检索结果-内蒙古大学图书馆

19th Chinese Intelligent Systems Conference, CISC 2023

作者： Qin, Minbo Li, Lin Automation Division Department of Control Science and Engineering University of Shanghai for Science and Technology Shanghai200093 China

ISBN: (纸本)9789819968855

Addressing the challenges of wild facial expression datasets being affected by illumination and pose variations, and the expression features being dispersed across multiple easily overlooked facial regions, this paper proposes a facial expression recognition network called Binary and Joint Attention Network. Firstly, The multi-scale binary convolution module integrates texture features of different granularities. Subsequently, the proposed Multi-head Joint Attention module focusing on multiple distinct facial areas through multiple attention heads. Lastly, the inter-attention map loss is designed to prevent attention overlap while assisting in classification. Experimental results on multiple datasets, including SFEW2.0, RAF-DB, FER2013, demonstrate that the proposed network can effectively recognize various facial expressions. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Local binary pattern

来源：评论

学校读者我要写书评

暂无评论

Optimal Cooperative Secondary control for Islanded DC Microgrids via a Fully Actuated Approach

引用

IEEE/CAA Journal of Automatica Sinica 2024年第2期11卷 405-417页

作者： Yi Yu Guo-Ping Liu Yi Huang Peng Shi IEEE Shenzhen Key Laboratory of Control Theory and Intelligent Systems Southern University of Science and TechnologyShenzhen 518055China School of Electrical Engineering and Automation Wuhan UniversityWuhan 430072China School of Electrical and Mechanical Engineering the University of AdelaideSA 5005Australia Research and Innovation Centre Obuda University1034 BudapestHungary

DC-DC converter-based multi-bus DC microgrids(MGs) in series have received much attention, where the conflict between voltage recovery and current balancing has been a hot topic. The lack of models that accurately portray the electrical characteristics of actual MGs while is controller design-friendly has kept the issue active. To this end, this paper establishes a large-signal model containing the comprehensive dynamical behavior of the DC MGs based on the theory of high-order fully actuated systems, and proposes distributed optimal control based on this. The proposed secondary control method can achieve the two goals of voltage recovery and current sharing for multi-bus DC MGs. Additionally, the simple structure of the proposed approach is similar to one based on droop control, which allows this control technique to be easily implemented in a variety of modern microgrids with different configurations. In contrast to existing studies, the process of controller design in this paper is closely tied to the actual dynamics of the MGs. It is a prominent feature that enables engineers to customize the performance metrics of the system. In addition, the analysis of the stability of the closed-loop DC microgrid system, as well as the optimality and consensus of current sharing are given. Finally, a scaled-down solar and battery-based microgrid prototype with maximum power point tracking controller is developed in the laboratory to experimentally test the efficacy of the proposed control method.

关键词： DC microgrids distributed control high-order fully actuated system approach linear quadratic regulator microgrid modeling secondary control

来源：评论

学校读者我要写书评

暂无评论

Deep Co-Training Partial Least Squares Model for Semi-Supervised Industrial Soft Sensing

引用

IEEE Transactions on Systems, Man, and Cybernetics: Systems 2025年第5期55卷 3363-3371页

作者： Zheng, Junhua Zhou, Le Ye, Lingjian Ge, Zhiqiang Zhejiang University of Science and Technology School of Automation and Electrical Engineering Hangzhou310023 China Huzhou University Huzhou Key Laboratory of Intelligent Sensing and Optimal Control for Industrial Systems School of Engineering Huzhou313000 China Southeast University School of Mathematics Nanjing210096 China

Data-driven soft sensing has become quite popular in recent years, which can provide real-time estimations of key variables in industrial processes. While the introduction of deep learning does improve the prediction performance, it is highly restricted to the number of labeled training data, as well as large computational burden and cumbersome parameter tuning procedures. How to break through the bottleneck of data-drive models in terms of limited labeled data and high computational complexity should be one of the main recent focuses in the field of industrial soft sensing. In this article, a deep co-training PLS (deep CT-PLS) model is proposed to extend the ordinary PLS model to the semi-supervised deep form. While the deep model can efficiently extract inherent natures of process data, the co-training strategy makes lots of unlabeled data useful through a two-view cross training and annotation process. In this case, the performance restriction of the deep PLS model can be greatly relieved, with the incorporation of additional unlabeled data, while at the same time the designed model structure keeps in a low computational complexity. Based on the case study on a real industrial production process, the deep CT-PLS model can significantly improve the soft sensing performance. © 2013 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Method of improving pedestrian navigation performance based on chest card

引用

Journal of Systems engineering and Electronics 2024年第4期35卷 987-998页

作者： CHENG Hao GAO Shuang CAI Xiaowen WANG Yuxuan WANG Jie School of Instrumentation and Optoelectronic Engineering Beihang UniversityBeijing 100191China School of Automation and Electronic Information Xiangtan UniversityXiangtan 411105China Navigation Guidance and Control Graduate School of the Second Institute of China Aerospace Science and Industry CorporationBeijing 100854China

With the development of positioning technology,loca-tion services are constantly in demand by *** a primary location service pedestrian navigation has two main approaches based on radio and inertial *** pedestrian naviga-tion based on radio is subject to environmental occlusion lead-ing to the degradation of positioning *** pedestrian navigation based on micro-electro-mechanical system inertial measurement unit(MIMU)is less susceptible to environmental interference,but its errors dissipate over *** this paper,a chest card pedestrian navigation improvement method based on complementary correction is proposed in order to suppress the error divergence of inertial navigation *** suppress atti-tude errors,optimal feedback coefficients are established by pedestrian motion *** extend navigation time and improve positioning accuracy,the step length in subsequent movements is compensated by the first step *** experi-mental results show that the positioning accuracy of the pro-posed method is improved by more than 47%and 44%com-pared with the pure inertia-based method combined with step compensation and the traditional complementary filtering com-bined method with step *** proposed method can effectively suppress the error dispersion and improve the positioning accuracy.

关键词： pedestrian navigation micro-electro-mechanical sy-stem(MEMS) inertial navigation complementary filtering

来源：评论

学校读者我要写书评

暂无评论

Resilient control of flexible hypersonic vehicles against unmatched distributed faults

引用

Chinese Journal of Aeronautics 2024年第5期37卷 60-70页

作者： Dong ZHAO Wenjing REN School of Artificial Intelligence Anhui UniversityHefei 230601China Key Laboratory of System Control and Information Processing Ministry of EducationShanghai Jiao Tong UniversityShanghai 200240China School of Electrical Engineering and Automation Hefei University of TechnologyHefei 230009China

This paper studies a robust fault compensation and vibration suppression problem of flexible hypersonic *** controlled plant is represented by a cascade system composed of a nonlinear Ordinary Differential Equation(ODE)and an Euler-Bernoulli Beam Equation(EBBE),in which the vibration dynamics is coupled with the rigid dynamics and suffers from distributed faults.A state differential transformation is introduced to transfer distributed faults to an EBBE boundary and a longitudinal dynamics is refined by utilizing T-S fuzzy IF-THEN rules.A novel T-S fuzzy based fault-tolerant control algorithm is developed and related stability conditions are *** robust exponential stability and well-posedness are proved by using the modified l_(0)-semigroup based Lyapunov direct approach.A simulation study on the longitudinal dynamics of flexible hypersonic vehicles effectively verifies the validity of the developed theoretical results.

关键词： Flexible hypersonic vehicles ODE-EBBE cascade Robust exponential stability Unmatched distributed fault compensation Vibration suppression

来源：评论

学校读者我要写书评

暂无评论

Convolution Neural Network-based Load Model Parameter Selection Considering Short-term Voltage Stability

引用

CSEE Journal of Power and Energy Systems 2024年第3期10卷 1064-1074页

作者： Ying Wang Chao Lu Xinran Zhang School of Technology Beijing Forestry UniversityBeijing 100083China State Key Laboratory of Control and Simulation of Power System and Generation Equipment Tsinghua UniversityBeijing 100084China School of Automation Science and Electrical Engineering Beihang UniversityBeijing 100083China IEEE

The recently proposed ambient signal-based load modeling approach offers an important and effective idea to study the time-varying and distributed characteristics of power ***,it also brings new *** the load model parameters of power loads can be obtained in real-time for each load bus,the numerous identified parameters make parameter application *** order to obtain the parameters suitable for off-line applications,load model parameter selection(LMPS)is first introduced in this ***,the convolution neural network(CNN)is adopted to achieve the selection purpose from the perspective of short-term voltage *** begin with,the field phasor measurement unit(PMU)data from China Southern Power Grid are obtained for load model parameter identification,and the identification results of different substations during different times indicate the necessity of ***,the simulation case of Guangdong Power Grid shows the process of LMPS,and the results from the CNNbased LMPS confirm its effectiveness.

关键词： Ambient signal CNN field PMU data load model parameter selection short-term voltage stability

来源：评论

学校读者我要写书评

暂无评论

PillarMamba: A Lightweight Mamba-based Model for 3D Object Detection 4

PillarMamba: A Lightweight Mamba-based Model for 3D Object D...

引用

4th IEEE International Conference on Digital Twins and Parallel Intelligence, DTPI 2024

作者： Liu, Yuhang Ge, Yinji Li, Mengyue Zheng, Guixu Sun, Boyi Wang, Fei-Yue Chinese Academy of Sciences Institute of Automation Beijing China Beijing Jiaotong University School of Mechanical Electronic and Control Engineering Beijing China

ISBN: (纸本)9798350349252

Parallel LiDAR is a novel framework for constructing next-generation intelligent LiDAR systems. 3D object detection serves as a common perception task in parallel LiDAR research. However, current approaches heavily rely on CNNs or Transformers for feature interaction, placing high demands on computational resources and memory. We introduce the evolving Mamba architecture into 3D object detection to address these issues and propose a new PillarMamba network. PillarMamba utilizes a pure Mamba-based backbone composed of multiple stacked BEVMamba blocks. Our experiments on the KITTI dataset demonstrate that PillarMamba can achieve 65.41% mAP in BEV and 59.13% mAP in 3D perspectives. It paves the way for constructing more efficient and accurate detection models, holding significant value for practical applications. © 2024 IEEE.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Odor Source Search with a Wolf Pack Algorithm via Multi-UAV in Outdoor Environment 6

Odor Source Search with a Wolf Pack Algorithm via Multi-UAV ...

引用

6th International Conference on Industrial Artificial Intelligence, IAI 2024

作者： Wu, Wen-Qiang Li, Ji-Gong Yang, Jing School of Automation and Electrical Engineering Tianjin University of Technology and Education Tianjin Key Laboratory of Information Sensing and Intelligent Control Tianjin China

ISBN: (纸本)9798350356618

Concerning the problem of odor source search with robots in a large outdoor environment, an odor source search method based on the improved wolf pack algorithm (IWPA) is proposed, in which each wolf corresponds to an unmanned aerial vehicle (UAV). The environment is firstly traversed by the UAVs in partitions by using rectangular wave- shaped paths. Once odor plume is detected by any UAV, the WPA is applied to guide the UAVs towards the odor source. Considering the limited number of UAVs, in order to improve the utilization rate of UAVs, the wolf pack is simplified into two roles: the alpha wolf and other wolves. Meanwhile, to avoid collisions between UAVs and enable UAVs to fully sample around the suspected target position, a besieging algorithm based on a virtual force field is designed to calculate next flight direction for the UAVs. During this period, the odor source position is determined by the alpha wolf which is constantly elected by comparing the fitness values of all wolves. Simulation results show that the IWPA method can find the odor source in short time without falling into local extremum, demonstrating good convergence and being suitable for odor source search tasks in outdoor environments. © 2024 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

A Method for Allocating Hybrid Teaching Credit Hours Using Hierarchical Analysis 25

A Method for Allocating Hybrid Teaching Credit Hours Using H...

引用

25th IEEE China Conference on System Simulation Technology and its Application, CCSSTA 2024

作者： Meng, Xiangang Li, Xiaojing Xu, Liang School of Electrical Engineering and Automation Tianjin University of Technology Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems Tianjin China

ISBN: (纸本)9798350366600

Hybrid teaching combines traditional teaching and flipped classroom, which is a new teaching mode with the advantages of both modes. In hybrid teaching mode, reasonable allocation of credit hours between traditional teaching and flipped classroom is an important issue for the teaching work. This paper first proposes a method of using hierarchical analysis to allocate credit hours for hybrid teaching of Digital Electronic Technology courses. Firstly, we divided hybrid teaching into stage and content layers, and determined the various elements of stage and content layers. Secondly, the requirements of the Analytic Hierarchy Process were applied to organize these two levels, and pairwise importance comparisons were made for each element within the level. Index judgment matrices were established for the stage level and content level, respectively. Then, the calculation steps of the Analytic Hierarchy Process were designed, and matrix operations were used to obtain the normalized weights of each element in the stage and content layers of traditional teaching and flipped classrooms. This weight was used to determine the class hours to be allocated for each stage and content. Finally, the feasibility and effectiveness of the method proposed in this paper were verified using the example of hybrid teaching hour allocation in Chapter 4 of the Digital Electronic Technology course at Tianjin University of Technology. © 2024 IEEE.

关键词： Hierarchical systems

来源：评论

学校读者我要写书评

暂无评论

Characteristics of perfluoromethyl vinyl ether:A new eco-friendly alternative gas for SF_(6)

引用

High Voltage 2024年第3期9卷 509-517页

作者： Song Xiao Yijiang Chen Mingjun Tang Shuangshuang Tian Haoran Xia Yifan Wang Ju Tang Yi Li Xiaoxing Zhang State Key Laboratory of Power Grid Environmental Protection School of Electrical Engineering and AutomationWuhan UniversityHubeiChina Key Laboratory for High-Efficiency Utilization of Solar Energy and Operation Control of Energy Storage System School of Electrical and Electronic EngineeringHubei University of TechnologyWuhanChina

The exploration of eco-friendly insulating gas to substitute the most potent greenhouse gas sulphur hexafluoride(SF6)has consistently garnered significant ***,the au-thors evaluated the feasibility of utilising perfluoromethyl vinyl ether(PMVE,C_(3)F_(6)O)as a new branch of eco-friendly insulating gas for the first *** primary dielectric and stability characteristics of PMVE regarding AC breakdown,partial discharge,dielectric recovery,and decomposition properties were revealed under various gas pressure and electrical field *** was found that PMVE demonstrated superior dielectric strength,with the AC breakdown and PD inception voltage(PDIV)1.10 and 1.14 times that of pure SF_(6).Furthermore,the dielectric strength of PMVE exhibits stability even after undergoing 100 cycles of AC breakdowns,and there is no observable formation of solid precipitation on the electrode *** discharge decomposition of PMVE mainly generates fluorocarbon(CF_(4),C_(2)F_(6),C_(3)F_(6),C_(3)F_(8),etc.)and ***,the exceptional insulation stabilityandno absence of solidprecipitation featuresendow PMVE tobe utilised as a new eco-friendly gas for SF_(6)-free gas-insulated equipment.

关键词： surface dielectric vinyl

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：