检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Wang, Cheng Cheng Zheng, Ziheng Luo, Xinlei Hou, Bingxue Liu, Bo Jia, Lichao Xie, Xianpan Luo, Dawei Shen Zhen Polytechnic University Shenzhen518055 China Aviation Engineering Institute Civil Aviation Flight University of China Guanghan618037 China Center for Fuel Cell Innovation State Key Laboratory of Material Processing and Die & Mould Technology School of Materials Science and Engineering Huazhong University of Science & Technology Wuhan430074 China

To attain superior electrochemical performance, a new series of high-entropy double perovskites are investigated as cathodes for solid oxide fuel cells. In this study, three kinds of LaBa0.5Sr0.5Co1.5Fe0.5O5+δ(LPBSCF) double perovskites with different dopings of La, Pr, Sm, Gd, Nd, Y elements in A-site, high-entropy double perovskites (HEDP) cathodes are successfully prepared by a EDTA-citrate combustion method and used as potential cathodes for SOFC at intermediate temperature. Three HEDP cathodes all form single phase perovskite structure and matches chemically well with Gd0.2Ce0.8O2-δ(GDC) electrolyte. The linear thermal expansion coefficient in the RT-900 °C range is found to be moderate, 18.39×10-6 *** anode supported SOFC with (La0.2Pr0.2Sm0.2Gd0.2Nd0.2)Ba0.5Sr0.5Co1.5Fe0.5O5(LPSGNBSCF)-HEDP cathode exhibits an excellent output performance of 1000 mW·cm-2 with a lower polarization resistance of 0.3 Ω·cm2 at 800 °C. These results might suggest that HEDP-LPSGNBSCF can be a potential excellent cathode for SOFCs. © 2023, The Authors. All rights reserved.

关键词： Cathodes

来源：评论

学校读者我要写书评

暂无评论

Helicopter Rotor Fault Diagnosis Based on IPSO and RVM

Helicopter Rotor Fault Diagnosis Based on IPSO and RVM

引用

Prognostics and System Health Management Conference (PHM-Qingdao)

作者： Xiaoyi Si Liang Zheng Guo Zheng Jinglin Wang Zhenping Zhao Ziang Guo School of Electronic Information Hangzhou Dianzi University Hangzhou China Aviation Key Laboratory of Science and Technology on Fault Diagnosis and Health Management Shanghai Institute of Aerospace Control Engineering Shangai China

To address the issue of low accuracy in traditional rotor fault diagnosis during the helicopter rotor fault diagnosis process, this paper presents a fault diagnosis method based on the Improved Particle Swarm Optimization (IPSO) algorithm for Relevance Vector Machine (RVM). The fitness function of the IPSO algorithm is defined as the mean squared error between the predicted classification results obtained through cross-validation and the actual classification. The IPSO algorithm is used to search for the optimal width factor of the RVM kernel function and establish the fault diagnosis model. Through simulation experiments and comparisons with Particle Swarm Optimization (PSO) algorithm-based RVM and Improved Particle Swarm Optimization-based Support Vector Machine (SVM), it is demonstrated that this approach, compared to traditional rotor fault diagnosis methods, effectively improves the accuracy of fault recognition.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Investigation of Friction and Vibration Performance of Lithium Complex Grease Containing Candle Soot on aviation Electrical Machine

SSRN

引用

SSRN 2024年

作者： Li, Kangshuai Zhang, Yanbin Tan, Wenkai Wang, Jiwen Xu, Zehua Li, Zhanjun He, Qiang School of Mechatronics Engineering Henan University of Science and Technology Henan Luoyang471003 China College of Civil Aviation Safety Engineering Civil Aviation Flight University of China Sichuan Guanghan618307 China Civil Aircraft Fire Science and Safety Engineering Key Laboratory of Sichuan Province Guanghan618307 China Sichuan Key Technology Engineering Research Center for All-electric Navigable Aircraft Sichuan Guanghan618307 China Anyang Institute of Technology Anyang455000 China

Abstract: The prolonged operation of the motor in the all-electric aircraft can cause the fragmentation and shortening of grease thickener fibers, ultimately resulting in the lubricating grease becoming ineffective. In order to avoid grease failure causing motor winding burnout, this paper uses a four-ball friction testing machine to test the tribological properties of six composite greases containing candle soot with different concentrations, and analyzes the changes in friction coefficient and wear diameter. In addition, by building a test platform for motor vibration and noise, this paper studies the influence of lithium complex grease on vibration and noise characteristics of aviation electrical machine at different propeller speeds. The results show that the addition of 0.04wt% candle soot lithium grease has the best tribological properties and vibration inhibition properties, because the candle soot in the oil film changes the sliding friction into rolling friction in the contact area of some friction pair. The temperature rise test of aviation electrical machine shows that the compound lithium grease plays an active role in the heat dissipation performance of the high speed rotating motor. © 2024, The Authors. All rights reserved.

关键词： Wear of materials

来源：评论

学校读者我要写书评

暂无评论

Research on Reward Distribution Mechanism Based on Temporal Attention in Episodic Multi-Agent Reinforcement Learning

Research on Reward Distribution Mechanism Based on Temporal ...

引用

Artificial Intelligence technology (ACAIT), Asian Conference on

作者： Baofu Fang Mingkuan Cao Zaijun Wang Hao Wang School of Computer Science and Information Engineering (Hefei University of Technology) Intelligent Interconnected Systems Laboratory of Anhui Province (Hefei University of Technology) Hefei China Key Laboratory of Flight Techniques and Flight Safety (Civil Aviation Flight University of China) Guanghan China

In episodic multi-agent reinforcement learning, we study how to distribute episodic rewards at the end of an episode by trajectory time steps to obtain high-quality and interpretable learning reward signals to guide agent training. This paper proposes a reward distribution method based on temporal attention. This method is used to characterize the influence of actions on state transitions along the trajectory, and the effect of each influence on the global reward at each time step. This method is combined with a deep deterministic strategy, and a multi-agent algorithm based on the temporal attention reward distribution mechanism is proposed to speed up the convergence speed of the agent. The effectiveness of the algorithm is verified in a multi-agent pursuit environment. Compared with other reward distribution methods, the method in this paper converges faster and obtains higher rewards.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Analysis of the Texture Evolution During Multipass Tube Spinning of a Ta15 Alloy Using the Crystal Plasticity Finite Element Model

SSRN

引用

SSRN 2023年

作者： Wang, Xianxian Wu, Wenhao Zhan, Mei Zheng, Zebang Li, Zhixin Liu, Tao School of Mechanical and Electrical Engineering Shaanxi University of Science and Technology Xi’an710021 China Shaanxi Key Laboratory of High-Performance Precision Forming Technology and Equipment State Key Laboratory of Solidification Processing School of Materials Science and Engineering Northwestern Polytechnical University Xi’an710072 China School of Science Civil Aviation Flight University of China Guanghan618307 China

In this study, we present an explicit crystal plasticity finite element model (CPFEM) to investigate the texture evolution during multipass tube spinning of a TA15 alloy. The texture formation mechanism is further revealed by analyzing grain rotation and slip behaviors. The results indicate that, for the grains whose c-axis are far from the normal direction (ND), basal slip is dominant under the significant compression deformation state of spinning. Therefore, the c-axis gradually turns toward the ND. However, for the grains whose c-axis are close to ND, the contribution ratios of prism , pyramidal and pyramidal increase, especially that of prism . Under these conditions, the c-axis deviates slightly from the ND, and grains mainly rotate around the c-axis. Therefore, most of the {0001} poles cluster around the ND and {10-10} poles are distributed in the rolling-hoop plane, exhibiting an obvious basal texture component. These results imply that the CPFEM can effectively predict the formation of basal texture component during spinning. With an increase in the number of spinning pass, the texture distribution becomes slightly inhomogeneous along the ND owing to the uneven distribution of macroscopic strain. In addition, the grain rotation first increases and then decreases with deformation. The smaller grain rotation at the first pass is because a large number of basal preferentially operates in the grain with favorable orientation, resulting in localized inhomogeneous deformation. The decrease at larger deformation is due to the lower Schmidt factor of basal , which limits the grain rotation. © 2023, The Authors. All rights reserved.

关键词： Prisms

来源：评论

学校读者我要写书评

暂无评论

Pseudo-Augmentation Entropy Domain Adaptation for Video Unsupervised Action Recognition

Pseudo-Augmentation Entropy Domain Adaptation for Video Unsu...

引用

Chinese Automation Congress (CAC)

作者： Zhi Chen Haibin Huang Yufei Zhuang Shuhua Liu Zhetao Zhong Hao Shu School of Information Science and Engineering Harbin Institute of Technology Weihai Weihai China Weihai Key Laboratory of Autonomous Control and Cooperation Technology for Unmanned Marine Systems Weihai Skysailing Technology Co. Ltd. Weihai China Weihai Huamei Aviation Technology Co. Ltd Weihai China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

This research tackles the challenge of video unsupervised domain adaptation (VUDA) in human action recognition, focusing on deploying models trained in well-lit conditions to poorly-lit environments. Current unsupervised domain adaptation (UDA) techniques mitigate performance degradation by aligning source and target domains through adversarial training. However, these approaches fail to enhance low-light images, resulting in information loss and suboptimal performance in dark settings. To address this issue, we introduce Pseudo-Augmentation Entropy Domain Adaptation (PANDA), an entropy theory-based method that simultaneously complements unsupervised adversarial alignment by incorporating image enhancement as an auxiliary task. Evaluations on the HMDB-ARID datasets demonstrate that proposed PANDA outperforms standard VUDA baselines, boosting action recognition accuracy by an average of 6.3%.

关键词： Training Performance evaluation Adaptation models Accuracy Computational modeling Focusing Entropy Human activity recognition Standards Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Numerical simulation and experimental research on Taylor Couette flow characteristics in air gap of aviation motor

Numerical simulation and experimental research on Taylor Cou...

引用

CSAA/IET International Conference on Aircraft Utility Systems (AUS 2024)

作者： Hui Ma Shuyue Liang Hongbo Zhan Lin Qi Weijian Chen Aviation Key Laboratory of Science and Technology on Aero Electromechanical System Integration No.33 Shuige Road Nanjing People's Republic of China Key Laboratory of Aircraft Environment Control and Life Support MIIT Nanjing University of Areonautics and Astronautics No.29 Yudao Street Nanjing People's Republic of China

ISBN: (数字)9781837242108

A test bench with PIV technology was built and visualization research on Taylor vortex between concentric rotating cylinders was carried out to explore the flow morphology within the annular gap by changing the rotational speed of the inner cylinder. The numerical method and accuracy were verified by experiments. The selected turbulence model was then applied for numerical simulation of the Taylor Couette flow in a simplified air gap model of an aviation motor with smooth inner and outer walls. The Taylor Couette flow characteristics in the air gap under varying rotational speed were studied, and simulation results were given for flow with axial flow and without axial flow.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Functional Connectivity Network Augmentation with Patch-entirety Self-attention GAN for ADHD Identification

引用

IEEE Transactions on Instrumentation and Measurement 2025年 74卷

作者： Pei, Shengbing Jiang, Wencong Cao, Shuai Fan, Cunhang Liang, Wen Lv, Zhao Guan, Jihong Zhang, Chao Anhui University Anhui Province Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Hefei230601 China Anhui University Institutes of Physical Science and Information Technology Hefei230601 China Google Company Mountain View94043 United States Civil Aviation Flight University of China Guanghan618307 China Tongji University Department of Computer Science and Technology Shanghai201800 China

Functional connectivity network (FCN) describes the cooperative state of the brain and is often used to identify neurological diseases. However, the performance of FCN-based recognition models is limited by small sample size for the high cost of patient data acquisition and labeling. Generative adversarial networks (GAN) can generate diverse samples to alleviate this problem. Due to the symmetry of FCN matrix, existing GAN-based data augmentation methods mainly adopt fully connected layers to learn flattened FCN data distribution, neglecting the functional collaboration structure within FCN. Here, we propose a novel patch-entirety self-attention GAN (PEGAN) for FCN data augmentation, thereby helping to improve brain disorder identification. PEGAN is a fully convolutional structure, and contains a two-stage attention mechanism to learn the collaboration of brain regions, at the first stage, the FCN is partitioned into multiple patches, each patch is encoded by itself with self-attention, this is to learn local consistency characteristic within a specific brain sub-function;at the second stage, the global self-attention involving all functional connections is performed, this is to learn the global collaborative characteristic of the entire brain. Meanwhile, a symmetry constraint is designed in the optimization objective of GAN to overcome the issue that the convolutional GAN model is not applicable to FCN data. With the sufficient augmentation data, a dual-stream network is trained for classification. Experimental results on ADHD-200 dataset indicates that 1) the proposed identification method with PEGAN demonstrates its superiority by comparing with existing ADHD identification methods;2) the improved optimization objective function effectively solves the problem that FCN data is not suitable for convolution processing;3) the reliability of the generated FCN data with PEGAN is verified from both qualitative and quantitative perspectives;4) the augmented FCN data can

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

A Direct Anti-high Repetition Jamming Design Method via The Minimum Interval Period Optimization

A Direct Anti-high Repetition Jamming Design Method via The ...

引用

Chinese control and Decision Conference, CCDC

作者： Jingjing Qiang Hui Liu Xiongjun Wu Yingbo Li Peipei Cao The Eighth Academy of China Aerospace Science and Technology Corporation The 802 Institute of Shanghai Academy of Space Flight Technology Shanghai China Department of Automation Ministry of Education of China Shanghai Jiao Tong University and Key Laboratory of System Control and Information Processing Shanghai China

ISBN: (数字)9798350387780

ISBN: (纸本)9798350387797

Semi-active laser detection is used extensively on many kinds of high-precision guidance weapon systems in the varied military fields. Although it is of high detection accuracy, this kind of detection mechanism, on the other hand, suffers from various laser interference modes which are added in view of the semi-active laser detection principle, covering from angle deception interference, synchronous forwarding interference, and high repetition frequency interference, etc. As a consequence, the overall performance is reduced accordingly. Among these types of deception interference, the high repetition frequency interference is the most effective one. In this work, to overcome this specific type of interference, a minimum interval period method (MIPM) is proposed to remove high repetition frequency interference and improve the detection accuracy of the laser semi-active guidance system. Numerical experiments validate that, this method is able to achieve good performance testing on the Semi-active laser detection under high repetition frequency interference via the False Alarm Probability (FAP for short) and Missed Alarm Probability (MAP).

关键词： Laser theory Accuracy Weapons Interference Resists Logic gates Laser modes

来源：评论

学校读者我要写书评

暂无评论

A Cross-Task Transfer SAR Target Recognition Method Based on AMFFNet and IACGAN

引用

IEEE Transactions on Aerospace and Electronic Systems 2025年

作者： Wan, Xunyang Du, Xiaolin Cui, Guolong Chen, Xiaolong Zheng, Jibin Yantai University School of Computer and Control Engineering Yantai264005 China University of Electronic Science and Technology of China School of Information and Communication Engineering Chengdu611731 China Naval Aviation University Yantai264001 China Xidian University National Key Laboratory of Radar Signal Processing Xi'an710071 China

Convolutional neural networks (CNN) have shown excellent capability in synthetic aperture radar (SAR) target recognition. However, obtaining sufficient training samples for improving network recognition is difficult due to the deficiency of labeled SAR image data. To tackle the problem, a cross-task transfer method for SAR target recognition is proposed in this paper, which is based on a designed attention multi-scale feature fusion network (AMFFNet) and an improved auxiliary classifier generative adversarial network (IACGAN). In this method, firstly, a data augmentation method based on you only cut twice (YOCT) is devised for expanding the training samples. Secondly, the partial weight parameters of AMFFNet are initialized by the pre-trained IACGAN discriminator. Finally, AMFFNet is fine-tuned using the training samples. Additionally, on the network structure of AMFFNet, multi-scale features are extracted by adopting a multi-scale depth separable convolution module, which allows the model to acquire more informative features. Attention mechanisms are employed in this network to enhance its ability to capture important features while reducing the effects of noise. A multi-level feature fusion structure is used to further raise the representational capability of the model. Experimental results on multiple open-source real SAR datasets show that the proposed method can achieve better recognition performance under different percentages of training data, and the effectiveness and superiority of the method are confirmed by its robustness to noise. © 1965-2011 IEEE.

关键词： Convolutional neural networks

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：