检索结果-内蒙古大学图书馆

9th International Conference on control, Decision and Information Technologies, CoDIT 2023

作者： Lin, Yu-Chen Chen, Wen-Hui Chen, Hung-Cheng Wang, Chia-Hung Feng Chia University Department of Automatic Control Engineering Taichung Taiwan Graduate Institute of Automation Technology National Taipei University of Technology Taipei Taiwan

ISBN: (纸本)9798350311402

In this paper, we propose a novel model compression method based on knowledge distillation, that is called Pre-Distillation, for object detection task. First, the full model is 'squashed' (by the instructor) to generate key information (a.k.a. attention mechanism), and it is also referred to as dataset condensation;it is then provided for lightweight model learning (for the student). Students can study and preview the course through lightweight models with key information that is compressed by the instructor. Additionally, students can also be able to improve their efficiency in learning and acquire integrative understanding of the subject through supplementary materials in which the they will be observing hidden information within the ground truth. This paper is verified and quantified by the public databases of Pascal VOC. The results show that the previewing distillation strategy developed in this paper has higher accuracy. The accuracy of ResNet-101 is 74.02%, which is 2.28% higher than that of the un-distilled 71.74%. The method in this paper is an algorithm-based performance improvement method. Our proposed scheme is a high-efficiency distillation strategy that does not need to change the network architecture and also can avoid the occurrence of model overfitting and speed up model training. © 2023 IEEE.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Low-Carbon Optimization Dispatch of Multi-Integrated Energy System Based on Kriging Metamodel and Stackelberg Game 16

Low-Carbon Optimization Dispatch of Multi-Integrated Energy ...

引用

16th IEEE PES Asia-Pacific Power and Energy engineering Conference, APPEEC 2024

作者： Zhang, Zhaoqing Sun, Yonghui Sheng, Fan Yin, Chenxu Sidorov, Denis N. Iskakov, Alexey B. School of Electrical and Power Engineering Hohai University Nanjing China Melentiev Energy System Institute Russian Academy of Sciences Irkutsk Russia School of Electrical Engineering and Automation Harbin Institute of Technology Harbin China Trapeznikov Institute of Control Sciences Russian Academy of Sciences Moscow Russia

ISBN: (纸本)9798350386127

Integrated energy system (IES) is an advanced configuration that combines electrical energy, thermal energy, and renewable energy, into a unified system. In recent years, the architecture of IES has gradually changed from vertical integration to interactive competition, and its distributed characteristics have become increasingly evident. Therefore, traditional centralized optimization strategies can no longer meet the current practical situation. In this paper, a low-carbon optimization dispatch for IES based on Stackelberg game and kriging metamodel is proposed. In order to address this problem, firstly, three typical models containing hydrogen blending gas technology and a kind of ladder-type carbon trading mechanism considering reward and punishment (RP-LCTM) are established. Secondly an integrated energy manager (IEM) is introduced and a Stackelberg game model with the IEM as the leader and three typical IESs as followers is established. Finally, the kriging metamodel is used to optimize the transaction electricity price. During the game process, the IPSO algorithm is used to optimize electricity prices in key price regions. At last, an experimental example is utilized to demonstrate the effectiveness of the proposed method. © 2024 IEEE.

关键词： Carbon sequestration

来源：评论

学校读者我要写书评

暂无评论

Multi-objective Optimal Operation of Centralized Battery Swap Charging System with Photovoltaic

引用

Journal of Modern Power Systems and Clean Energy 2022年第1期10卷 149-162页

作者： Yuanzheng Li Yihan Cai Tianyang Zhao Yun Liu Jian Wang Lei Wu Yong Zhao School of Artificial Intelligence and Automation Ministry of Education Key Laboratory of Image Processing and Intelligence ControlHuazhong University of Science and TechnologyWuhanChina School of Electrical and Electronic Engineering Nanyang Technological UniversitySingaporeSingapore College of Mechatronics and Control Engineering Shenzhen UniversityShenzhenChina Department of Electrical&Computer Engineering Stevens Institute of TechnologyHobokenUSA

Electric vehicles(EVs)are widely deployed throughout the world,and photovoltaic(PV)charging stations have emerged for satisfying the charging demands of EV *** paper proposes a multi-objective optimal operation method for the centralized battery swap charging system(CBSCS),in order to enhance the economic efficiency while reducing its adverse effects on power *** proposed method involves a multi-objective optimization scheduling model,which minimizes the total operation cost and smoothes load fluctuations,***,we modify a recently proposed multi-objective optimization algorithm of non-sorting genetic algorithm III(NSGA-III)for solving this scheduling ***,simulation studies verify the effectiveness of the proposed multi-objective operation method.

关键词： Multi-objective optimization electric vehicle battery swap charging system scheduling photovoltaic

来源：评论

学校读者我要写书评

暂无评论

PDR Algorithm for Particle Filtering Based on Motion Optimization Models

PDR Algorithm for Particle Filtering Based on Motion Optimiz...

引用

2023 China automation Congress, CAC 2023

作者： Xu, Wanyong Chen, Guangwu Wang, Siqi Zhou, Xin Yang, Yang LiPeng, Peng Key Laboratory of Traffic Information Engineering and Control in Plateau Lanzhou Jiaotong University LanZhou China Institute of Automation Lanzhou Jiaotong University LanZhou China

ISBN: (纸本)9798350303759

In this paper, for the problem of decreased positioning accuracy of Global Navigation Satellite System (GNSS) in urban environment due to signal occlusion, reflection and other factors, combined with the demand of ordinary pedestrians for high-precision positioning, we propose a Pedestrian Dead Reckoning (PDR) combination positioning technique based on GNSS assistance. The double threshold energy detection method is used to detect the MEMS data after wavelet noise reduction, to realize accurate and efficient pace recognition, so as to improve the PDR positioning accuracy, to establish the observation model with the GNSS information, and to correct the PDR algorithm through the improved particle filtering, which can effectively inhibit the cumulative error caused by the long time working of MEMS and the positioning error caused by the reduced accuracy of GNSS in the complex environment. Experiments are designed to demonstrate the algorithm, and the pace recognition rate reaches more than 99% and the mean square error of the positioning result is 1.2m when tested in the complex test section, indicating that the algorithm can effectively improve the accuracy of positioning. © 2023 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Intelligent Log Analysis Technology for Distributed Energy Production Management System 6

Intelligent Log Analysis Technology for Distributed Energy P...

引用

6th IEEE International Electrical and Energy Conference, CIEEC 2023

作者： Qie, Kaiming Wang, Yuanyuan Lin, Fuliang Zhao, Ruizheng Yang, Han Beijing Institute of Control and Electronic Technology Science and Technology on Information Systems Engineering Laboratory Beijing China School of Automation Chongqing University Chongqing China

ISBN: (纸本)9798350346671

Aiming at the demand of distributed energy production management system for intelligent operation and maintenance, considering the problems in current log analysis method, we propose an intelligent log analysis technology for distributed energy production management system. This technology applies distributed log framework to achieve the collection, storage, analysis and display of various equipment and service logs in the energy production management system. On the one hand, we use log anomaly detection technology to realize the anomaly detection of single node and the generating of log anomaly alarm, On the other hand, we use rule reasoning technology to realize the analysis and tracing of log anomaly alarm. In addition, we combine with practical application, optimize the traditional rule matching algorithm, which improves the fault tolerance of the matching network, and gets better accuracy and efficiency of the algorithm. © 2023 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Fuzzy-Cycle: Visible to Infrared Ship Image Translation Based on CycleGAN 6

Fuzzy-Cycle: Visible to Infrared Ship Image Translation Base...

引用

6th International Conference on Industrial Artificial Intelligence, IAI 2024

作者： He, Long Yu, Yue Liu, Chang Sun, Yangyang Jiang, Feng Hu, Xiaoning Pan, Chengwei Dong, Xiwang School of Artificial Intelli-gence Beihang University Beijing China Beijing Institute of Control and Electronic Technology Beijing China School of Automation Science and Electrical Engineering Science and Technology on Aircraft Control Laboratory Beihang University School of Artificial Intelligence Institute of Unmanned System Beijing China

ISBN: (纸本)9798350356618

Detecting targets in infrared ship images is crucial for various applications, such as maritime rescue and ship inspection. Training contemporary mainstream detection and segmentation models, however, requires large-scale, high-quality infrared ship image datasets. In open-world maritime confrontation scenarios, the complex and variable environment, scarcity of target ships, and limited acquisition conditions make it challenging to construct high-quality infrared ship image datasets. To address this issue, this paper proposes an unpaired visible-infrared ship image translation model based on CycleGAN, named Fuzzy-Cycle. The model introduces a fuzzy cycle loss to encourage the model to learn feature mapping rules between different domains while minimizing attention to unnecessary features. Additionally, the method employs U-Net as the generator network to retain shallow image features during upsampling and selects PatchGAN as the discriminator network, embedding Haar wavelet transform to enhance the discriminator's ability to analyze image frequency domain features. Experiments on the VAIS dataset demonstrate that the proposed algorithm outperforms mainstream unpaired image transfer models, showing excellent performance in the task of visible-infrared ship image translation. Furthermore, zero-shot image translation experiments on the HRSC2016 dataset prove the generalizability and reliability of the proposed method. © 2024 IEEE.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Practical Predefined-Time Consensus control for High-Order Multiagent Systems Via Output Feedback

Practical Predefined-Time Consensus Control for High-Order M...

引用

2024 China automation Congress, CAC 2024

作者： Li, Xiaoting Cao, Xiaotong Li, Yueti Jiao, Dexin Wang, Chen Zou, An-Min College of Engineering Shantou University Shantou China School of Control Engineering Northeastern University at Qinhuangdao Qinhuangdao China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798350368604

This paper considers the problem of practical predefined-time (PPT) consensus control for a class of high-order nonlinear multiagent systems. With the help of the smooth time-varying function-based technique, the leader’s state and the follower’s unmeasurable states are estimated by introducing PPT observers. Then, a PPT output feedback consensus control algorithm with no singularity and discontinuity is proposed based on the observers. Finally, the effectiveness of the designed output feedback PPT consensus control scheme is validated by virtue of an illustrative numerical example. © 2024 IEEE.

关键词： Feedback

来源：评论

学校读者我要写书评

暂无评论

Optimizing Hydrogen Highway Planning Model Considering Hydrogen Cost and Vehicle Flow Effects

Optimizing Hydrogen Highway Planning Model Considering Hydro...

引用

2024 IEEE IAS Industrial and Commercial Power System Asia, I and CPS Asia 2024

作者： Zhang, Yan Lv, Yong Wan, Yanming Sun, Yuxin Zhang, Xian Wang, Guibin Liu, Chang China Hydrogen Alliance Research Institute Beijing China Shenzhen University School of Mechanical Electrical and Control Engineering Shenzhen China University of Liverpool Department of Electrical and Electronic Engineering Liverpool United Kingdom School of Mechanical Engineering and Automation Shenzhen China

ISBN: (纸本)9798350352290

In recent years, global governments have been actively advocating for the adoption of hydrogen fuel cell vehicles (HFCVs) as a means to foster a more sustainable future in transportation. However, the widespread integration of these vehicles necessitates robust hydrogenation infrastructure support. This paper presents a novel hydrogen highway optimization planning model tailored for the strategic placement of hydrogen refueling stations (HRSs) along highways. Based on the traditional HRS site selection models, this approach innovatively integrates factors encompassing hydrogen procurement, transportation, and utilization. The model optimizes the location, scale of the HRSs and quantity of hydrogen dispensers within each HRS, utilizing the minimum unit cost of hydrogen as the objective function. To verify the effectiveness, the proposed model is applied in the Beijing-Tianjin-Hebei (BTH) and Chongqing regions, conducting HRS location planning across both demonstration and promotion stages and the specific planning results are obtained. This study offers valuable insights into hydrogen infrastructure planning along highways, serving as a reference for future endeavors in this domain. © 2024 IEEE.

关键词： Hydrogen fuels

来源：评论

学校读者我要写书评

暂无评论

Advances in 3D printing of magnetic materials:Fabrication,properties,and their applications

引用

Journal of Advanced Ceramics 2022年第5期11卷 665-701页

作者： Xiangxia WEI Ming-Liang JIN Haiqiang YANG Xiao-Xiong WANG Yun-Ze LONG Zhangwei CHEN Institute for Future School of AutomationShandong Key Laboratory of Industrial Control TechnologyQingdao UniversityQingdao 266071China Collaborative Innovation Center for Nanomaterials&Devices College of PhysicsQingdao UniversityQingdao 266071China Additive Manufacturing Institute College of Mechatronics and Control EngineeringShenzhen UniversityShenzhen 518060China

Magnetic materials are of increasing importance for many essential applications due to their unique magnetic ***,due to the limited fabrication ability,magnetic materials are restricted by simple geometric ***-dimensional(3D)printing is a highly versatile technique that can be utilized for constructing magnetic *** shape flexibility of magnets unleashes opportunities for magnetic composites with reducing post-manufacturing costs,motivating the review on 3D printing of magnetic *** paper focuses on recent achievements of magnetic materials using 3D printing technologies,followed by the characterization of their magnetic properties,which are further enhanced by ***,the corresponding properties depend on the intrinsic nature of starting materials,3D printing processing parameters,and the optimized structural *** emphasis is placed on the functional applications of 3D-printed magnetic materials in different ***,the current challenges and future opportunities are also addressed.

关键词： three-dimensional(3D)printing hard magnets soft magnets magnetic properties applications

来源：评论

学校读者我要写书评

暂无评论

Global-Local Adaptive Attention-Based U-Net for Single Image Deblurring

Global-Local Adaptive Attention-Based U-Net for Single Image...

引用

2024 China automation Congress, CAC 2024

作者： Yu, Xinran Li, Yueti Peng, Xuanzhi Wang, Chen Zou, An-Min College of Engineering Shantou University Shantou China School of Control Engineering Northeastern University at Qinhuangdao Qinhuangdao China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798350368604

Image deblurring is a classical ill-posed problem aimed at recovering a clear image from a blurred one. The recent application of Transformers to image restoration tasks has significantly improved performance, thanks to their powerful long-range dependency modeling capabilities. However, the high computational cost of self-attention mechanisms limits their practical use. Additionally, the training cost for Transformer models is considerable. To address the issues of high computational cost and training cost, this paper proposes a novel Global Local Attention (GLA) mechanism that combines global and local adaptive attention. The mechanism uses 1D adaptive pooling operations to capture global context information, while fixed-size 1D pooling with different kernel sizes (7 and 11) is used to capture local details, effectively addressing both long-range dependencies and fine-grained information. Furthermore, a larger receptive field is crucial for effective image deblurring. To this end, we introduce a Feature Enhancement Module (FEM) with an expansive convolutional kernel size that serves as a bottleneck layer to further improve recovery quality. Experimental results demonstrate that our proposed model achieves competitive performance on several benchmark datasets, advancing the field of image restoration. © 2024 IEEE.

关键词： Restoration

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：