检索结果-内蒙古大学图书馆

Content-decoupled Contrastive Learning-based Implicit Degradation Modeling for Blind Image Super-Resolution Supplementary Material

引用

IEEE Transactions on Image Processing 2025年 34卷 3013-3024页

作者： Yuan, Jiang Ma, Ji Wang, Bo Hu, Weiming North China Electric Power University School of Control and Computer Engineering Beijing102206 China CASIA State Key Laboratory of Multimodal Artificial Intelligence Systems Beijing100190 China University of Chinese Academy of Sciences School of Artificial Intelligence Beijing100049 China ShanghaiTech University School of Information Science and Technology Shanghai201210 China

Implicit degradation modeling-based blind super-resolution (SR) has attracted more increasing attention in the community due to its excellent generalization to complex degradation scenarios and wide application range. How to extract more discriminative degradation representations and fully adapt them to specific image features is the key to this task. In this paper, we propose a new Content-decoupled Contrastive Learning-based blind image super-resolution (CdCL) framework following the typical blind SR pipeline. This framework introduces negative-free contrastive learning technique for the first time to model the implicit degradation representation, in which a new cyclic shift sampling strategy is designed to ensure decoupling between content features and degradation features from the data perspective, thereby improving the purity and discriminability of the learned implicit degradation space. In addition, we propose a detail-aware implicit degradation adapting module that can better adapt degradation representations to specific LR features by enhancing the basic adaptation unit's perception of image details, significantly reducing the overall SR model complexity. Extensive experiments on synthetic and real data show that our method achieves highly competitive quantitative and qualitative results in various degradation settings while obviously reducing parameters and computational costs, validating the feasibility of designing practical and lightweight blind SR tools. Codes and models will be available at https://***/Fieldhunter/CdCL. © 1992-2012 IEEE.

关键词： Depression Anxiety disorders Face recognition Schizophrenia Visualization Training Data collection Uncertainty Facial features Emotion recognition

来源：评论

学校读者我要写书评

暂无评论

Large-signal Stability Analysis of Grid-forming Inverters with Equivalent-circuit Models

引用

IEEE Transactions on Energy Conversion 2025年

作者： Baeckeland, Nathan Pal, Diptak Seo, Gab-Su Johnson, Brian Dhople, Sairaj National Renewable Energy Laboratory Power Systems Engineering Center GoldenCO80401 United States Hitachi Energy Ltd United States University of Texas Chandra Family Department of Electrical and Computer Engineering AustinTX United States University of Minnesota Department of Electrical and Computer Engineering MN United States

This paper proposes an energy function-based direct method for large-signal stability assessment of grid-forming (GFM) inverters leveraging an equivalent-circuit representation of all involved control- and physical-layer dynamics. Three different primary controls, a standard inner-current outer-voltage cascaded-control architecture, output CL filter, and reference-current saturation limiting are featured in the modeling and analysis framework. A composite energy function for the GFM inverter is obtained by summing up individual energy contributions gleaned from the circuit representation. The approach can readily be generalized to different primary controls, output-filter arrangements, and current limiters since it is based on a circuit-theoretic foundation. Numerical simulations validate the efficacy of the approach in estimating the critical clearing time following a large-signal disturbance. © 1986-2012 IEEE.

关键词： Electric network analysis

来源：评论

学校读者我要写书评

暂无评论

A High Frequency Coupled Inductor with Distributed Air Gap for High power DC-DC Converters

A High Frequency Coupled Inductor with Distributed Air Gap f...

引用

Annual IEEE Conference on Applied power Electronics Conference and Exposition (APEC)

作者： Muhammad Fasih Uddin Ahmed H. Ismail Peyman Darvish Baher Abu Sba Yue Zhao Department of Electrical Engineering Power Electronic Systems Laboratory at Arkansas (PESLA) University of Arkansas Fayetteville AR USA

ISBN: (数字)9798331516116

ISBN: (纸本)9798331516123

In coupled inductor designs, minimizing AC resistance and achieving an optimal coupling coefficient are crucial for the performance of high frequency, high power DC-DC converters. The location and length of air gaps not only influence the loss profile but also affect the coupling coefficient, directly impacting the system’s performance. This article is focused on a coupled inductor design using custom planar ferrite blocks and distributed air gaps with 3D printed bobbins for mechanical stability. The proposed design achieves over 30% reduction in AC losses by reducing fringing effects and offers the flexibility to adjust the coupling coefficient, while ensuring a cost-effective and repeatable assembly process. System level advantages of the proposed method are verified using 2D FEM simulations. Finally, experimental results for a two-phase interleaved boost converter application have been presented in this paper to validate the effectiveness of the proposed inductor design.

关键词： Couplings Resistance Ferrites Atmospheric modeling Air gaps Windings DC-DC power converters Three-dimensional printing High frequency Inductors

来源：评论

学校读者我要写书评

暂无评论

A Self-Supervised Pre-Learning Method for Low Wind power Forecasting

引用

IEEE Transactions on Sustainable Energy 2025年

作者： Song, Weiye Yan, Jie Han, Shuang Zang, Ning Liu, Shihua Ge, Chang Liu, Yongqian North China Electric Power University State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources School of New Energy Beijing102206 China Tsinghua University State Key Laboratory of Power Systems Department of Electrical Engineering Beijing100084 China

As wind power is becoming a major energy source of power systems, the risk of power shortages due to its intermittent low power output is growing. Accurate forecasting of low wind power is crucial for mitigating these impacts. However, conventional methods struggle with few-sample issues due to the infrequent occurrence of low wind power, limiting accuracy improvements. To address this, a self-supervised pre-learning method is proposed to forecast low wind power occurrence period and output, leveraging the similarities and differences among low output samples to enhance forecasting accuracy. Low wind power output is decomposed into low wind power events (LWPE), which represent the occurrence timeframe, and low wind power processes (LWPP), which represent the power sequences. For LWPE forecasting, a siamese residual shrinkage network based on contrastive learning is introduced. This network pre-learns LWPE features from sample pairs to mitigate the impact of imbalanced sample distribution. For LWPP forecasting, a pattern recognition-based embedded forecasting framework is proposed, embedding typical LWPP fluctuations into the prediction network to improve fit under limited sample conditions. A case study on 3 wind farm clusters shows that this method improves LWPP forecasting accuracy from 84.99%-86.6% to 89.97%, outperforming traditional methods without pre-learning. © 2010-2012 IEEE.

关键词： Wind forecasting

来源：评论

学校读者我要写书评

暂无评论

Collision-Aware MPCC Integrated with Neural Augmentation for Quadrotor Trajectory Tracking

Collision-Aware MPCC Integrated with Neural Augmentation for...

引用

2025 IEEE International Conference on Mechatronics, ICM 2025

作者： Hu, Chuanqi Wang, Jin Chen, Yikai Chen, Yonghang Zheng, Zhi Meng, Jun Lu, Guodong Zhejiang University State Key Laboratory of Fluid Power and Mechatronic Systems Hangzhou310058 China Zhejiang University Zhejiang Key Laboratory of Industrial Big Data and Robot Intelligent Systems Hangzhou310058 China Robotics Research Center of Yuyao City Ningbo315400 China National Elite Institute of Engineering Chongqing University Chongqing401135 China School of Mechanical Engineering Zhejiang University Hangzhou310058 China College of Electrical Engineering Zhejiang University Hangzhou310027 China Center for Data Mining and Systems Biology College of Electrical Engineering Zhejiang University Hangzhou310027 China

ISBN: (纸本)9798331533892

This paper presents a trajectory tracking algorithm designed for autonomous quadrotors to navigate complex dy-namic environments that is resilient to collision disturbances. Since it combines Model Predictive Contouring Control (MPCC) with the capabilities of neural networks, our method is named MPCC Integrated with Neural Augmentation (MINA). By equip-ping the quadrotor with PVDF piezoelectric sensors, we achieve real-time perception of collision forces and utilize S4D-Conv Adaptive Net Architecture (SANA) for state computation, a network that integrates the advantages of S4D and convolutional kernels to enhance the accuracy of state predictions. We incorporate the predicted results into the MPCC framework to optimize the thrust output of the quadrotor for the next time step, ensuring precise trajectory tracking. Experimental validation demonstrates the reliability and effectiveness of our algorithm, providing an innovative solution for autonomous flight and trajectory tracking of quadrotors in complex dynamic environments. © 2025 IEEE.

关键词： Flight paths

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence Techniques With Digital Twin for Fault Diagnosis in Interconnected systems: A Review

引用

IEEE Access 2025年 13卷 91860-91874页

作者： Imen Nakti Majdi Mansouri Rami Al-Hmouz Atef Khedher Laboratory of Advanced Technology and Intelligent Systems ENISO University of Sousse Sousse Tunisia Department of Electrical and Computer Engineering College of Engineering Sultan Qaboos University Muscat Oman

As industrial systems become more complex and interconnected, diagnosing faults accurately and in real time has become increasingly challenging. This paper explores how combining artificial intelligence with digital twin technology can address these challenges. We focus on developing hybrid Artificial intelligence models that leverage diverse data sources to enhance fault detection and diagnosis, enabling secure and distributed diagnostics. Digital twins, virtual models of physical systems, are shown to enhance predictive maintenance and decision-making by providing real-time system insights. What sets our work apart is the way we integrate these technologies to create scalable, adaptive, and context-aware diagnostic solutions. We demonstrate the potential of this approach across applications such as smart grids, manufacturing, and autonomous systems. Our goal is to provide researchers and practitioners with a practical and forward-looking framework for developing intelligent, reliable fault diagnosis systems in today’s data-rich industrial environments.

关键词： Artificial intelligence Real-time systems Sensors Fault detection Fault diagnosis Interconnected systems Intelligent sensors Smart grids Digital twins Adaptation models

来源：评论

学校读者我要写书评

暂无评论

Electromagnetic Forces and Vibrations Under Stator and Rotor Reference Frames in Permanent Magnet Synchronous Machines

引用

IET Electric power Applications 2025年第1期19卷

作者： Yao, Lei Wang, Yunchong Cui, Rui-Zhen Qin, Xue-Fei Shi, Dan Shen, Jian-Xin College of Electrical Engineering Zhejiang University Hangzhou China Li Auto Inc. Shanghai China Zhejiang Provincial Key Laboratory of Electrical Machine Systems Hangzhou China State Laboratory of Fluid Power and Mechatronic Systems Hangzhou China

The electromagnetic force plays a significant role in contributing to torque ripple and electromagnetic vibration in permanent magnet synchronous machines (PMSMs), thereby impacting the noise, vibration, and harshness (NVH) performance. However, in most cases, existing design and analysis approaches predominantly focus on torque ripple, radial force and vibration under the stator reference frame, which is not sufficiently comprehensive. To address this gap, this paper presents the derivation of the spatial and temporal orders of force harmonics under both the stator stationary reference frame and the rotor rotating reference frame. Through theoretical analysis and finite element method (FEM) simulations, this paper highlights the differences in force harmonics and vibrations between the two reference frames. Furthermore, it explores the relationship between torque ripple and vibrations under different reference frames. Additionally, the superposition and cancellation effects of radial and tangential forces in producing vibrations are investigated. Finally, to validate the theoretical analysis, two prototypes of PMSMs with 6 poles and 9 slots have been manufactured and subjected to performance testing. © 2025 The Author(s). IET Electric power Applications published by John Wiley & Sons Ltd on behalf of The Institution of engineering and Technology.

关键词： Synchronous machinery

来源：评论

学校读者我要写书评

暂无评论

Experimental implementation of chaos-based video encryption using visible light communication technology

引用

Applied Optics 2025年第9期64卷 C101-C118页

作者： Fotso, Sorel Bagio Nono Mbé, Jimmi Hervé Talla Takotue, Jean Ernest Takougang, Armand Cyrille Nzeukou Ndjiongue, Alain Richard Research Unit of Condensed Matter Electronics and Signal Processing Department of Physics University of Dschang P.O. Box 67 Dschang Cameroon Research Unit of Automation and Applied Computer Department of Electrical Engineering IUT-FV Bandjoun University of Dschang P.O. Box: 134 Bandjoun Cameroon Laboratory of Industrial Systems and Environmental Engineering Fotso Victor University Institute of Technology University of Dschang P.O. Box 134 Bandjoun Cameroon School of Electrical and Information Engineering Faculty of Engineering and the Built Environment University of the Witwatersrand Johannesburg South Africa

Simulations are commonly used to develop and evaluate video encryption algorithms. Although these approaches are useful for demonstrating theoretical feasibility and algorithm performance, they neglect practical challenges and real-world communication conditions. This oversight creates a critical gap in evaluating their effectiveness and security in practical applications. In this paper, we describe a novel, to the best of our knowledge, video encryption scheme that employs a modified chaotic Colpitts oscillator, a customized Josephus problem, and ribonucleic acid (RNA) operations, and is implemented in visible light communication (VLC) environment. The modified Colpitts oscillator reveals significant phenomena, the most prominent for this study being chaos. The encryption scheme involves block scrambling and pixel-level permutation employing a customized Josephus problem and a column and row shifting technique. Diffusion is then achieved through a custom Josephus problem-oriented RNA operation combined with basic RNA operations and cipher block chaining (CBC). Based on the results, we found that the customized Josephus problem-based permutation performed more efficiently than traditional methods, whereas the column and row shifting permutation was more robust. By eliminating key sequence coding and item-to-item operations, the proposed RNA operation reduces computational overhead. This video encryption scheme is proven to be effective and resilient at securing video data transmitted over the VLC channel, and it constitutes a significant advancement in areas such as surveillance, medical imaging, and military communication requiring robust secured video data. © 2025 Optica Publishing Group. All rights, including for text and data mining (TDM), Artificial Intelligence (AI) training, and similar technologies, are reserved.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Understanding the Impact of Unobservable Variables on the Performance of Predictive Models: The Need for Feature Space Partitioning and Fusion

Understanding the Impact of Unobservable Variables on the Pe...

引用

AIAA Science and Technology Forum and Exposition, AIAA SciTech Forum 2025

作者： Juarez Garcia, Ezequiel Stephens, Chad L. Napoli, Nicholas J. Laboratory Department of Electrical and Computer Engineering University of Florida GainesvilleFL32611 United States Crew Systems & Aviation Operations Branch and System-Wide Safety Project NASA Langley Research Center HamptonVA23681 United States

ISBN: (数字)9781624107238

ISBN: (纸本)9781624107238

When developing predictive models over a dataset, the model is globally optimized across the entire feature space to learn a decision boundary. However, when unobservable variables—which cannot be measured or estimated—interact with the observable variables, this can negatively impact the optimization applied to the decision boundary since the data samples introduced by unobservable variables may have little to no association with the applied global optimization. This, consequently, penalizes the entire decision boundary and model performance. This paper examines some of the detrimental effects of unobservable variables, particularly their role in creating new modes in the distribution of observable variables and reducing the separ ability of class distributions. Such challenges result in unrepresentative training data, complex skewedor warped decision boundaries, and decreased accuracy of model predictions, particularly for interpretable models like logistic regression and decision trees. Through two illustrative case examples, we highlight the need to address the challenges imposed by unobservable variables. We propose a strategy to mitigate these challenges by creating local regions with in the feature space through partitioning. This enables the optimization of local models with inthe regions to overcome the impact of un observ ability and complex decision boundaries indifferent feature space localities. Research into a more sophisticated partitioning strategy and where the partition should be relative to the sample of interest is left as future work. Through the analysis of the impact of un observability and the development of a partitioning method, we demonstrate the clear need for a partitioning strategy that integrates knowledge from multiple local models to estimate risk factors using information fusion. Thus, we establish the foundation and motivation for using partitioning and information fusion to overcome the effects of unobserv ability in predictive mo

关键词： Information fusion

来源：评论

学校读者我要写书评

暂无评论

Quantifying and Optimizing the Time-Coupled Flexibilities at the Distribution-Level for TSO-DSO Coordination

引用

IEEE Transactions on power systems 2025年

作者： Wen, Yilin Guo, Yi Hu, Zechun Hug, Gabriela Tsinghua University Department of Electrical Engineering Beijing100084 China Urban Energy Systems Laboratory Dübendorf8600 Switzerland ETH Zürich Power Systems Laboratory Zürich8092 Switzerland

Distributed energy resources (DERs) in distribution systems offer substantial flexibility potential for power system operations, necessitating effective quantification and optimization methods for their utilization. This paper presents a unified timecoupled flexibility cost quantification approach that aligns with time-coupled flexibility models of various types of DER, whether individual or aggregated. The superior capability in accurately capturing the user inconvenience costs compared to traditional power-range-based, time-decoupled methods is demonstrated, thereby enhancing user willingness to provide flexibility to support the power system operation. Based on the quantification method, a DSO optimization model that activates DER flexibility for energy arbitrage and ancillary services provision in the transmission system while maintaining the distribution system's security and economic efficiency, i.e., TSO-DSO coordination, is developed. The optimization model introduces the concept of marginal flexibility prices (MFPs), which quantify the marginal contribution of flexibility in TSO-DSO coordination. Using MFPs for revenue allocation, incentive compatibility, revenue adequacy, and the non-profit status of DSO are guaranteed, enabling the proposed flexibility provision framework to operate sustainably. Numerical tests on the IEEE test system verify the proposed methods. © 1969-2012 IEEE.

关键词： Costs

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：