检索结果-内蒙古大学图书馆

international conference on Autonomous Unmanned systems (ICAUS)

作者： Li, Xinpeng Wang, Yue Yin, Hao Zhuang, Xing Li, Xiang Beijing Inst Technol Sch Mechatron Engn Beijing 100081 Peoples R China

ISBN: (纸本)9789819904815;9789819904792;9789819904785

UAV cluster plays an important role in large-scale complex task, there are still many challenges like the planning and control quantities cannot be properly matched when facing the exploration of large-scale unknown environment with possible obstacles. This paper proposes an adaptive guidance distributed model predictive control (AG-DMPC) exploration method for unknown complex environment of UAV cluster. The control quantity of UAV is directly planned to avoid the conflict between planning quantity and control quantity in traditional methods. The initial solution is generated based on dynamic constraints, and the rolling optimization solution is carried out through the symbiotic biological search algorithm. The evaluation function is constructed by comprehensively considering the growth of exploration rate, cluster collision avoidance and obstacle avoidance, and the adaptive clustering guidance method is introduced to escape local maximum exploration in trap the search process, so as to realize faster exploration of the environment under the condition of ensuring safety constraints. The simulation results show that this method can effectively avoid collision problems, reduce explore lost and escape local traps to improve exploration efficiency.

关键词： Unknown environment exploration UAV cluster Distributed model predictive control

来源：评论

学校读者我要写书评

暂无评论

Methodology of Social Development Research 4

Methodology of Social Development Research

引用

4th international conference on control systems, Mathematical modeling, Automation and Energy Efficiency, SUMMA 2022

作者： Kononov, Dmitry Russian State University for the Humanities Institute of Control Sciences of Ras Moscow Russia

ISBN: (数字)9781665456593

ISBN: (纸本)9781665456593

A system of research directions for the development of a methodology for managing social development at various levels of social stratification is proposed. The study of the relationship between the types of human activity and the development of Society is supposed to be developed based on the basic principles, concepts and provisions of the Marxist theory of the alienation of labor in its most modern form. The application of the principle of interdisciplinary analysis allows us to consider the problem from different points of view and apply research methods of a range of related scientific disciplines: natural, technical, humanitarian. A list of scientific directions and tasks is proposed, which, apparently, should be paid special attention to by scientists of the specified complex of scientific disciplines. The role of cybernetics in solving the tasks is considered. The stratification of Society by levels of types of activity is proposed. The conditions under which it is advisable to use mathematical models, methods and modern tools of control theory and cybernetics (scientific and technological progress, informatization and digitalization), in particular, the methodology of scenario research of complex systems developed at the Institute of Management problems of the Russian Academy of Sciences (methodology 3K), are indicated. The purpose of the research is to create the foundations of a social design system. © 2022 IEEE.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

Regional Intelligent Traffic Signal control System Based on Multi-agent Deep Reinforcement Learning 8

Regional Intelligent Traffic Signal Control System Based on ...

引用

8th international conference on Computer and Communication systems, ICCCS 2023

作者： Zheng, Peng Chen, Yanhao Kumar, Burra Venkata Durga School of Computing & Data Science Xiamen University Malaysia Selangor Sepang Malaysia

ISBN: (纸本)9781665456128

Urban traffic congestion is becoming a severe problem. A reinforcement learning-based intelligent traffic signal control system can alleviate traffic congestion problems. However, when reinforcement learning faces complex multi-agent decision problems, it is difficult for single-agent reinforcement learning algorithms to realize the complex relationships among multiple agents. Therefore, integrating reinforcement learning with multi-agent techniques in multiple ways is becoming inevitable. Based on reinforcement learning, multi-agents obtain optimal regional strategies through continuous interaction and improvement. This paper proposes a new approach to regional intelligent traffic signal control combining multi-agent techniques and deep reinforcement learning. The method effectively reduces the average trip waiting time (ATWT) and the total waiting queue length (TWQL) of vehicles in the region while performing better on the reward function compared to the deep Q network (DQN) algorithm. This approach improves traffic efficiency and increases resource utilization efficiency while reducing congestion time, road utilization, and resource waste. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Chinese Nested Entity Recognition Benchmark in the Field of Naval Warfare

Chinese Nested Entity Recognition Benchmark in the Field of ...

引用

2024 IEEE international conference on Unmanned systems, ICUS 2024

作者： Zhang, Shengjie Li, Qi Kou, Yueping Wang, Jun Li, Zhengwei Wu, Baolei School of Computer Science and Technology China University of Mining and Technology Xuzhou China School of Information and Control Engineering China University of Mining and Technology Xuzhou China

ISBN: (纸本)9798350384185

Named entity recognition (NER) is a fundamental task in natural language processing and a key technology for building knowledge graphs. However, the performance of NER is often limited by domain-specific characteristics. For unpopular Chinese entity recognition fields, such as naval warfare, NER typically performs poorly due to the lack of sufficient pre-trained models and labeled data. Furthermore, the naval warfare field includes numerous specialized terms and complex domain knowledge, with nested structures and physical relationships that are uncommon in conventional corpora, posing additional challenges for NER. To address these issues, we manually construct a high-quality naval warfare domain corpus. We also propose a new nested entity recognition framework, which fully leverages entity boundary information, enhances the learning of entity adjacency modeling information, and uses multi-scale convolution to obtain richer span feature representation. Experiments demonstrate the effectiveness of this method in four Chinese NER corpora. © 2024 IEEE.

关键词： Naval warfare

来源：评论

学校读者我要写书评

暂无评论

Dynamics Analysis of the Cooperative Dual Marine Lifting systems Subject to Sea Wave Disturbances

Dynamics Analysis of the Cooperative Dual Marine Lifting Sys...

引用

international conference on Applied Nonlinear Dynamics, Vibration, and control, ICANDVC 2023

作者： Li, Gang Ma, Xin Li, Yibin Center for Robotics School of Control Science and Engineering Shandong University Jinan250061 China

ISBN: (纸本)9789819705535

Strong coupling and complex nonlinearities increase the difficult of the dynamic modeling of the cooperative dual marine lifting system (DMLS). Moreover, it is a great challenge for DMLS model analysis while considering complex sea wave disturbances. To solve these issues, this paper establishes an accurate model of the DMLS by Lagrangian method without any simplifications. The dynamic relationship among the dual horizontal mechanism displacement, the dual lifting boom heights and the payload attitudes is analyzed accurately. The dynamic model considers ship rolling, heave and sway motion induced to sea wave disturbances. Finally, the simulation results are verified the effectiveness of the proposed dynamic model. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Dynamic models

来源：评论

学校读者我要写书评

暂无评论

Building a cloud-based digital twin for remote monitoring and control of a robotic assembly system

引用

international JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY 2023年第9-10期129卷 4045-4057页

作者： Bin Touhid, Md Tahmid Marne, Mrunal Oskroba, Theodore Mirahmadi, Sayed Amirhossein Zhu, Enshen Mehrabian, Alireza Defersha, Fantahun Yang, Sheng Univ Guelph Sch Engn Guelph ON Canada Aleo Canada Inc Montreal PQ H3C 2M7 Canada

The potential of digital twin (DT) technology to revolutionize industry by enabling virtual simulations of physical systems in real-time has garnered significant attention in recent years. DTs have been widely applied in the manufacturing field to solve various problems, such as shopfloor resource optimization, layout design, commissioning, monitoring, and supervisory control. Cloud-based DT (CBDT) is an emerging concept and shows promise in achieving enhanced remote accessibility, data processing and analysis capabilities, and scalability. However, current CBDT research is still very limited and mainly focuses on theoretical framework that leverages cloud computing advantages in data processing aspects. Yet, practical implementation with technical details for creating a CBDT of a complex manufacturing system is rarely reported, and the interactions between cloud infrastructure and DT modeling and visualization are scarcely investigated. To fill the gaps, this paper first proposes a general CBDT framework for supporting smart manufacturing services. This framework features the integration of modularized cloud intelligence, DT modeling, and DT visualization to achieve enhanced remote accessibility. Moreover, a prototyping system that entails the CBDT-enabled remote monitoring and control services is implemented for a legacy robotic assembly system to partially showcase the process of the proposed framework. The usefulness and remote accessibility of the developed CBDT-based prototype system is further demonstrated with web-based functionalities such as assembly job status update, real-time 3-dimensional DT visualization and simulation of assembly tasks, and remote feedback control over the physical system. Lastly, the prototype system is built upon open-source toolkits (e.g., WebGL) and low-cost commercial software platforms (e.g., Unity and Google Cloud Platform), which could potentially open new opportunities for aiding small-to-medium companies for digital transfo

关键词： Digital twin Cyber-physical system Cloud-based infrastructure Smart manufacturing Remote monitoring and control Robotic assembly system

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Wire Grid Scatterers with Different Cells Using MoM and Pulse Basis Functions

Comparative Analysis of Wire Grid Scatterers with Different ...

引用

2024 international conference on Engineering Management of Communication and Technology, EMCTECH 2024

作者： Dang, Tuan Phuong Alhaj Hasan, Adnan F. Gazizov, Talgat R. Tomsk State University of Control Systems and Radioelectronics Department of Television and Control Tomsk Russia

ISBN: (纸本)9798331507909

modeling scattering structures of various shapes using the method of moments (MoM) with wire grid (WG) models remains crucial in contemporary research. Although many publications focus on WG models constructed with square cells, there are also alternative cell shapes available. Until now, however, there has been a lack of comprehensive performance comparisons across these different cell types especially using MoM with pulse basis functions (PBF). This work addresses this gap by simulating flat plate scatterers using MoM with PBF with various WG cell shapes, including square, rhombus, right triangle, hexagonal, and triangular RWG cells. The results demonstrated that cells with simpler geometries, such as squares and rhombuses, provide higher accuracy, whereas cells with more complex shapes tend to yield lower accuracy. © 2024 IEEE.

关键词： Radar cross section

来源：评论

学校读者我要写书评

暂无评论

Optimization geometric design in intelligent systems for ensuring safety 12

Optimization geometric design in intelligent systems for ens...

引用

12th international Scientific and Practical conference "Information control systems and Technologies", ICST 2024

作者： Chuhai, Andrii Yaskov, Georgiy Starkova, Olha Anatolii Pidhornyi Institute of Mechanical Engineering Problems The National Academy of Sciences of Ukraine Pozharsky St. 2/10 Kharkiv61129 Ukraine Simon Kuznets Kharkiv National University of Economics Nauky Ave 9A Kharkiv61166 Ukraine Kharkiv National University of Radio Electronics Nauky Ave. 14 Kharkiv61166 Ukraine

Packing optimization problems have a wide spectrum of real-word applications. In today's technologically advanced world, the need for safety systems is ubiquitous and paramount. From industrial processes to everyday applications, safety systems play a crucial role in ensuring the smooth and secure operation of various systems. One such critical application is the safe storage of spent nuclear fuel (SNF), a significant scientific problem in the present day. The solution of the problem can be reduced to the solution of the problem of finding the optimal placement of a given set of congruent circles into a multiconnected domain taking into account technological restrictions. A mathematical model of the problem is constructed and its peculiarities are considered. Our approach is based on the mathematical modelling of relations between geometric objects by means of phi-function technique. That allowed us to reduce the problem solving to nonlinear programming. © 2024 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 international (CC BY 4.0).

关键词： Intelligent systems for ensuring safety mathematical modeling non-linear programing optimization packing problem phi-function

来源：评论

学校读者我要写书评

暂无评论

Research on 3D Printing control System

Research on 3D Printing Control System

引用

2023 international conference on Intelligent systems, Communications, and Computer Networks, ISCCN 2023

作者： Song, Xinhao Wang, Xiaobo Zhang, Ying Department of Mechanical Engineering Xijing University Shaanxi Xi'an China Department of Robot Engineering Xijing University Shaanxi Xi'an China

ISBN: (纸本)9781510666238

As an emerging manufacturing technology, 3D printing has the characteristics of forming complex structures, mass customization and rapid prototyping. It is widely used in biomedical, aerospace, construction, and other fields. problems such as poor printing effect, wire drawing, and nozzle blockage in the process of 3D printing are often closely related to its control system. Therefore, the 3D printing system should have an excellent motion control system and temperature control system, which is of great significance for improving the quality of 3D printing. This paper mainly summarizes the types, methods, and characteristics of motion control and temperature control in the control mode of existing 3D printing equipment and prospects for the optimization of the control scheme in the control system. © 2023 SPIE.

关键词： control systems

来源：评论

学校读者我要写书评

暂无评论

Model-Free Predictive Current control for Induction Motor Drive Using Recursive Least Squares Algorithm 2

Model-Free Predictive Current Control for Induction Motor Dr...

引用

2nd international conference on Power, Electrical, Electronics and Industrial Applications, PEEIACON 2024

作者： Hossen, Md. Belal Habibullah, Md. Rafiq, Md. Abdur Khulna University of Engineering & Technology Dept. of Electrical and Electronic Engineering Khulna9203 Bangladesh

ISBN: (纸本)9798331517984

A conventional model predictive current control (MPCC) scheme for an induction motor (IM) drive performs as an effective controller at dynamic and steady-state conditions. However, the performance of this control scheme is highly dependent on the mismatch in the motor parameters. In addition, the modeling knowledge of the IM and its accurate parameters measurement are required in the controller. In this paper, a new model-free PCC (MF-PCC) scheme has been proposed to overcome the aforementioned problems. The proposed scheme uses an auto-regressive exogenous (ARX) model instead of the motor model to form a model-free controller. The ARX model works only on the motor's input-output transfer function. The unknown coefficients or parameters in the ARX model are estimated by using a recursive least squares algorithm. To obtain an accurate prediction, an ARX structure has been modified into an observable canonical state-space model. Simulation results show that the proposed control scheme is robust against motor parameters mismatch under different operating conditions in comparison with the conventional MPCC scheme. © 2024 IEEE.

关键词： Predictive control 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：