检索结果-内蒙古大学图书馆

4th International Conference on electrical engineering and computer Science, ICECOS 2024

作者： Dinata, Noer Fadzri Perdana Jambak, Muhammad Irfan Ramli, Makbul Anwari Muhammad Sidik, Muhammad Abu Bakar Universitas Sriwijaya Faculty of Engineering Department of Electrical Engineering Palembang Indonesia King Abdulaziz University Faculty of Engineering Department of Electrical and Computer Engineering Jeddah Saudi Arabia

ISBN: (纸本)9798350368253

This study explores the application of Deep Reinforcement Learning (DRL) in controlling a microgrid, with a focus on evaluating the performance of a DRL-based inverter voltage regulator compared to a traditional PID-based controller. The microgrid is subjected to fluctuating load conditions, simulating real-world scenarios where load demand varies significantly. Detailed specifications for the microgrid components are provided, and both control algorithms are tested for their effectiveness in maintaining voltage stability and synchronization with the main grid. Simulation results reveal that the DRL-based controller outperforms the PID controller in tracking the main grid voltage and stabilizing the voltage profile under dynamic conditions. While islanded, the DRL controller achieves a mean absolute deviation of 0.02 from the setpoint, compared to 0.06 for the PID. In grid synchronization, the DRL maintains a synchronization error of less than 6Vrms, while the PID controller exhibits a larger error of up to 15 Vrms. The DRL controller's adaptive learning capabilities allow it to respond more effectively to rapid load changes, reducing deviations and enhancing overall performance. These findings suggest that DRL offers a promising alternative to conventional control methods for microgrids, providing improved reliability and efficiency in environments characterized by high variability. Further research is recommended to optimize DRL algorithms for better voltage stability and synchronization. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Single-Phase Dynamic Voltage Restorer Based on Filterless Z-Source AC-AC Converter 16

A Single-Phase Dynamic Voltage Restorer Based on Filterless ...

引用

16th Annual Power Electronics, Drive Systems, and Technologies Conference, PEDSTC 2025

作者： Hosseinzadeh, Nazanin Mousavi, Seyyed Mohammad Javad Alizadeh, Darioush Babaei, Ebrahim University of Tabriz Faculty of Electrical and Computer Engineering Tabriz Iran Imam Khomeini International University Faculty of Technical and Engineering Electrical Engineering Department Qazvin Iran

ISBN: (纸本)9798331533946

In this paper, a single-phase dynamic voltage restorer (DVR) based on a Z-source AC-AC converter is proposed. The Z-source converter has a shared ground and continuous input current. Using the impedance network filter feature, the direct connection of the primary side of the injection transformer to the impedance network is provided. Therefore, the proposed system's volume, weight, and cost are reduced due to the elimination of the input and output LC filter. The impedance network consists of a three-winding coupling inductor. Therefore, in addition to the duty cycle, the voltage injected by the DVR can be controlled by the coupled inductor turn ratios. Unlike conventional impedance source converter-based DVRs, the proposed DVR is able to compensate for a wide range of voltage sag and swell, even voltage sags of more than 50%. The proposed DVR is analyzed in different compensation and protection modes and simulation results are presented in PSCAD/EMTDC software to validate the calculated relationships and performance. © 2025 IEEE.

关键词： Voltage-source converters

来源：评论

学校读者我要写书评

暂无评论

Physical Beam Sharing for Communications With Multiple Low Earth Orbit Satellites

引用

IEEE Transactions on Signal Processing 2024年 72卷 2783-2798页

作者： He, Yan-Yin Tsai, Shang-Ho Poor, H. Vincent Institute of Electrical and Control Engineering National Yang Ming Chiao Tung University Hsinchu300093 Taiwan National Yang Ming Chiao Tung University Department of Electronics and Electrical Engineering Hsinchu300093 Taiwan Princeton University Department of Electrical and Computer Engineering PrincetonNJ08544 United States

Physical (analog) beamforming is expected to become an important technique in Low Earth Orbit (LEO) satellite transmission in upcoming 6G communications. To build dense networks via LEO satellites and decrease deployment expenses, the corresponding satellites should have minimal hardware, low computational complexity, and limited power consumption. Additionally, issues such as different propagation delays, Doppler effects, long feedback delays, and serious attenuation caused by bad weather should also be addressed in LEO satellite communications. This work proposes a novel physical beam sharing scheme for multiple-satellite systems that enables a satellite to simultaneously serve multiple users using only one Radio-Frequency (RF) chain, consequently leading to a significant reduction in hardware complexity and power consumption. In this case, all users can achieve full multiplexing gain. Furthermore, we propose two ways of optimizing for this novel scheme. One is maximizing the throughput of all users, and the other is minimizing the LEO satellite system's power consumption. For the problems, we propose both solutions using instantaneous Channel State Information (iCSI) and long-term statistical Channel State Information (sCSI). Simulation results demonstrated that the proposals significantly outperform conventional schemes in terms of throughput and power consumption, and the performance of the proposed sCSI solutions is close to that of iCSI ones. © 1991-2012 IEEE.

关键词： Electric power utilization

来源：评论

学校读者我要写书评

暂无评论

FSIW Cavity-Based Self-Packaging Filtering Slot Antennas with Wide-Stopband and High Frequency Selectivity

引用

IEEE Transactions on Antennas and Propagation 2025年第6期73卷 3503-3516页

作者： Zhou, Xin Zhang, Gang Tam, Kam-Weng Pang, Ziyu Zhang, Zhuowei Lin, Huawei Hong, Jiasheng University of Macau Faculty of Science and Technology Department of Electrical and Computer Engineering China Nanjing Normal University School of Electrical and Automation Engineering Nanjing210046 China Nanjing Normal University Jiangsu Key Laboratory of 3D Printing Equipment and Manufacturing School of Electrical and Automation Engineering Nanjing210046 China Heriot-Watt University School of Engineering and Physical Sciences Department of Electrical Electronic and Computer Engineering EdinburghEH14 4AS United Kingdom

This article proposes a novel design approach for miniaturized, highly selective, self-packaged, and wide-stopband filtering slot antennas based on C- and T-type folded substrate integrated waveguide (C-/T-FSIW) cavities. Firstly, two forms of FSIW cavity are explored and analyzed. A new coupled C-type half-mode FSIW (C-HMFSIW) cavities are developed. A filtering antenna is proposed, employing a C-HMFSIW cavity for feeding and a slot-loaded C-FSIW cavity for radiation. By introducing cross-coupling between different resonators, a radiation null (RN) is achieved. To further enhance bandwidth and frequency selectivity, a new antenna configuration is developed using a C-HMFSIW cavity for feeding and a slot-loaded T-FSIW cavity for radiation. After loading the radiation slot, the T-FSIW cavity serves as two parts: one as the main radiator and the other as a parasitic radiator opposite to it. This configuration increases antenna bandwidth and generates an additional RN. Interestingly, adjusting the position of the radiation slot allows the RN to switch between the upper and lower stopbands. The antennas proposed in this work exhibit good stopband performance and compact size. Three filtering antenna prototypes are designed, fabricated, and measured, showing consistent results between measurements and simulations. © 1963-2012 IEEE.

关键词： Radiators

来源：评论

学校读者我要写书评

暂无评论

SUP: Security User Profiles for Behavioral Data Platforms

SUP: Security User Profiles for Behavioral Data Platforms

引用

2024 International Symposium on Networks, computers and Communications, ISNCC 2024

作者： Sulayman, Iman I. M. Abu Ouda, Abdelkader Western University Faculty of Engineering Department of Electrical and Computer Engineering LondonON Canada

ISBN: (纸本)9798350364910

Integrating user behavior across domains to create comprehensive profiles is crucial for system efficiency and security. This paper delves into the use of data analytics techniques to gather user data from various application domains, enabling the creation of security user profiles that contain data suitable for user authentication. Specifically, these methods are capable of identifying patterns in the users' data and then using said patterns to detect legitimate but anomalous activities performed by the users. Furthermore, we propose an innovative mechanism that dynamically integrates these profiles to create a comprehensive and global security profile for user authentication. Typically, each profile represents a distinctive entity detailing infrequent user behaviors that significantly impact identity verification. The verification process involves posing user challenge questions generated from these integrated profiles. The generated user profiles ensure the selection of questions that meet both security and usability requirements. We uphold security by issuing each question from the integrated user profiles only once, protecting user responses from potential compromise. We prioritize usability by using fresh data, which helps legitimate users recall and complete the challenge easily. © 2024 IEEE.

关键词： Behavioral data analytics Behavioral modeling Information security User profile

来源：评论

学校读者我要写书评

暂无评论

Implementation of Photovoltaic Power Maximization through Dynamic Power and Current control 12

Implementation of Photovoltaic Power Maximization through Dy...

引用

12th International electrical engineering Congress, iEECON 2024

作者： Jantharamin, Niphat Lousuwankun, Peeradech Naresuan University Faculty Of Engineering Department Of Electrical And Computer Engineering Phitsanulok Thailand

ISBN: (纸本)9798350383591

A novel approach to optimizing photovoltaic (PV) power through adaptive step size adjustments based on variations in PV module output power and current is introduced in this research paper. Utilizing the incremental conductance technique, the algorithm dynamically adjusts the duty cycle of a step-up converter, optimizing the operating point of a PV module toward the maximum power point (MPP). By eliminating the need for a multiplier and requiring no preceding knowledge of PV module output characteristics, this approach stands out for its efficiency. Hardware implementation and a comparison with a fixed step-size strategy demonstrated superior tracking speed (52% faster) and impeccable accuracy. The proposed method accelerates the maximum power point tracking (MPPT) process and also significantly enhances the overall performance of the PV system. The study presents a breakthrough promising a more responsive and precise system for optimizing PV power, showcasing potential advancements in renewable energy technology. © 2024 IEEE.

关键词： Solar panels

来源：评论

学校读者我要写书评

暂无评论

Trolleybus overhead line as a linear charger for battery-electric buses

eb - Elektrische Bahnen

引用

eb - Elektrische Bahnen 2024年第5期122卷 176-184页

作者： Bartlomiejczyk, Mikolaj Gdansk University of Technology Faculty of Electrical and Control Engineering Department of Electrical Transport ul. G. Narutowicza 11/12 Gdansk80-233 Poland

With increasing urbanization and growing pollution, electric buses are becoming a key element in the transformation of public transport. However, before this ecological trend becomes the norm, it is crucial to understand the challenges of its implementation. Electric buses require infrastructure for charging or operating. This has different efficiencies and environmental impacts. Furthermore, dynamic charging via the trolleybus network offers an economical alternative to other charging technologies as well as battery replacement. Electric buses have a perspective in electric public transport. © Georg Siemens Verlag GmbH & Co. KG.

关键词： Electric buses

来源：评论

学校读者我要写书评

暂无评论

Exploring Feature Map Correlations for Effective Fake Face Detection 11

Exploring Feature Map Correlations for Effective Fake Face D...

引用

11th International Symposium on Telecommunication, IST 2024

作者： Honarjoo, Narges Taher, Fatemeh Mansouri, Azadeh Kharazmi University Faculty of Engineering Department of Electrical and Computer Engineering Tehran Iran

ISBN: (纸本)9798350356250

In recent years, the internet and social media platforms have seen a massive influx of data, particularly images. To effectively identify fake content, we employ a deepfake detection technique aimed at determining the authenticity of uploaded material. In this paper, we achieve fake face detection with high accuracy by utilizing deep feature map relations. Our approach leverages transfer learning techniques from pretrained deep models, such as VGG16, VGG19, and ResNet50. We analyze the generated Gram Matrix of each layer, where deep feature relations are similar to the covariance matrix, reflecting correlations between different feature maps. These features are used to classify content as fake or real using a simple CNN, and the results are reported and compared. This study explores deep feature map relations as crucial indicators for detecting inconsistencies introduced by image generators. By employing pre-trained networks, we analyze and explore feature map relations generated in each layer as higher-order quality features. Experimental results demonstrate that the proposed inconsistency detection feature yields satisfactory results. The entire implementation of this work can be found at https: //***/hnarges91/Fake-Face-Detection. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Energy Management Strategy with a Hybrid Renewable Energy System for a Standalone House 16

Energy Management Strategy with a Hybrid Renewable Energy Sy...

引用

16th International Conference on Applied and Theoretical Electricity, ICATE 2024

作者： Mustata, Laurentiu-Alex Sorea, Gheorghe-Dan Helerea, Elena Transilvania University Electrical Engineering and Computer Science Faculty Electrical Engineering and Applied Physics Department Brasov Romania

ISBN: (纸本)9798350388107

In the case of standalone houses, ensuring a continuous and regulated power supply from renewable sources is crucial. To address their unpredictable nature, an environmentally conscious hybrid renewable energy system combining photovoltaic panels, a battery, and a Diesel generator is considered. A software application simulates the power flow in a standalone house with common AC loads, analysing summer and winter scenarios over 24 hours. The strategy employed provides an optimal energy management by using the Diesel generator only during peak demand when PV is available and to cover loads and maintain battery life when PV is not in operation. The simulation results provide valuable insights for designing such hybrid energy systems and for enhancing system responsiveness to dynamic energy demands. © 2024 IEEE.

关键词： Hybrid power

来源：评论

学校读者我要写书评

暂无评论

Anomaly-Focused Augmentation Method for Industrial Visual Inspection

引用

IEEE Access 2025年 13卷 89118-89139页

作者： Melvinlara, Melvin A. Hameed, Ibrahim A. Koziorek, Jiri Faculty of Electrical Engineering and Computer Science Department of Cybernetics and Biomedical Engineering Ostrava70800 Czech Republic Department of Mechanical Engineering and Technology Management Ås1433 Norway

In industrial inspection, the detection of surface defects - such as scratches, dents, or other defects - is crucial for ensuring product quality. However, the limited availability of annotated images of such defects poses challenges for developing reliable detection models. This paper proposes a novel image augmentation algorithm to address this limitation by generating synthetic imperfections from a small sample set. Unlike traditional approaches that augment entire images, the proposed approach isolates defects and applies spatial transformations (e.g., rotation, shear) before blending them into background images. This allows for the creation of diverse training datasets. The algorithm employs a 2D binary map to encode the spatial relationship between defect and background regions of images and then applies an AI-driven model to generate new realistic blended images. By leveraging a generator-discriminator framework, the augmentation process is iteratively refined during training to maintain the style and texture of the original imperfections. Experimental results show that the proposed method significantly enhances the performance of defect detection models compared to existing augmentation techniques while preserving the realism of the generated images. © 2013 IEEE.

关键词： Photointerpretation

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：