检索结果-内蒙古大学图书馆

International Conference on Guidance, Navigation and control, ICGNC 2022

作者： Nie, Ying Zhang, Yuan Bai, Wenyan Cao, Yuteng Yu, Chunmei Beijing Aerospace Automatic Control Institute Beijing100854 China National Key Laboratory of Science and Technology on Aerospace Intelligent Control Beijing100854 China

ISBN: (纸本)9789811966125

A reinforcement learning (RL) controller with identification of the dynamic parameter of hypersonic morphing flight vehicle (HMFV) is proposed in this paper, successfully realizing the end-to-end control of attack angle in the longitudinal plane. The following improvements are made in this paper: Firstly, the dynamic parameter (rudder efficiency coefficient) of the flight vehicle is added into the state vector, so that the RL controller can understand the control ability of the rudder and generates the optimal control commands in the current state. Secondly, five instead of only one consecutive attack angle deviations are used to jointly generate the state vector, which enables the RL controller to use the model state information of the previous period of time and improve the control stability. Three simulations are set up in this paper. The simulation results show that the RL controller proposed in this paper can achieve stable and high precision attack angle control under large-scale environmental deviations and has strong generalization under different guidance commands. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Feedback Generative Adversarial Network With Channel-space Attention for Image-Based Optimal Path Search Planning

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第8期5卷 4293-4307页

作者： Sun, Tao Li, Jian-Sheng Zhang, Yi-Fan Ru, Xin-Feng Wang, Ke Tsinghua University Department of Automation Beijing100084 China Dalian University of Technology School of Control Science and Engineering Dalian116024 China Dalian University of Technology Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Dalian116024 China Tongji University School of Economics and Management Shanghai200092 China

Path planning and seeking is one of the most challenging and interesting problems in the field of artificial intelligence. In this article, we propose a new image-based path planning algorithm to overcome traditional design concepts based on complex topological networks. Specifically, a novel feedback generative adversarial network learning model with channel-space attention (CSA-FGAN) is developed to search and plan an optimal path. It is worth noting that the input and output of the proposed feedback learning model are RGB images with complex spatial obstacle environment maps and RGB images with feasible paths, respectively. In particular, in order to further enhance the feature extraction ability and path prediction accuracy of image data, the feedback attention mechanism controls and improves the depth of the network by forming a closed loop of the proposed learning model. Final, three application scenario image examples are conducted to verify the superiority of the proposed path planning policy. © 2020 IEEE.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Generation of Sub-Nanosecond Microwave Pulse with High Compression Factor Using Reflection Structure

Generation of Sub-Nanosecond Microwave Pulse with High Compr...

引用

2024 Photonics and Electromagnetics Research Symposium, PIERS 2024

作者： Zhang, Zhiyuan Pan, Ruoyang Wang, Weijie Wu, Zhiqiang Liu, Guo Yao, Yelei Jiang, Wei Wu, Zeiwei Wang, Jianxun Luo, Yong School of Integrated Circuit Science and Engineering University of Electronic Science and Technology of China Chengdu China School of Electronic Science and Engineering University of Electronic Science and Technology of China Chengdu China Laboratory of Electromagnetic Space Cognition and Intelligent Control Beijing China

ISBN: (纸本)9798350375909

This paper presents a method of generating sub-nanosecond microwave pulses with a high compression factor using a reflection structure. This method can reduce the length of the compressor and has a high compression factor, which can further enhance the power level of broadband vacuum electron amplifiers. In the experiment, a microwave pulse with a duration of 0.257 ns and a high compression factor of 43.3 is generated. The experiment is in good agreement with our theory and simulation. © 2024 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Portrait Matting via Semantic and Detail Guidance 1

引用

7th Asian Conference on Pattern Recognition, ACPR 2023

作者： Wang, Deming Gao, Changxin Sang, Nong Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9783031476341

ISBN: (纸本)9783031476334

Portrait matting is a challenging computer vision task that aims to estimate the per-pixel opacity of the foreground human regions. To produce high-quality alpha mattes, the majority of available methods employ a user-supplied trimap as an auxiliary input. However, obtaining trimap is difficult, which restricts the application of these methods. Recently, trimap-free approaches have been developed, but the alpha quality is significantly lower than that of trimap-based methods due to the lack of guidance. In this paper, we propose a portrait matting framework via semantic and detail guidance. We use the mask obtained from portrait segmentation as semantic guidance to improve semantic understanding of portrait matting, and we present a detail encoder block to capture the low-level feature around the subject as detail guidance, which helps to refine alpha details, such as hair. The proposed approach achieves remarkable results on both composition and real-world benchmarks. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Adaptive modification of turbofan engine nonlinear model based on LSTM neural networks and hybrid optimization method

引用

Chinese Journal of Aeronautics 2022年第9期35卷 314-332页

作者： Yanhua MA Xian DU Ximing SUN School of Microelectronics Dalian University of TechnologyDalian 116024China Key Laboratory of Intelligent Control and Optimization for Industrial Equipment Ministry of EducationDalian University of TechnologyDalian 116024China School of Control Science and Engineering Dalian University of TechnologyDalian 116024China

An accurate and reliable turbofan engine model which can describe its dynamic behavior within the full flight envelop and lifecycle plays a critical role in performance optimization, controller design and fault diagnosis. However, due to the performance differences caused by the tolerance of engine manufacturing and assembly, and performance degradation during continuously stringent environmental regulations, the model accuracy is severely reduced. In this paper, an adaptive modification method of turbofan engine nonlinear Component-Llevel Model(CLM) based on Long Short-Term Memory(LSTM) Neural Network(NN) and hybrid optimization algorithm is pro-posed. First, a dynamic compensator with a combined LSTM NN architecture is constructed to compensate for the initial error between the experimental data and CLM of a turbofan engine under health condition. Then, a sensitivity analysis approach based on the entropy coefficient and technique for order preference by similarity to an ideal solution integrated evaluation is developed to choose the unmeasurable health parameters to be adjusted. Finally, a parallel hybrid optimization algorithm is developed to complete the adaptive model modification when the performance degrades. The proposed method is verified on a military low-bypass twin-spool turbofan engine, and the experimental results show the effectiveness of the proposed method.

关键词： Hybrid optimization Long short-term memory Model modification and testing Sensitivity analysis Turbofan engines

来源：评论

学校读者我要写书评

暂无评论

Robust Target Detection and Localization for UAV Autonomous Landing with Partially Occluded Targets 15th

Robust Target Detection and Localization for UAV Autonomous ...

引用

15th International Conference on Genetic and Evolutionary Computing, ICGEC 2023

作者： Shao, Mingmei Liu, Yanyan Tang, Jiaze Liu, Huanyu Li, Junbao Faculty of Computing Harbin Institute of Technology Harbin150080 China National Key Laboratory of Electromagnetic Space Security Tianjin300308 China Electrical Measurement Technology and Intelligent Control Institute School of Instrumentation Science and Engineering Harbin Institute of Technology Harbin150080 China

ISBN: (纸本)9789819700677

This paper presents an approach for robust target detection and localization in the context of UAV autonomous landing with partially occluded targets. Since the performance of the autonomous landing system largely depends on the accurate detection and positioning of the landing target, it is very important to deal with the local occlusion caused by obstacles or environmental factors. In order to improve the overall performance of the system, we propose a fault-tolerant target detection method and target completion strategy. The proposed target detection method combines image processing technology with feature extraction algorithm, which can recognize and locate the landing target even in the case of occlusion. The target completion strategy aims to recover the missing part of the occluded target and make the detection and location algorithm execute more reliably. We perform experiments on image data sets with different horizontal object occlusion to evaluate the performance of the proposed method. The results show that our method successfully detects and locates the landing target under different occlusion levels, and significantly improves the performance of UAV autonomous landing system in the real scene. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

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 to accelerate the design of sheet beam traveling wave tube depressed collector 16

A method to accelerate the design of sheet beam traveling wa...

引用

16th UK-Europe-China Workshop on Millimetre Waves and Terahertz Technologies, UCMMT 2023

作者： Jiang, Zhi Wang, Jianxun Wan, Yixin Jiang, Wei Li, Hao Luo, Yong University of Electronic Science and Technology of China School of Electronic Science and Engineering Chengdu China University of Electronic Science and Technology of China Laboratory of Electromagnetic Space Cognition and Intelligent Control Chengdu China

ISBN: (纸本)9798350339406

An efficient collector is one of the key factors in improving the overall efficiency of a sheet beam traveling wave tube(SB-TWT). In this paper, K-means algorithm is used to process the massive data of sheet electron beam (EB) after beam-wave interaction, so that a more representative and smaller amount of data is obtained. These data will be imported into the CST Tracking module for the quickly simulation design of the collector. The designed two-stage depressed collector is applied to a 6 kW continuous wave Ku-band SB-TWT with 26 kV Voltage and 1.3 A current. The collector efficiency is up to 80.79% with a backflow current of 0.13%. The overall efficiency of SB-TWT reaches about 52.9%. © 2023 IEEE.

关键词： Collector efficiency

来源：评论

学校读者我要写书评

暂无评论

GraphLoc: Enhancing Fingerprint-Based Localization With Graph Representation Learning

引用

IEEE Internet of Things Journal 2025年第12期12卷 21593-21603页

作者： Zhang, Lingyan Qiu, Yuanfeng Wu, Shaohua Zhang, Tingting Zhang, Qinyu Heilongjiang University School of Electronics Engineering Harbin China HongKong University of Science and Technology Thrust of Artificial Intelligence Guangzhou China School of Electronics and Information Engineering Shenzhen China Guangdong Provincial Key Laboratory of Space-Aerial Networking and Intelligent Sensing Shenzhen China

For 6G inherent intelligent capability, deeplearning-based wireless localization will become a promising technology for offering commercial location-based services (LBS). Classical deep neural networks (DNN) have been designed to learn feature representation for localization tasks. However, due to the uncertainty of radio measurements with complicated wireless propagation, the existing solution has achieved unsatisfactory performance with environmental dynamics. To address this issue, we propose GraphLoc, a novel approach to enhancing fingerprint-based localization with graph representation learning which can encode the structural information underlying radio fingerprints for robust localization. We first adopt graph signal processing of CSI fingerprints to create an unweighted graph. GraphLoc transforms the tasks of location estimations into node classification in a constructed graph. Then, we develop multilayer graph attention networks with the residual structure (Res-GAT) to learn graph representation by collecting the neighboring node features and aggregating their neighboring embeddings. Furthermore, in order to guarantee and speed up our Res-GAT convergence, we propose an appropriate training strategy to overcome training difficulty and overfitting for improving the quality of graph representations. Finally, extensive experimental results in many typical indoor scenarios demonstrate that the GraphLoc system can achieve better accuracy than other comparative schemes, even with the robustness of environmental dynamics, effectively facilitating fingerprint-based localization for fully practical LBS. © 2025 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Inverse synthetic aperture radar imaging based on a multiple norm constrained GOMP algorithm 24

Inverse synthetic aperture radar imaging based on a multiple...

引用

24th International Vacuum Electronics Conference, IVEC 2023

作者： Wang, Xin Yang, Jing Luo, Yong Li, Xiaoxue Qi, Jiabin University of Electronic Science and Technology of China Sichuan Chengdu611731 China Laboratory of Electromagnetic Space Cognition and Intelligent Control Beijing100089 China

ISBN: (纸本)9781665473217

In this paper, an inverse synthetic aperture radar imaging method based on multiple norm constrained generalized orthogonal matching pursuit (MNGOMP) algorithm is proposed to improve the imaging process of inverse synthetic aperture radar is prone to noise interference in compressed sensing environment. Orthogonal matching pursuit (OMP) and generalized orthogonal matching pursuit (GOMP) converge slowly in radar imaging and are susceptible to noise interference. Therefore, multiple norm constraints were introduced into the iteration update to improve convergence speed and accuracy and enhance noise resistance. The results show that this method is effective in suppressing unnecessary clutter and enhancing desired target. © 2023 IEEE.

关键词： Inverse synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

A Ku-band Compact High-power Sheet Beam Extended Interaction Oscillator 16

A Ku-band Compact High-power Sheet Beam Extended Interaction...

引用

16th UK-Europe-China Workshop on Millimetre Waves and Terahertz Technologies, UCMMT 2023

作者： Zhao, Wen Wang, Jianxun Li, Xinjie Jiang, Wei Li, Hao Luo, Yong University of Electronic Science and Technology of China School of Electronic Science and Engineering Chengdu China University of Electronic Science and Technology of China Laboratory of Electromagnetic Space Cognition and Intelligent Control Chengdu China

ISBN: (纸本)9798350339406

A compact sheet beam extended interaction oscillator (SBEIO) with frequency of 13.986 GHz is proposed in this paper. The model adopts a ladder structure with six gaps and operates in the TM11-2π mode. By optimizing the structure through the MATLAB program of the nonlinear theoretical simulation designed in our group, the efficiency is increased from 23.6% to 32.1%. The voltage and current of the electron beam are respectively 45 kV, 14 A. The current density remains at 50 A/cm2, which is suitable for the application of the periodic permanent magnet and beneficial for compact overall structure. The output power reaches 157 KW. © 2023 IEEE.

关键词： MATLAB

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：