检索结果-内蒙古大学图书馆

2024 International Conference on Control, Robotics and Informatics, ICCRI 2024

作者： Cao, Duc Sang Ngo, Van Hien Le, Tran Thang Ngo, Van He Control Automation in Production and Improvement of Technology Institute Department of Electric Actuators & Automation Ha Noi Viet Nam Hanoi University of Science and Technology Department of Mechanical Engineering Ha Noi Viet Nam Control Automation in Production and Improvement of Technology Institute Department of Integrated System Ha Noi Viet Nam

ISBN: (纸本)9798350380309

Ocean engineering demands systemic solutions for mission-critical demands and technological challenges. From an industrial control perspective, development engineers need to factor in both costs and established standards to ensure the efficient implementation of the control system development lifecycle within a reasonable budget. Customization and reusability play key roles in driving down costs, resources, and development time when creating new applications. In the paper, the Unified Architecture Framework (UAF) [5], Model Based systems Engineering (MBSE), combined with real time Unified Modeling Language/systems Modeling Language (UML/SysML) are merged and tailored to produce an object-oriented (OO) control model. This model is then extensively applied to develop a controller for Autonomous Underwater Vehicles (AUVs). To reach this objective, the dynamic model of an Autonomous Underwater Vehicle (AUV) are linked with specific specializations of UAF/MBSE. In this setup, the model of analysis is precisely outlined through the detailed description of a use case model, aimed at closely capturing the intricate control demands. The designed model is then specialized by using the real-time UML/SysML to retain key blocks, which are used to describe in detail structures for control and behaviors of AUV. Next, the designed model is transformed into the model of implementation via round-trip engineering, facilitating the quick realization of an AUV controller. Building upon this object-oriented model, a controller for course-tracking applied to a miniature AUV was designed. The results from the simulation demonstrate the good feasibility of the proposed model. © 2024 IEEE.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Learning to Branch in Combinatorial Optimization With Graph Pointer Networks

引用

IEEE/CAA Journal of Automatica Sinica 2024年第1期11卷 157-169页

作者： Rui Wang Zhiming Zhou Kaiwen Li Tao Zhang Ling Wang Xin Xu Xiangke Liao IEEE the Xiangjiang Laboratory and the College of Systems Engineering National University of Defense TechnologyChangsha 410073China the Institute of Automation Chinese Academy of SciencesBeijing 100190China the College of Systems Engineering National University of Defense TechnologyChangsha 410073 the Hunan Key Laboratory of Multi-Energy System Intelligent Interconnection Technology Changsha 410073China the Department of Automation Tsinghua UniversityBeijing 100084China the College of Intelligence Science and Technology National University of Defense TechnologyChangsha 410073China the College of Computer Science and Technology National University of Defense TechnologyChangsha 410073China

Traditional expert-designed branching rules in branch-and-bound(B&B) are static, often failing to adapt to diverse and evolving problem instances. Crafting these rules is labor-intensive, and may not scale well with complex *** the frequent need to solve varied combinatorial optimization problems, leveraging statistical learning to auto-tune B&B algorithms for specific problem classes becomes attractive. This paper proposes a graph pointer network model to learn the branch rules. Graph features, global features and historical features are designated to represent the solver state. The graph neural network processes graph features, while the pointer mechanism assimilates the global and historical features to finally determine the variable on which to branch. The model is trained to imitate the expert strong branching rule by a tailored top-k Kullback-Leibler divergence loss function. Experiments on a series of benchmark problems demonstrate that the proposed approach significantly outperforms the widely used expert-designed branching rules. It also outperforms state-of-the-art machine-learning-based branch-and-bound methods in terms of solving speed and search tree size on all the test instances. In addition, the model can generalize to unseen instances and scale to larger instances.

关键词： Branch-and-bound(B&B) combinatorial optimization deep learning graph neural network imitation learning

来源：评论

学校读者我要写书评

暂无评论

Characteristic Optimization Based on Combined Statistical Indicators and Random Forest Theory

引用

CSEE Journal of Power and Energy systems 2024年第6期10卷 2657-2666页

作者： Qingzhen Liu Chao Cai Lei Wu Renwu Yan School of Electric Engineering and Automation Fuzhou UniversityFuzhou 350116China Quanzhou Electric Power Supply Company State Grid Fujian Electric Power CompanyQuanzhou 362000China Electrical and Computer Engineering Department Stevens Institute of TechnologyHobokenNJ07030USA Department of Power System Fujian University of TechnologyFuzhou 350116China

In order to effectively utilize the dielectric response characteristics of transformers to diagnose the insulation state,this paper proposes a two-level hybrid optimization method for analyzing time-domain dielectric response *** optimization algorithm is based on the combined statistical indicators(CSI)and random forest(RF)*** initial feature space set is formed with 23 time-domain *** the first-level stage,statistical indices correlation,distance,and information indicators are integrated to assess the synthesis score of the characteristics,while highly redundant and lowclass discrimination characteristics are eliminated from the initial space *** the second-level stage,the Random Forest based outside bagging data theory is introduced to evaluate the least important characteristics,and the characteristics with low importance indices are excluded to obtain the final optimal feature space *** proposed method is carried out on 82 sets of data from actual dielectric response tests on oil-paper insulation ***,the final optimal feature space set,along with several other data sets,is tested via different diagnosis *** results show that the optimal feature space set obtained via the proposed method outperforms other feature space sets in terms of better adaptability and diagnosis accuracy.

关键词： Feature space optimization integrated statistical indicators oil-paper insulation state random forest time domain characteristic two-level algorithm

来源：评论

学校读者我要写书评

暂无评论

Dynamic Event-Triggered Fixed-Time Consensus Analysis of Multi-Agent systems Under Input Delays and Switching Topologies 3

Dynamic Event-Triggered Fixed-Time Consensus Analysis of Mul...

引用

3rd IEEE Industrial Electronics Society Annual On-Line Conference, ONCON 2024

作者： Zhang, Yu Li, Yajing Ran, Guangtao Yu, Hao Ma, Guangfu Department of Automation Shenzhen518055 China Shanghai Institute of Aerospace System Engineering Shanghai200241 China Harbin Institute of Technology Department of Control Science and Engineering Harbin150001 China School of Automation Beijing Institute of Technology Beijing100081 China

ISBN: (纸本)9798331540319

This paper proposes a dynamic event-triggered control method for first-order multi-agent systems with input delays and disturbances under switching topologies. The controller design and its properties of dynamic event-triggered fixed-time consensus are presented in detail. Furthermore, agents can achieve consensus in a fixed time for any initial conditions and topologies that comply with the control protocol. Zeno behavior is avoided. Simulation examples demonstrate the effectiveness of the proposed algorithm and simulate scenarios in which the communication environment deteriorates due to external disturbances affecting the MASs. © 2024 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Solving Orienteering Problems by Hybridizing Evolutionary Algorithm and Deep Reinforcement Learning

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第11期5卷 5493-5508页

作者： Wang, Rui Liu, Wei Li, Kaiwen Zhang, Tao Wang, Ling Xu, Xin National University of Defense Technology College of System Engineering Changsha410073 China Xiangjiang Laboratory Changsha410205 China Hunan Key Laboratory of Multi-Energy System Intelligent Interconnection Technology HKL-MSI2T Changsha410073 China Tsinghua University Department of Automation Beijing100084 China National University of Defense Technology College of Intelligence Science and Technology Changsha410073 China

The orienteering problem (OP) is widely applied in real life. However, as the scale of real-world problem scenarios grows quickly, traditional exact, heuristics, and learning-based methods have difficulty balancing optimization accuracy and efficiency. This study proposes a problem decomposition-based double-layer optimization framework named DEA-DYPN to solve OPs. Using a diversity evolutionary algorithm (DEA) as the external optimizer and a dynamic pointer network (DYPN) as the inner optimizer, we significantly reduce the difficulty of solving large-scale OPs. Several targeted optimization operators are innovatively designed for stronger search ability, including a greedy population initialization heuristic, an elite strategy, a population restart mechanism, and a fitness-sharing selection strategy. Moreover, a dynamic embedding mechanism is introduced to DYPN to improve its characteristic learning ability. Extensive comparative experiments on OP instances with sizes from 20 to 500 are conducted for algorithmic performance validation. More experiments and analyses, including the significance test, stability analysis, complexity analysis, sensitivity analysis, and ablation experiments, are also conducted for comprehensive algorithmic evaluation. Experimental results show that our proposed DEA-DYPN ranks first according to the Friedman test and outperforms the competitor algorithms by 69%. © 2024 IEEE.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Knowledge-Guided Evolutionary Optimization for Large-Scale Air Defense Resource Allocation

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第12期5卷 6267-6279页

作者： Li, Wenhua Wang, Rui Heng, Yong Zhang, Tao Wang, Ling National University of Defense Technology College of Systems Engineering Changsha410073 China Hunan Key Laboratory of Multi-Energy System Intelligent Interconnection Technology Changsha410073 China Xiangjiang Laboratory Changsha410073 China Beijing Institute of Electronic System Engineering Beijing100854 China Tsinghua University Department of Automation Beijing100084 China

In the high-stakes domain of air defense, resource allocation is a challenging optimization problem that involves many constraints and requires fast solutions. Previous work mainly addressed the single-intercept sensor-weapon-target assignment problem, which assigns missiles and radars to targets without optimizing the launch time. However, this problem can become large-scale and difficult to solve when saturation attack tactics are employed. Therefore, we propose a more realistic model that allows multiple missiles to intercept the same target and considers the launch time as a decision variable. We also incorporate radar relay guidance to maximize the interception probability and minimize the missile cost. To solve this model efficiently, we present a novel evolutionary algorithm with linear population size reduction (LPSR) and knowledge-guided strategies, called LKEA. Specifically, we design a heuristic method to quickly find the optimal launch time for each missile and a knowledge-guided strategy to use the radar channel collision information to guide the evolution. Experimental results show that LKEA is competitive in solving small/medium/large air defense resource allocation problems (ADRAPs). © 2020 IEEE.

关键词： Combinatorial optimization

来源：评论

学校读者我要写书评

暂无评论

Online Optimization in Power systems With High Penetration of Renewable Generation:Advances and Prospects

引用

IEEE/CAA Journal of Automatica Sinica 2023年第4期10卷 839-858页

作者： Zhaojian Wang Wei Wei John Zhen Fu Pang Feng Liu Bo Yang Xinping Guan Shengwei Mei Key Laboratory of System Control and Information Processing Ministry of Education of ChinaDepartment of AutomationShanghai Jiao Tong UniversityShanghai 200240China State Key Laboratory of Power System and the Department of Electrical Engineering Tsinghua UniversityBeijing 100084China Institute of High Performance Computing(IHPC) Agency for Science Technology and Research(A*STAR)Singapore 138632Singapore

Traditionally,offline optimization of power systems is acceptable due to the largely predictable loads and reliable *** increasing penetration of fluctuating renewable generation and internet-of-things devices allowing for fine-grained controllability of loads have led to the diminishing applicability of offline optimization in the power systems domain,and have redirected attention to online optimization ***,online optimization is a broad topic that can be applied in and motivated by different settings,operated on different time scales,and built on different theoretical *** paper reviews the various types of online optimization techniques used in the power systems domain and aims to make clear the distinction between the most common techniques *** particular,we introduce and compare four distinct techniques used covering the breadth of online optimization techniques used in the power systems domain,i.e.,optimization-guided dynamic control,feedback optimization for single-period problems,Lyapunov-based optimization,and online convex optimization techniques for multi-period ***,we recommend some potential future directions for online optimization in the power systems domain.

关键词： optimization Lyapunov optimization online convex optimization online optimization optimization-guided control

来源：评论

学校读者我要写书评

暂无评论

Comparative study on the hydrogen storage performance of as-milled MgRENi rapid quenched alloy catalyzed by metal sulfides

引用

Journal of Magnesium and Alloys 2024年第5期12卷 2010-2023页

作者： Xiaoping Dong Zhaoqing Zhang Liying Yang Shenghai Xin Dandan Su Zhiyuan Li Department of Mechanical Design and Manufacture and Automation Hebei UniversityBaoding 071000PR China Baoding New Energy Vehicle Power Engineering Technology Research Center Hebei UniversityBaoding 071002PR China Hebei Technology Innovation Center for Lightweight of New Energy Vehicle Power System(Preparation) Hebei UniversityBaoding 071002PR China

The composites of Mg_(20)Pr_(1)Sm_(3)Y_(1)Ni_(10)as-quenched alloy and 3 wt.%M(M=CoS,CoS_(2),MoS_(2))catalyst were prepared by high-speed vibration ball *** effects of metal sulfides on the hydrogenation and dehydrogenation dynamics of alloys were *** results show that the as-milled composites contain a large number of amorphous embedded by a small amount of nanocrystals,and there are many point *** ball milling,the crystal grain size in the composites containing CoS is relatively larger,followed by CoS_(2)and MoS_(2)*** hydrogenation,the amorphous phase is crystallized to form Mg_(2)NiH_(4),YH_(3),Pr_(8)H_(18.96),Sm_(3)H_7,Mg,Co or Mo phases,however,Mg_(2)Ni,YH_(2),PrH_(2)and Ni_(3)Y phases appeared after *** maximum hydrogenation capacity of the composites containing CoS,CoS_(2)and MoS_(2)are 3.939,4.265 and 4.507 wt.%,*** hydrogenation saturation ratio of composite containing MoS_(2)is higher than that of the composites containing CoS and CoS_(2).The dehydrogenation activation energy of the composites containing CoS,CoS_(2)and MoS_(2)is 107.76,68.43 and 63.28 ***^(-1).H_(2).On the improvement of hydrogen storage performance of Mg_(20)Pr_(1)Sm_(3)Y_(1)Ni_(10)alloy,the catalytic effect of MoS_(2)sulfide is better than that of CoS_(2)sulfide,and which is better than CoS sulfide.

关键词： Mg_(20)Pr_(1)Sm_(3)Y_(1)Ni_(10)as-quenched alloy CoS CoS_(2)and MoS_(2)sulfide Milling Activation energy Hydrogen storage dynamics

来源：评论

学校读者我要写书评

暂无评论

Cataract Surgical Instruments Segmentation Free of Motion Blur Influence 24

Cataract Surgical Instruments Segmentation Free of Motion Bl...

引用

13th International Conference on Bioinformatics and Biomedical Science, ICBBS 2024

作者： Sun, Xuebin Wang, Jinxi Yang, Xiaofei School of Electrical Automation and Information Engineering Tianjin University Tianjin China Department of Aerospace Laser Technology and System Shanghai Institute of Optics and Fine Mechanics Shanghai China

ISBN: (纸本)9798400717956

Most of the existing cataract surgical instrument segmentation algorithms fail to consider the motion blur caused by the surgeon's hand movement or defocused camera. Most prior deblurring methods are oriented to visual tasks to merely recover the structure information from motion-blurred images. However, during surgical instrument segmentation, it is important to obtain the exact location of the surgical instruments at the current time to pave the way for subsequent downstream tasks, such as tracking and position estimation. In this work, we propose a spatiotemporal (ST) information-based network, consisting of the deblurring module and a subsequent segmentation module, for cataract surgical instrument segmentation free of motion blur influence to address the missing gap in the existing literature. The ST recurrent network with a series of ST-LSTM and gradient highway units removes the motion blur, which then enables for accurate semantic segmentation. The ST network model subsequently captures the temporal and spatial correlation for semantic segmentation. Experimental results quantitatively and qualitatively demonstrate that our method outperforms the state-of-the-art on our self-constructed dataset and the CaDIS benchmark dataset. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

A joint sparse Bayesian learning for wideband DOA estimation

A joint sparse Bayesian learning for wideband DOA estimation

引用

2024 Conference on Spectral technology and Applications, CSTA 2024

作者： Zhao, Yonghong Liu, Jisong Wang, Junlong Dong, Shuxin Shannxi Key Laboratory of Complex System Control and Intelligent Information Processing Department of Automation and Information Engineering Xi'an University of Technology Shaanxi Xi'an710048 China

ISBN: (纸本)9781510683082

Wideband direction of arrival (DOA) estimation using sensor array is a noteworthy problem frequently occurring in many applications involving radar, sonar, and communication. We present a wideband DOA method based on a sparse Bayesian learning of multiple sub-bands jointly with the redundant dictionary matrix at the reference frequency. Explicitly enforcing the focusing operation and the singular value decomposition (SVD) to sensor measurements is motivated by a desire to decrease the computational complexity and storage capacity. A joint sparse Bayesian learning framework is proposed to deal with multiple sub-bands under one segment to obtain the DOA information. Moreover, the proposed method can be directly extended to multiple segments. Comparing to other wideband DOA estimation methods, the proposed method has the advantages of increased resolution, higher accuracy, and correlation of the sources, as well as not requiring the initial angles for the focusing matrix. Simulations are provided to show the effectiveness and improved performance of the proposed method. © 2024 SPIE.

关键词： Direction of arrival

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：