Tracking Methods with External Radiation Radar

Doppler Measurement-Based Positioning and Tracking Methods w...

引用

Signal, Information and Data Processing (ICSIDP), IEEE International Conference on

作者： Weifeng Liu Linqing He Zhengwang Tian School of Electrical and Control Engineering Shaanxi University of Science and Technology Xi’an China School of Automation Hangzhou Dianzi University Hangzhou China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

This paper introduces a new approach for addressing the complex problem of Multi-target tracking in external radiation radar systems equipped with Multi-static Doppler measurements. Drawing from research on sensor arrays and mobile sensors, the method utilizes the Generalized Labelled Multi-Bernoulli (GLMB) filter to navigate the intricacies of Multi-target tracking across sensor arrays. The study validates the effectiveness of the GLMB and the computationally efficient Gibbs-GLMB filters in a setup involving three transmitters and one receiver. Experimental results, assessed with the Optimal Sub-Pattern Assignment (OSPA) metric, suggest that the Gibbs-GLMB filter accelerates computation while potentially compromising on measurement precision, which could lead to reduced accuracy in specific cases. The investigation also examines the influence of sensor geometry on tracking results, indicating that there is an association between tracking performance and sensor arrangement.

关键词： Accuracy Target tracking Radar measurements Transmitters Receivers Radar tracking Time measurement Doppler radar Doppler effect Sensor arrays

来源：评论

学校读者我要写书评

暂无评论

Event-Triggered Energy Optimization of Wireless Sensor Networks 19

Event-Triggered Energy Optimization of Wireless Sensor Netwo...

引用

19th IEEE International Conference on Networking, Sensing and control, ICNSC 2022

作者： Liu, Lu Song, Ruizhuo Wei, Qinglai School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing China Institute of Automation Chinese Academy of Sciences The State Key Laboratory of Management and Control for Complex Systems Beijing China

ISBN: (纸本)9781665472432

Aiming at limited communication and energy re-sources in wireless sensor networks (WSN s), this paper proposes an energy management scheme of WSNs via adaptive dynamic programming (ADP) based on event-triggered mecha-nism (ETM). The optimal control strategy obtained by iteration can schedule the sensor nodes and make the nodes switch between working and sleeping situations, thus improving the energy utilization and extending the service life of the energy-constrained WSNs. Firstly, the mathematical model of WSNs is established, and the state is estimated by extended Kalman filter (EKF) algorithm to improve the measurement accuracy. Then, ADP solves the designed value function to achieve the scheduling plan. On the premise of system stability, ETM is applied to activate the controller on demand, which can reduce communication burden and save WSNs energy consumption. Finally, the simulation experiment reveals that the proposed algorithm can reduce the unnecessary triggering times of the controller effectively while ensuring the requirements, and avoid data congestion and interaction resource waste. © 2022 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

The Study of RWENN for Proton Exchange Membrane Fuel Cell System in Microgrid 2

The Study of RWENN for Proton Exchange Membrane Fuel Cell Sy...

引用

2nd International Symposium on Electrical, Electronics and Information engineering, ISEEIE 2022

作者： Lu, Kai-Hung Yiping, Deng Zhimin, Li Ziyu, Xu Yunhao, Chen Junfang, Lian Xia, Yang School of Electronic and Electrical Engineering Minnan University of Science and Technology Fujian Key Laboratory of Industrial Automation Control Technology and Information Processing Fujian Quanzhou China School of Electrical and Automation Engineering East China Jiaotong University Jiangxi Nanchang China

ISBN: (数字)9781665468749

ISBN: (纸本)9781665468749

Fuel cells are an effective use of clean energy. It has strong controllability, low operating noise and low heat radiation. This is one of the important development directions for future service-oriented computing and power supply. Them, proton exchange membrane fuel cell (PEMFC) has become a research hotspot in this field because of its high power, low operating temperature, fast start-up and long life. This paper studies the PEMFC power generation system in microgrid by Recurrent Wavelet-based Elman neural network (RWENN). The PEMFC power system is integrated into the distribution network by AC/DC. The microgrid is designed from the hierarchical structure of the fuel cell microgrid system. The effectiveness of the RWENN control strategy is verified by modeling and simulation analysis in this paper. © 2022 IEEE.

关键词： Protons Analytical models Power supplies Heuristic algorithms Power system dynamics Neural networks Fuel cells

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：