检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Yan, Tijin Zhou, Tong Zhan, Yufeng Xiaa, Yuanqing Key Laboratory of Intelligent Control Decision of Complex Systems School of Automation Beijing Institute of Technology Beijing100081 China

With the development of AIoT, data-driven attack detection methods for cyber-physical systems (CPSs) have attracted lots of attention. However, existing methods usually adopt tractable distributions to approximate data distributions, which are not suitable for complex systems. Besides, the correlation of the data in different channels does not attract sufficient attention. To address these issues, we use energy-based generative models, which are less restrictive on functional forms of the data distribution. In addition, graph neural networks are used to explicitly model the correlation of the data in different channels. In the end, we propose TFDPM, a general framework for attack detection tasks in CPSs. It simultaneously extracts temporal pattern and feature pattern given the historical data. Then extract features are sent to a conditional diffusion probabilistic model. Predicted values can be obtained with the conditional generative network and attacks are detected based on the difference between predicted values and observed values. In addition, to realize real-time detection, a conditional noise scheduling network is proposed to accelerate the prediction process. Experimental results show that TFDPM outperforms existing state-of-the-art attack detection methods. The noise scheduling network increases the detection speed by three times. Copyright © 2021, The Authors. All rights reserved.

关键词： Embedded systems

来源：评论

学校读者我要写书评

暂无评论

Resistance Distances in Directed Graphs: Definitions, Properties, and Applications

arXiv

引用

arXiv 2023年

作者： Zhu, Mingzhe Zhu, Liwang Li, Huan Li, Wei Zhang, Zhongzhi Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai200433 China Shanghai Engineering Research Institute of Blockchains Fudan University Shanghai200433 China Research Institute of Intelligent Complex Systems Fudan University Shanghai200433 China Academy for Engineering and Technology Fudan University Shanghai200433 China

Resistance distance has been studied extensively in the past years, with the majority of previous studies devoted to undirected networks, in spite of the fact that various realistic networks are directed. Although several generalizations of resistance distance on directed graphs have been proposed, they either have no physical interpretation or are not a metric. In this paper, we first extend the definition of resistance distance to strongly connected directed graphs based on random walks and show that the two-node resistance distance on directed graphs is a metric. Then, we introduce the Laplacian matrix for directed graphs that subsumes the Laplacian matrix of undirected graphs as a particular case, and use its pseudoinverse to express the two-node resistance distance, and many other relevant quantities derived from resistance distances. Moreover, we define the resistance distance between a vertex and a vertex group on directed graphs and further define a problem of optimally selecting a group of fixed number of nodes, such that their resistance distance is minimized. Since this combinatorial optimization problem is NP-hard, we present a greedy algorithm with a proved approximation ratio, and conduct experiments on model and realistic networks to validate the performance of this approximation algorithm. Copyright © 2023, The Authors. All rights reserved.

关键词： Directed graphs

来源：评论

学校读者我要写书评

暂无评论

Optimal Carbon Capture, Utilization and Storage Planning for Multi-Energy System

Optimal Carbon Capture, Utilization and Storage Planning for...

引用

Chinese Control Conference (CCC)

作者： Aoyu Hu Da Xu Menglu Gao School of Automation China University of Geosciences Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China DC Company of State Grid Hubei Electric Power Co. Ltd. Yichang China

In response to the national dual carbon policy, carbon capture, utilization and storage (CCUS) are currently attracting much attention. This paper proposes optimal CCUS planning for multi-energy system. In this multi-energy system, transmission network and natural gas network are coupled via conversion and storage devices in the energy hubs. The CCUS planning is formulated based on a source-sink matching method to analyze the CO2 capture points, CO 2 storage points and CO 2 transportation routes. Furthermore, the original CCUS planning problem is reformulated as a mixed integer second order cone programming (MISOCP) and subsequently solved to guarantee a satisfactory convergence performance. Numerical studies on an urban multi-energy system are implemented to verify the effectiveness and superiority of the proposed methodology over conventional scheme.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Steady Conformal Support Structures for 3D Printing*

Steady Conformal Support Structures for 3D Printing*

引用

IEEE International Conference on Automation Science and Engineering (CASE)

作者： Dong Wang Zhen Shen Qihang Fang Dong-Ming Yan Weixing Wang Qing Wang Gang Xiong School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences Dongguan China Intelligent Manufacturing Center Qingdao Academy of Intelligent Industries Qingdao China Beijing TenDimensions Technology Co. Ltd. Beijing China

ISBN: (数字)9798350358513

ISBN: (纸本)9798350358520

In vat photopolymerization 3D printing, cylindrical supports are commonly utilized due to their versatility. However, these supports, which vary in length and possess independent structures, are susceptible to deformation when exposed to external forces exerted by the 3D printer’s scraper during its movement. This deformation can potentially compromise the accuracy of the entire printing process. We propose a conformal support structure that adapts to the shape of the bottom contour of the model. By employing the Delaunay triangulation algorithm to approximate the bottom contour points of the model, the conformal support surface significantly reduces the length of the top support bars and integrates all the top support rods into a unified structure, thereby enhancing the stability of the entire support system. Additionally, the bottom ribs of the support structure can be reoriented to withstand forces in the X or Y direction, which are generated by the 3D printer’s scraper during its movement. We have developed a support region finding algorithm based on the Union-Find Disjoint Sets data structure, which calculates the region requiring support in the 3D model to be printed and generates the top support rods quickly. Finite element simulations have been conducted, and the results demonstrate that the conformal support structure exhibits a 96% reduction in deformation compared to the cylindrical support, indicating that our proposed structures are steadier.

关键词： Deformable models Solid modeling Adaptation models Three-dimensional displays Deformation Simulation Three-dimensional printing Stability analysis Finite element analysis Surface treatment

来源：评论

学校读者我要写书评

暂无评论

Stability and Bifurcation control of Fractional BAM Neural Networks with Diffusion and Time Delays

Stability and Bifurcation control of Fractional BAM Neural N...

引用

Chinese Control Conference (CCC)

作者： Feng Liu Wei Wang Gang Cai Feifan Zhou Hua O Wang Xiuqin Yang School of Automation China University of Geosciences Wuhan China Engineering Research Center of Ministry of education for intelligent technology of earth exploration Hubei key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China Department of Mechanical Engineering Boston University Boston MA USA School of Education Minzu University of China Beijing China

Based on fractional calculus theory and reaction-diffusion equation theory, a fractional-order time-delay reaction-diffusion neural network with Neumann boundary conditions is investigated. By constructing the phase space basis based on the Laplace operator eigenvector, the system equation is linearized to obtain the characteristic equation. Then, the characteristic equation is analyzed, and the local stability of the system at the equilibrium point is discussed. And taking the time delay as the bifurcation parameter, the stability changes of the system at the equilibrium point and the generation conditions of the Hopf bifurcation are studied when the time delay changes. Moreover, a state feedback controller is designed to control the bifurcation of the system. Finally, the theoretical derivation is verified by numerical simulation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of a Web-based Collaborative Manufacturing System Based on Knowledge Graph

Design and Implementation of a Web-based Collaborative Manuf...

引用

Digital Twins and Parallel Intelligence (DTPI), IEEE International Conference on

作者： Meng Yuan Huaiyu Wu Zhen Shen Yunjun Han Jiehan Zhou Zhijian Yue Gang Xiong State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences Dongguan China Intelligent Manufacturing Center Qingdao Academy of Intelligent Industries Qingdao China Faculty of Information Technology and Electrical Engineering University of Oulu Oulu Finland

ISBN: (数字)9798350349252

ISBN: (纸本)9798350349269

Collaborative manufacturing is central to agile, intelligent, and cloud-based manufacturing paradigms. This paper presents the design and implementation of a web-based collaborative manufacturing system based on a knowledge graph (KG). The system achieves the full spectrum of knowledge extraction, fusion, and reasoning across the industrial chain, thereby enhancing efficiency and reducing operational costs. The proposed system constructs an industrial chain KG and multi-agent systems, offering comprehensive digital services across the manufacturing value chain. It supports the integration of business processes, data, and standard information for enterprise groups, presenting collaborative manufacturing data of the industrial chain in real-time visualization. The paper further discusses a method for real-time perception of anomalies in the collaborative manufacturing process, utilizing expert knowledge and data-driven insights to construct an operational risk KG. The system’s architecture, workflow, and functional design are detailed, along with application cases in visual dynamic management. The conclusion underscores the system’s potential to improve supply-demand chain management and operational efficiency in collaborative manufacturing.

关键词： Knowledge engineering Visualization Manufacturing processes Collaboration Data visualization Knowledge graphs Real-time systems Digital twins Standards Multi-agent systems

来源：评论

学校读者我要写书评

暂无评论

Efficient waste heat recovery of a hybrid solar-biogas-fueled gas turbine cycle for poly-generation purpose: 4E analysis, parametric study, and multi-objective optimization

引用

Fuel 2023年 333卷

作者： Zhou, Jincheng Zoghi, Mohammad Abed, Hooman School of Computer and Information Qiannan Normal University for Nationalities Guizhou Duyun 558000 China Key Laboratory of Complex Systems and Intelligent Optimization of Guizhou Guizhou Duyun 558000 China Faculty of Mechanical Engineering University of Guilan Rasht Iran

In the present theoretical study, a steam Rankine cycle (SRC) and a modified organic flash cycle (MOFC) are used as bottoming systems for a gas turbine cycle (GTC). Then, the waste energy of the compression stage of the GTC is recuperated by a hot water unit, and the waste energy of the SRC and MOFC is recovered in a single effect LiCl-H₂O absorption chiller and a thermoelectric generator, correspondingly. Furthermore, the power produced in the SRC and MOFC is transmitted to a proton exchange membrane electrolyzer and a reverse osmosis desalination unit to produce hydrogen and freshwater. Thus, the system is converted into a ploy-generation layout. In the parametric study section, the effects of changes in the pressure ratio of the GTC, inlet temperature of the solar power tower, number of heliostat mirrors, methane content of biogas, inlet temperature of the gas turbine, and direct normal irradiance on the energy, exergy, exergy-economic, and environmental output parameters are investigated. The results show that solar power tower is the most influential component in the exergy destruction and cost rates. Furthermore, the exergy efficiency, total cost rate, the unit cost of products, and payback period are obtained as 24.34 %, 6390 $/h, 20.17 $/GJ, and 0.687 years in the base case. Considering exergy efficiency and total cost rate as the objective functions, these two parameters improved by 14.87 % and 11.01 % in the optimum case, respectively. © 2022 Elsevier Ltd

关键词： Biogas fuel Gas turbine cycle Poly-generation Solar power tower Thermo-economic Waste heat recovery

来源：评论

学校读者我要写书评

暂无评论

Explainable Deep Learning for Semg-Based Similar Gesture Recognition: A Shapley-Value-Based Solution

SSRN

引用

SSRN 2023年

作者： Wang, Feng Ao, Xiaohu Wu, Min Kawata, Seiichi She, Jinhua School of Automation China University of Geosciences Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan430074 China School of Engineering Tokyo University of Technology Hachioji Tokyo192-0982 Japan

Surface electromyography (sEMG) based gesture recognition shows promise in enhancing human-robot interaction. However, accurately recognizing similar gestures is a challenging task, and the underlying mechanisms of gesture recognition are not well understood. To address these issues, we developed a new solution called the Shapley-value-based similar gesture recognition (SV-SGR) method. Our solution combines deep learning and game theory to achieve high recognition accuracy and interpretability. First, we devised a data preprocessing method that converts sEMG signals into sEMG color images, which can be more effectively utilized by deep learning techniques. Next, we established a deep-neural-network-based model for gesture recognition using the processed sEMG color images. Then, we designed a global explanation approach based on Shapley values to quantify the contribution of each channel to recognizing similar gestures. Finally, we carried out an explanation analysis, which provides feedback on the recognition model to enhance the precision of gesture recognition. Extensive comparisons and interpretable analyses have been conducted on real-world datasets, and the results demonstrate that the SV-SGR method outperforms other baselines under various experimental conditions. The interpretable analysis method based on Shapley values effectively enhances the performance of recognizing similar gestures and provides valuable insights into the decision-making process of recognition models. © 2023, The Authors. All rights reserved.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

Learning Greenhouse Climate Control Policy from Monitored Data

Learning Greenhouse Climate Control Policy from Monitored Da...

引用

2022 Chinese Automation Congress, CAC 2022

作者： Zhao, Xiaoxuan Wang, Haoyu Wang, Xiujuan Lewlomphaisarl, Udom Li, Dong Hua, Jing Kang, Mengzhen The State Key Laboratory for Management and Control of Complex Systems Chinese Academy of Sciences Institute of Automation Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Beijing Engineering Research Center of Intelligent Systems and Technologies Beijing China National Electronics and Computer Technology Center Pathum Thani Thailand Institute of Digital Agriculture Zhejiang Academy of Agricultural Sciences Hangzhou China Qingdao AgriTech Co. Ltd. Qingdao China

ISBN: (纸本)9781665465335

The knowledge of solar greenhouse growers on environment control plays an important role in greenhouse production and management. We proposed a way to extract the control strategies from the monitored data of greenhouses by building a long short-term memory (LSTM) model. The result is verified according to the real monitored data of a solar greenhouse, which shows that the model can learn the control strategy of a ventilator in the solar greenhouse. Through monitored data and models, the knowledge of greenhouse ventilation control can be learned, and automatic control can be achieved in a greenhouse with a similar configuration. © 2022 IEEE.

关键词： Greenhouses

来源：评论

学校读者我要写书评

暂无评论

Optimal Portfolio of Wind-solar-hydro Hybrid Renewable Generation based on Variable Speed Pumped Storage

Optimal Portfolio of Wind-solar-hydro Hybrid Renewable Gener...

引用

China International Electrical and Energy Conference (CIEEC)

作者： Shizhe Xiang Da Xu Menglu Gao School of Automation China University of Geosciences Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China Ministry of Education Engineering Research Center of Intelligent Technology for Geo-Exploration Wuhan China DC Company of State Grid Hubei Electric Power Co. Ltd. Yichang China

Compared with separate solar or wind generation, the hybrid wind-solar-hydro renewable portfolio can achieve better generation characteristics due to their temporal-spatial complementarities. This paper proposes optimal portfolio of wind-solar-hydro hybrid renewable generation based on variable speed pumped storage (VSPS). In this portfolio, the complementarities of hydro-solar-wind hybrid renewable energy sources (RESs) are fully exploited via various conversion and storage devices for zero carbon 100% renewable supplies. Compared to traditional fixed speed pumped storage (FSPS), the VSPS has obvious advantages in power regulation and renewable accommodation, which is comprehensively modeled to capture its dynamic operational dispatchability and flexibility. The portfolio production, conversion, storage, and consumption are formulated via a two-stage framework, which takes the minimum system investment cost as the objective function. Case studies on southwest China are performed to show the effectiveness and superiority of the proposed methodology on cost-effective accommodation.

关键词：

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：