检索结果-内蒙古大学图书馆

Flexible Inverse Design of Microwave Filter Customized on Demand With Wavelet Transform Deep Learning

IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 2025年第3期44卷 806-817页

作者： Xu, Kuiwen Wang, Jianguo Cai, Jialin Ma, Xuetiao Lv, Qinyi Chen, Shichang Liu, Jie Liu, Jun Hangzhou Dianzi University Innovation Center for Electronic Design Automation Technology The Key Laboratory of RF Circuits and Systems Ministry of Education Hangzhou310018 China Chang'an Campus Northwestern Polytechnical University School of Electronic Information Xi'an710060 China University of Electronic Science and Technology of China School of Electronic Science and Engineering Chengdu610054 China Information Science Academy China Electronics Technology Group Corporation Beijing100846 China

Artificial intelligence (AI) techniques are increasingly being used for the inverse design of microwave devices. However, several challenges, including intensive computation costs for training samples, high-dimensional data, nonuniformity, and low-quality samples in the design space, can negatively impact the final modeling performance. To alleviate these issues, a high-quality sampling inverse design scheme incorporating wavelet transform deep learning (HQS-WTDL) is proposed to achieve customized, automated microwave filter design. In the forward simulation-based sampling, particle swarm optimization (PSO) is used to tentatively select rule-defined samples. Multilabel synthetic minority over-sampling technique (MLSMOTE) is then applied to enlarge the training samples and improve their uniformity in the design space. An inverse modeling approach using neural networks to map the nonlinear relationship between a given set of S-parameters and required filter structural parameters is presented. Given that the dimension of the S-parameters is much higher than that of the structure parameters, the corresponding neural network used in this approach is deep and complex, with multiple layers and neurons. To reduce the number of input variables, the S-parameters are subjected to wavelet transformation, allowing for more efficient representation by the neural network. The proposed method is validated using a band-pass microstrip hairpin filter as an example. Results demonstrate that the proposed approach achieves better modeling effectiveness and inverse design efficiency than conventional methods. In addition, the proposed method allows for fast customization of device parameters, such as center frequencies and bandwidths with good prediction accuracy. © 1982-2012 IEEE.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Finite-Time Active Disturbance Rejection Control for Electromagnetic Formation Flight in Near-Earth Orbit 2nd

Finite-Time Active Disturbance Rejection Control for Electr...

引用

2nd International Conference on the Frontiers of Robotics and Software engineering, FRSE 2024

作者： Shen, Xixi Meng, Bin Hu, Jiangping Zhou, Qingrui School of Automation Engineering University of Electronic Science and Technology of China Chengdu611731 China Beijing Institute of Control Engineering Beijing100080 China University of Electronic Science and Technology of China Huzhou313000 China Qian Xuesen Laboratory of Space Technology China Academy of Space Technology Beijing100094 China

ISBN: (纸本)9789819631605

This paper investigates the position tracking control problem in electromagnetic satellite formation by utilizing the relative motion CW equation as the dynamic model. Firstly, a finite-time state feedback controller is derived using the adding a power integrator method, without considering external disturbances. This controller constitutes the feedback component of the composite controller. Subsequently, when the relative velocity of the system cannot be measured and is subject to external disturbances, a finite-time extended state observer is designed to estimate the relative velocity and disturbances of the system. The estimated disturbances serve as feedforward compensation, and the combination of the observer and the feedback control law achieves finite-time control without velocity measurements. Finally, it is proven that the proposed control law can achieve position tracking within a finite time. Numerical simulations at the end of the paper validate the theoretical analysis. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Disturbance rejection

来源：评论

学校读者我要写书评

暂无评论

Frequency-Spatial Complementation: Unified Channel-Specific Style Attack for Cross-Domain Few-Shot Learning

引用

IEEE Transactions on Image Processing 2025年 34卷 2242-2253页

作者： Ji, Zhong Wang, Zhilong Liu, Xiyao Yu, Yunlong Pang, Yanwei Han, Jungong Tianjin University School of Electrical and Information Engineering Tianjin Key Laboratory of Brain-Inspired Intelligence Technology Tianjin300072 China Shanghai Artificial Intelligence Laboratory Shanghai200232 China Shenyang Institute of Automation Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences State Key Laboratory of Robotics Shenyang110169 China Zhejiang University College of Information Science and Electronic Engineering Hangzhou310027 China Tsinghua University Department of Automation Beijing100084 China

Cross-Domain Few-Shot Learning (CD-FSL) addresses the challenges of recognizing targets with out-of-domain data when only a few instances are available. Many current CD-FSL approaches primarily focus on enhancing the generalization capabilities of models in spatial domain, which neglects the role of the frequency domain in domain generalization. To take advantage of frequency domain in processing global information, we propose a Frequency-Spatial Complementation (FSC) model, which combines frequency domain information with spatial domain information to learn domain-invariant information from attacked data style. Specifically, we design a Frequency and Spatial Fusion (FusionFS) module to enhance the ability of the model to capture style-related information. Besides, we propose two attack strategies, i.e., the Gradient-guided Unified Style Attack (GUSA) strategy and the Channel-specific Attack Intensity Calculation (CAIC) strategy, which conduct targeted attacks on different channels to provide more diversified style data during the training phase, especially in single-source domain scenarios where the source domain data style is homogeneous. Extensive experiments across eight target domains demonstrate that our method significantly improves the model’s performance under various styles. © 1992-2012 IEEE.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Research on thermal control elimination method of screening current of high-temperature superconducting magnets based on K-means clustering algorithm

引用

The European Physical Journal Special Topics 2025年 1-17页

作者： Ma, Zhirui Wang, Lei Li, Pengwei Liu, Shixian Wang, Qiuliang Department of Automation University of Science and Technology of China Hefei China Institute of Electrical Engineering Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

This paper proposes an improved heating elimination method to mitigate screening currents in high-temperature superconducting (HTS) magnets. To address the non-uniform target temperatures across different regions of the magnet during heating, a spatially non-uniform heating strategy is proposed to enhance its application in large and medium-sized magnets. First, an electromagnetic-thermal coupling model for HTS magnetic energy storage system is established, and the desired heating temperatures at key locations are back-calculated using the critical current formula of superconductors. The K-means algorithm is then employed to cluster the calculated temperature data, with the desired heating temperature as a one-dimensional feature. The clustering results are used to define heating zones and identify the temperature feedback points for each zone. Subsequently, fuzzy PID control is implemented based on the information from these temperature feedback points. Simulation results demonstrate that the combination of the K-means algorithm with fuzzy PID heating control can reduce the screening currents by 86.21%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Effect of X-Ray Irradiation on Properties of Insulating Materials

引用

IEEE Transactions on Plasma science 2025年第4期53卷 562-570页

作者： Zhang, Guobao Yang, Wei Huang, Weimin Wu, Zhengyang Zhang, Lei Yang, Xi Tong, Hui Zhang, Cheng State Grid Anhui Electric Power Company Limited Research Institute Hefei230601 China State Grid Anhui Electric Power Company Ltd. Hefei230061 China Hefei University of Technology School of Electrical Engineering and Automation Hefei230009 China Institute of Electrical Engineering Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing International S&T Cooperation Base for Plasma Science and Energy Conversion Beijing101408 China

X-ray digital imaging technology can be used for visualization and nondestructive detection of power equipment, which is widely used in defect determination and anomaly detection. However, when X-ray is used for defect detection of power equipment, it remains to be investigated whether X-ray irradiation will deteriorate the properties of insulating materials or not. In this study, four kinds of insulating materials that are commonly used in power equipment, including alumina (Al2O3), epoxy/alumina (EP/Al2O3) composite material, polyether ether ketone (PEEK), and polyimide (PI), are irradiated with high-penetration and high-dose X-rays. The effects of irradiation time and atmosphere on the properties of insulating materials were studied systematically. The results show that the crystalline structure of inorganic materials and the chemical structure of organic materials are basically unchanged after X-ray irradiation. In terms of insulation properties that include dielectric property, surface flashover voltage, surface potential decay, and volume resistivity, it turns out that the insulation performance of the insulating materials tends to deteriorate after X-ray irradiation, while the degree of degradation is extremely low. In addition, the results of surface potential decay of EP/Al2O3 show that the X-ray irradiation would accelerate the dissipation of surface charge, which is in favor of the safety of power insulation. © 1973-2012 IEEE.

关键词： Organic chemicals

来源：评论

学校读者我要写书评

暂无评论

Compact and aberration effects-shielded objective intraocular scatter measurement system

引用

Biomedical Optics Express 2025年第2期16卷 669-678页

作者： Zhao, Junlei Zhang, Zitao Yang, Yanrong Zhang, Haobo Chen, Hao Wang, Shengqian Dai, Yun Eye School Chengdu University of TCM No. 37 Twelve Bridge Road Sichuan Chengdu610075 China Key Laboratory of Sichuan Province Ophthalmopathy Prevention & Cure and Visual Function Protection with TCM No. 37 Twelve Bridge Road Sichuan Chengdu610075 China National Laboratory on Adaptive Optics Chengdu610209 China Institute of Optics and Electronics Chinese Academy of Sciences Chengdu610209 China University of Chinese Academy of Sciences Beijing100049 China School of Electronic Electrical and Commutation Engineering University of Chinese Academy of Science Beijing100049 China School of Automation Engineering University of Electronic Science and Technology of China Sichuan Chengdu611731 China

The measurement of the double-pass (DP) point spread function (PSF) provides an objective, non-invasive method for estimating intraocular scatter in the human eye. In this paper, we propose a compact double-pass objective intraocular scatter measurement system that eliminates the influence of aberrations. The system includes a far-field DP PSF detection channel and a Shack-Hartmann wavefront aberration detection channel, which are used to obtain the far-field DP PSF image and 7 orders Zernike aberration coefficients, respectively. The far-field DP PSF image is used to calculate the initial objective scatter index of the human eye. The aberration coefficients are used to reconstruct the DP PSF image caused by aberrations and calculate the influence coefficient of aberrations on intraocular scatter. By subtracting this influence coefficient from the initial objective scatter index (OSI0), the effect of aberrations on scatter measurement can be eliminated, resulting in an accurate objective scatter coefficient. Experimental verification showed that when the exit pupil aperture of this system was set to 4 mm and 6 mm, the measurement accuracy increased by at least 11.9% and 28.9%, respectively, compared to before eliminating the influence of aberrations. While improving the measurement accuracy, the system also keeps the device size and manufacturing costs at a low level, making it more suitable for clinical applications. © 2025 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement.

关键词： Aberrations

来源：评论

学校读者我要写书评

暂无评论

Co-Opetition Network-Based Group Decision-Making Under Incomplete Information

引用

IEEE Transactions on Systems, Man, and Cybernetics: Systems 2025年第5期55卷 3464-3479页

作者： Ma, Xiwen Hu, Zhihuan Duan, Kairong Ai, Xiaolin Xie, Wei Yang, Jingsong Zhang, Weidong Shanghai Jiao Tong University School of Oceanography Shanghai200030 China Second Institute of Oceanography Ministry of Natural Resources State Key Laboratory of Satellite Ocean Environment Dynamics Hangzhou310012 China Shanghai Jiao Tong University Department of Automation Shanghai200030 China Hainan University School of Information and Communication Engineering Hainan Haikou570228 China University of Science and Technology Beijing School of Computer and Communication Engineering Beijing100083 China Institute of Automation Chinese Academy of Sciences Beijing100190 China Zhuhai519082 China

The integration of cooperation and competition strategies in game theory emphasizes the systematic nature of strategy spaces and group interactions, forming the basis for achieving win-win scenarios. This is particularly crucial under coalition constraints and incomplete information. Addressing these challenges, this article introduces a comprehensive mathematical method for policy formation using co-opetition topological networks. This method enables autonomous decision-making and game equilibrium in group decision scenarios, considering individual preferences amidst constraints like incomplete information and alliance limitations. Leveraging the complementary entropy theorem on superiority, inferiority, and fuzzy measures, we propose a cognitive model for information interaction and attribute fusion. Utilizing the ordered weighted averaging operator and average tree solutions aids in identifying optimal alliance structures. We subsequently discuss evaluating missing information to complete the topological network. Updating the cognitive model and value function, we develop a Gaussian oscillation heuristic algorithm to explore alliance and component strategy spaces. Simulation results are provided and analyzed to illustrate the performance and effectiveness of our approach. © 2013 IEEE.

关键词： Network topology

来源：评论

学校读者我要写书评

暂无评论

Analysis of Reverse Voltage Distribution and Preliminary Design of Voltage Sharing for High-Frequency and High-Voltage Rectified Silicon Stack 11th

Analysis of Reverse Voltage Distribution and Preliminary Des...

引用

11th Frontier Academic Forum of Electrical engineering, FAFEE 2024

作者： Wang, Rixin Liang, Lizhen Wang, Longyang Tao, Jun School of Electrical Engineering and Automation Anhui University Anhui Hefei230601 China Institute of Plasma Physics Hefei Institutes of Physical Science Chinese Academy of Sciences Anhui Hefei230031 China Institute of Energy Hefei Comprehensive National Science Center Anhui Hefei230001 China

ISBN: (纸本)9789819788279

High-voltage rectifier silicon stack is a key component of DC high-voltage generation system, which is composed of many silicon rectifier diodes in series, and its internal reverse voltage sharing is the key technology in the development of high-voltage rectifier silicon stack. The phenomenon of uneven reverse voltage distribution of high-voltage rectifier silicon stack is the most prominent at the ends. Firstly, the equivalent circuit of high-voltage rectifier silicon stack in reverse operation is established, the distribution law and influencing factors of reverse voltage in high-voltage rectifier silicon stack are analyzed, and the voltage sharing principle of high-voltage rectifier silicon stack is expounded. Then the simulation model of voltage sharing design of high voltage rectifier silicon stack is established, the reverse voltage distributions of high-voltage rectifier silicon stack at power frequency and high frequency are studied under three kinds of equal parameter voltage sharing measures of capacitance voltage sharing, resistance voltage sharing and resistance-capacitance voltage sharing and unequal parameter voltage sharing measure of end voltage sharing, and the effects of these voltage sharing measures on the voltage non-uniform coefficient and reverse leakage current of high-voltage rectifier silicon stack are analyzed. Finally, based on simulation results, according to the working conditions of DC high-voltage rectifier silicon stack in DC high-voltage generation system of the project of 2.5 MV accelerator neutron source prototype, the voltage sharing design scheme of rectifier silicon stack with working frequency of 120 kHz and withstanding reverse voltage of 200 kV is designed preliminarily, and the configuration parameters of voltage sharing devices of high-frequency and high-voltage silicon stack are obtained, which lays a theoretical foundation for the development of high-frequency and high-voltage rectifier silicon stack. © Beijing Paike Cul

关键词： DC distribution systems

来源：评论

学校读者我要写书评

暂无评论

UNIP: RETHINKING PRE-TRAINED ATTENTION PATTERNS FOR INFRARED SEMANTIC SEGMENTATION

arXiv

引用

arXiv 2025年

作者： Zhang, Tao Wen, Jinyong Chen, Zhen Ding, Kun Xiang, Shiming Pan, Chunhong MAIS Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China School of Automation Science and Electrical Engineering Beihang University China

Pre-training techniques significantly enhance the performance of semantic segmentation tasks with limited training data. However, the efficacy under a large domain gap between pre-training (e.g. RGB) and fine-tuning (e.g. infrared) remains underexplored. In this study, we first benchmark the infrared semantic segmentation performance of various pre-training methods and reveal several phenomena distinct from the RGB domain. Next, our layerwise analysis of pre-trained attention maps uncovers that: (1) There are three typical attention patterns (local, hybrid, and global);(2) Pre-training tasks notably influence the pattern distribution across layers;(3) The hybrid pattern is crucial for semantic segmentation as it attends to both nearby and foreground elements;(4) The texture bias impedes model generalization in infrared tasks. Building on these insights, we propose UNIP, a UNified Infrared Pre-training framework, to enhance the pre-trained model performance. This framework uses the hybrid-attention distillation NMI-HAD as the pre-training target, a large-scale mixed dataset InfMix for pre-training, and a last-layer feature pyramid network LL-FPN for fine-tuning. Experimental results show that UNIP outperforms various pre-training methods by up to 13.5% in average mIoU on three infrared segmentation tasks, evaluated using fine-tuning and linear probing metrics. UNIP-S1 achieves performance on par with MAE-L while requiring only 1/10 of the computational cost. Furthermore, UNIP significantly surpasses state-of-the-art (SOTA) infrared or RGB segmentation methods and demonstrates broad potential for application in other modalities, such as RGB and depth. Our code is available at https://***/casiatao/UNIP. © 2025, CC BY.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Numerical simulation of HTS butterfly lens based on H- formulation

引用

The European Physical Journal Special Topics 2025年 1-20页

作者： Zhi, Tengfei Liu, Jianhua Chen, Yong Teng, Zhifan Liu, Shixian Ji, Xiaoyu Wang, Qiuliang Institute of Electrical Engineering Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Department of Automation University of Science and Technology of China Hefei China Ganiiang Innovation Academy Chinese Academy of Sciences Ganzhou China

As a novel passive magnetic field focusing device, the high-temperature superconducting (HTS) magnetic lens has great promise for various applications due to its compact structure and low losses. However, there is still insufficient experience in the material selection basis and operation control law for the magnetic lens. In this paper, a 2D finite element simulation model based on H- $${\Phi }$$ formulation is innovatively constructed, and the feasibility of the 2D finite element simulation model is proved by comparing it with the 3D simulation model and combining it with the experimental data of Z Y Zhang. Under the premise of guaranteeing calculation accuracy, calculation time is greatly reduced, which provides a new computational model for exploring the operation control law of the magnetic lens. In this paper, we innovatively take the critical current density characteristics of HTS bulks as an entry point to investigate the numerical relationship between the magnetic convergence characterization, magnetic remanet characterization of the magnetic lens, and the critical current density of the materials under different background magnetic field amplitude conditions. The research results show that: under different background magnetic field amplitudes, the steady-state convergence ratio increases with the increase of critical current density; the steady-state residual magnetism ratio increases first and then decreases with the increase of critical current density, and there is an extreme value. Therefore, this paper proposes reference critical current density based on the performance of the magnetic lens on magnetic fields focusing under different operating states, which provides a reasonable reference basis for the selection of magnetic lens materials and strong support for the development of the magnetic lens.

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：