检索结果-内蒙古大学图书馆

Group Hybrid Coordination control of Multi-Agent systems With Time-Delays and Additive Noises

IEEE/CAA Journal of Automatica Sinica 2023年第3期10卷 737-748页

作者： Chuanjian Li Xiaofeng Zong School of Automation China University of GeosciencesWuhan 430074 Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan 430074 the Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of EducationWuhan 430074China IEEE

A new kind of group coordination control problemgroup hybrid coordination control is investigated in this *** group hybrid coordination control means that in a whole multi-agent system(MAS)that consists of two subgroups with communications between them,agents in the two subgroups achieve consensus and containment,*** MASs with both time-delays and additive noises,two group control protocols are proposed to solve this problem for the containment-oriented case and consensus-oriented case,*** developing a new analysis idea,some sufficient conditions and necessary conditions related to the communication intensity betw een the two subgroups are obtained for the following two types of group hybrid coordination behavior:1)Agents in one subgroup and in another subgroup achieve weak consensus and containment,respectively;2)Agents in one subgroup and in another subgroup achieve strong consensus and containment,*** is revealed that the decay of the communication impact betw een the two subgroups is necessary for the consensus-oriented ***,the validity of the group control results is verified by several simulation examples.

关键词： Additive noises consensus control containment control group hybrid coordination control multi-agent systems(MASs) time-delays

来源：评论

学校读者我要写书评

暂无评论

A hybrid wind power prediction model based on seasonal feature decomposition and enhanced feature extraction

引用

Energy and AI 2024年第4期18卷 368-379页

作者： Weipeng Li Yuting Chong Xin Guo Jun Liu School of Automation and Information Engineering Xi’an University of TechnologyNo.5 Jinhua South RoadXi’an710048ShaanxiChina Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing No.5 Jinhua South RoadXi’an710048ShaanxiChina

Efficient and accurate wind power prediction is crucial for enhancing the reliability and safety of power *** data-driven forecasting methods are regarded as an effective ***,the inherent randomness and nonlinearity of wind power systems,along with the abundance of redundant information in measurement data,present challenges to forecasting *** integration of precise and efficient techniques for data feature decomposition and extraction is essential in conjunction with advanced driven data-forecasting *** on the seasonal variation characteristics of wind energy,a hybrid wind power prediction model based on seasonal feature decomposition and enhanced feature extraction is *** effectiveness and superiority of the proposed method in predictive accuracy are demonstrated through comprehensive multi-model experiment comparisons.

关键词： Wind power prediction Data-driven Hybrid model Seasonal feature decomposition Gated recurrent networks Attention mechanism

来源：评论

学校读者我要写书评

暂无评论

A probe into the acid deposition mitigation path in China over the last four decades and beyond

引用

National Science Review 2024年第4期11卷 84-92页

作者： Qian Yu Xiaodong Ge Haotian Zheng Jia Xing Lei Duan Dongwei Lv Dian Ding Zhaoxin Dong Yisheng Sun Posch Maximilian Danni Xie Yu Zhao Bin Zhao Shuxiao Wang Jan Mulder Thorj?rn Larssen Jiming Hao State Key Laboratory of Environmental Simulation and Pollution Control School of EnvironmentTsinghua University State Key Laboratory of Pollution Control &Resource Reuse and School of the Environment Nanjing University State Environmental Protection Key Laboratory of Sources and Control of Air Pollution Complex School of EnvironmentTsinghua University International Institute for Applied System Analysis(IIASA) School of Land Engineering Chang'an University Faculty of Environmental Sciences and Natural Resource Management Norwegian University of Life Sciences Norwegian Institute for Water Research

China currently has the highest acid deposition globally, yet research on its status, impacts, causes and controls is lacking. Here, we compiled data and calculated critical loads regarding acid deposition. The results showed that the abatement measures in China have achieved a sharp decline in the emissions of acidifying pollutants and a continuous recovery of precipitation p H, despite the drastic growth in the economy and energy consumption. However, the risk of ecological acidification and eutrophication showed no significant decrease. With similar emission reductions, the decline in areas at risk of acidification in China(7.0%) lags behind those in Europe(20%) or the USA(15%). This was because, unlike Europe and the USA, China's abatement strategies primarily target air quality improvement rather than mitigating ecological impacts. Given that the area with the risk of eutrophication induced by nitrogen deposition remained at 13%of the country even under the scenario of achieving the dual targets of air quality and carbon dioxide mitigation in 2035, we explored an enhanced ammonia abatement pathway. With a further 27% reduction in ammonia by 2035, China could largely eliminate the impacts of acid deposition. This research serves as a valuable reference for China's future acid deposition control and for other nations facing similar challenges.

关键词： acid deposition critical loads acidification eutrophication ammonia abatement

来源：评论

学校读者我要写书评

暂无评论

Dehazing Network Based on U-Net Structure and Residual Block 41

Dehazing Network Based on U-Net Structure and Residual Block

引用

第41届中国控制会议

作者： Wenbo Zhang Haoze Li Han Sun Yongqiang Bai School of Automation Beijing Institute of Technology Key Laboratory of Complex System Intelligent Control and Decision Beijing Institute of Technology

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

With the development of deep learning technology,the dehazing method based on convolutional neural network has also developed ***,it still faces some problems such as incomplete dehazing and difficulty in detail *** at the problems,we propose a dehazing network based on U-Net structure and residual *** the down sampling process,we introduce the residual block of attention mechanism,which effectively improves the feature extraction and expression ability of the *** the middle part of the network,the smooth dilation convolution residual block is used to expand the receptive field of the network and improve the restoration effect of small *** the same time,we introduce a feature fusion mechanism based on attention mechanism,which can reduce the loss of information and weight the down-sampling features into intermediate *** the process of up sampling,the method of adding elements instead of feature stitching is used to reduce the number of parameters and realize the function of jump ***,dense convolution residual blocks are added to the jump connection between input and output to further improve the *** experimental results show that the PSNR of this method can reach 32.893,which is better than the existing methods.

关键词： Image Dehazing Residual Network Attention mechanism

来源：评论

学校读者我要写书评

暂无评论

BeltLineNet: A Shape-Prior-Guided Lightweight Network for Real-Time Deviation Detection in Circular Pipe Conveyors

引用

IEEE Sensors Journal 2025年第11期25卷 20024-20036页

作者： Zhao, Long Su, Jinhui Zhong, Yusheng Xie, Weiwei Su, Jinya Chen, Xisong Chen, Congyan Li, Shihua Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education School of Automation Nanjing210096 China Fujian Longking Intelligent Conveying Engineering Co. Ltd Longyan China

Belt deviation in circular pipe conveyor systems could lead to material spillage, environmental contamination, reduced efficiency, and accelerated belt wear. Real-time belt deviation detection is crucial for ensuring safe and efficient operation. However, existing methods, primarily developed for flat-belt systems, heavily rely on distinct belt-background semantics, making them unsuitable for circular conveyors where indistinct target features, motion blur, and occlusions pose significant challenges. To address these issues, we reformulate the deviation detection task as an object detection problem, proposing BeltLineNet, a lightweight, real-time deviation detection network specifically designed for circular pipe conveyors. Our method integrates explicit feature learning with a coarse-to-fine global feature fusion mechanism, enhancing belt line representation under complex conditions. Additionally, a shape-prior loss strategy is introduced to improve supervision during training, ensuring more accurate detection of elongated targets. The model is also optimized for real-time deployment through layer-adaptive pruning, achieving a balance between accuracy and computational efficiency. Extensive comparative experiments involving 8 state-of-the-art (SOTA) feature extraction networks and 6 feature enhancement strategies on a self-collected dataset under industrial conditions demonstrate that BeltLineNet surpasses SOTA feature extraction and fusion networks, improving average precision (AP) by 8.23% before pruning and 6.33% after pruning. © 2001-2012 IEEE.

关键词： Belt conveyors

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent Reinforcement Learning with Region Division and Leader-Follower Communication

Multi-Agent Reinforcement Learning with Region Division and ...

引用

2024 China Automation Congress, CAC 2024

作者： Wang, Chao Xu, Xiang Shenzhen Key Laboratory of Control Theory and Intelligent Systems School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen China

ISBN: (纸本)9798350368604

The integration of multi-agent reinforcement learning (MARL) into complex systems has paved new ways for collaborative problem-solving. However, traditional approaches to MARL frequently encounter the challenge of achieving efficient communication among agents, essential for coordinated action. This paper introduces a region division and leader-follower(RDLF) communication algrithm with the MARL framework. RDLF divides the environment into several regions, each managed by a leader agent that coordinates the actions of follower agents and handling inter-region communication. This hierarchical structure reduces unnecessary communication, enhancing learning efficiency. Experimental results in multi-particle environments demonstrate RDLF’s superiority over existing MARL algorithms, especially with increasing agent numbers. RDLF effectively addresses scalability and communication challenges in large-scale multi-agent systems, providing a robust foundation for its application in complex and dynamic environment. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Image Matching Method for SAR and Optical Image Based on Siamese Network 1

引用

3rd International Conference on Autonomous Unmanned systems, ICAUS 2023

作者： Yang, Yanjiao Wang, Ziwei Qu, Guangzhou Ma, Meng Liu, Shuaishuai Chi, Qingxi Beijing Electro-Mechanical Engineering Institute Beijing China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China

ISBN: (数字)9789819710874

ISBN: (纸本)9789819710867

Aiming at the difficulty of the similarity extraction between the SAR and optical satellite image, an image Matching method for SAR and Optical image based on siamese network is studied. The radar system can provide SAR images while also providing SAR distance and other measurement information. Optical satellites can obtain real-time optical images and provide corresponding longitude and latitude information. Based on the satellite positioning algorithm, the cumulative error of sins can be corrected by kalman filter using SAR and optical image matching results and SAR measurements. Simulation results show the effectiveness of the algorithm. © Beijing HIWING Scientific and Technological Information Institute 2024.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Recommendation Based on Knowledge Graph and Graph Neural Network 7th

Recommendation Based on Knowledge Graph and Graph Neural Net...

引用

7th Chinese Conference on Swarm Intelligence and Cooperative control, CCSICC 2023

作者： Shen, Hongjie Guo, Qiuhao Xu, Hongfeng Jiang, Jixiang Chen, Linxiu Zhejiang Huzhou Aviation Intelligent Technology Research Center Hangzhou310000 China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China

ISBN: (纸本)9789819733231

The recommendation system based on knowledge graph assistance has more advantages than the traditional recommendation system, mainly reflected in: accurate, efficient and explainable. Most of the recommendation methods of existing studies use knowledge graph representation learning for information mining of entity features, but some of them ignore the neighborhood information of knowledge graph entities, resulting in the loss of high-order feature information. Considering the above problem, this study proposes a recommendation method based on graph neural network for the problem that the existing recommendation methods ignore the overall information in the process of knowledge graph entity information mining. The graph attention network is introduced to carry out neighborhood information aggregation to make up for the neighborhood information of missing entities in the process of extracting the features of the knowledge graph in existing research. In this study, the prediction experiments of click rate and top-k recommendation scenarios were carried out on the data under the four backgrounds of movies, books, online courses and music, and the influence of some key parameters and structures in the model on the model was analyzed, compared and discussed. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Probabilistic Forecast of Wind Power in High Wind Scenarios of Cold Wave Weather 7

Probabilistic Forecast of Wind Power in High Wind Scenarios ...

引用

7th IEEE Conference on Energy Internet and Energy system Integration, EI2 2023

作者： Zhou, Haoyang Yang, Ming Yu, Yixiao Li, Menglin Wang, Chuanqi Zhang, Yuanhe Shandong University Key Laboratory of Power System Intelligent Dispatch and Control Jinan China

ISBN: (纸本)9798350345094

As the proportion of installed renewable energy in the power system increases, the weather attributes of the new power system become more and more. and the current meteorological changes are becoming more and more complex, with frequent occurrence of cold wave weather, triggering large fluctuations in wind power output. The traditional wind power forecast method is difficult to adapt to the cold wave weather scenario. The large deviation of the forecast brings a great challenge to the wind power consumption. In this paper, we analyze the characteristics of wind power forecast error fluctuation and the mechanism of error generation based on wind power forecast and measured data during cold wave weather. On this basis, we extract the wind power data and numerical weather prediction data under the cold wave weather, and select the strong correlation meteorological factors based on the Pearson correlation coefficient to determine the inputs of the forecast model. Use the generative adversarial network algorithm to expand the samples, so the wind power dataset under the cold wave weather is constructed. Finally, the quantile regression wind power probabilistic forecast model based on the support vector machine is constructed, and an example is set up to verify the effectiveness of the proposed method. © 2023 IEEE.

关键词： Wind power

来源：评论

学校读者我要写书评

暂无评论

Improved Image Matching Method Between SAR and Optical Based on Gaussian Vote by Ballot 11th

Improved Image Matching Method Between SAR and Optical Based...

引用

11th China Conference on Command and control, C2 2023

作者： Yang, Yanjiao Wang, Ziwei Qu, Guangzhou Ma, Meng Liu, ShuaiShuai Chi, QingXi Beijing Electro-Mechanical Engineering Institute Beijing China Science and Technology on Complex System Control and Intelligent Agent Coopration Laboratory Beijing China

ISBN: (纸本)9789819990207

Aiming to obtain the high-precision matching position and reduce time and resource requirements, an image matching method between SAR and optical based on CSP-DenseNet and Gaussian vote by ballot is proposed. First, in order to detect stable interest points and extract deep feature in SAR image, we use FAST operator and CSP-DenseNet. Then, in order to save time and resource requirements, we use gaussian vote by ballot to determine the high-precision matching position between two *** simulation results reveal the validity of the algorithm. © Chinese Institute of Command and control 2024.

关键词： Synthetic aperture radar

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：