检索结果-内蒙古大学图书馆

PMD-Transformer: A Domain Generalization Approach for Person Re-Identification

IEEE Access 2025年 13卷 93178-93189页

作者： Xingguo Jiang Ling Yu Guojun Lin Yuchao Zhang School of Automation and Information Engineering Sichuan University of Science and Engineering Yibin China Intelligent Perception and Control Key Laboratory of Sichuan Province Yibin China

Domain generalization person re-identification (DG-ReID) aims to address the performance degradation caused by domain shift between the training domain and unseen target domains. Transformers often demonstrate better generalization ability than CNNs due to their self-attention mechanism and capacity for capturing global features. However, the supervised learning strategy on the source domain makes the Transformer-based ReID model inevitably overfit the bias in some regions. Therefore, a transformer model (PMD Transformer) for DG-ReID is proposed. First, by introducing relative position coding, it prevents the person image block from losing its relative position information when passing through the attention mechanism and improves the extraction of person features. Second, in order to solve the excessive attention of the model to the features of some regions and thus the overfitting phenomenon, the part mask attention (PMA) module is designed to limit the scope of the attention mechanism and improve the computational efficiency. Finally, a new feedforward network (DRFNN) is used to enhance the mastery of spatial information and further improve the generalization performance of the model. The experimental results show that, in the setting where Market is the source domain and Duke is the target domain, the average precision (mAP) and Rank-1 metrics increased by 12.5% and 9.2%, respectively, compared to the optimal algorithm. In the setting where Duke is the source domain and CUHK03-NP is the target domain, the mAP and Rank-1 metrics increased by 10.5% and 8.6%, respectively. The experiments demonstrate that the proposed model exhibits outstanding generalization ability in DG-ReID.

关键词： Adaptation models Transformers Data models Feature extraction Computational modeling Identification of persons Image coding Computer vision Robustness Training

来源：评论

学校读者我要写书评

暂无评论

Simulation Device of Subway Short-Circuit Current Based on Luenberger Observer 11th

Simulation Device of Subway Short-Circuit Current Based on L...

引用

11th Frontier Academic Forum of Electrical engineering, FAFEE 2024

作者： Zou, Jiajin Chen, Peng Wang, Chunjie School of Electrical Engineering and Automation Tianjin University of Technology Tianjin300382 China Tianjin Key Laboratory of New Energy Power Conversion Transmission and Intelligent Control Tianjin University of Technology Tianjin300382 China

ISBN: (纸本)9789819788194

With the rapid development of urban subway system in recent years, the failure of subway traction network has become a research hotspot. In order to ensure the reliability of the subway power supply, better study the fault characteristics, provide close to the real subway short circuit current, study the action characteristics of the subway high voltage DC circuit breaker under the fault current, design a simulation device based on phase shift full bridge that can generate the subway short circuit current, by controlling the amplitude, frequency, initial phase angle of the input waveform, so that the corresponding waveform can be generated. And it is verified by experiments. The experimental results show that the output has the characteristics of good dynamic response and small error. Considering that the sensor is affected by the interference noise such as the environment, the Luenberger observer is added to optimize the device control algorithm reasonably. © Beijing Paike Culture Commu. Co., Ltd. 2025.

关键词： Short circuit currents

来源：评论

学校读者我要写书评

暂无评论

Modeling and Simulation of Mixed Traffic Flow Considering Autonomous Vehicles and the Impact of Trucks 24

Modeling and Simulation of Mixed Traffic Flow Considering Au...

引用

4th Asia-Pacific Artificial Intelligence and Big Data Forum, AIBDF 2024

作者： Kuang, Xianyan Zhang, Zuliang Jiangxi Province Key Laboratory of Multidimensional Intelligent Perception and Control Jiangxi University of Science and Technology Jiangxi Ganzhou China School of Electrical Engineering and Automation Jiangxi University of Science and Technology Jiangxi Ganzhou China

ISBN: (纸本)9798400710865

Heavy trucks play a crucial role in shaping highway traffic dynamics. Their slower speed and unique acceleration and deceleration patterns can greatly influence the efficiency and stability of mixed traffic streams. This study explores a traffic scenario involving both heavy trucks and Connected and Autonomous Vehicles (CAVs), presenting an innovative model for mixed traffic flow and establishing specific lane-changing protocols for autonomous vehicles. Utilizing numerical simulations and comparative analyses, the research explores how heavy trucks affect traffic speed and lane-changing dynamics across different levels of CAV integration and varying traffic conditions. The findings of the study indicate that with lower rates of CAV penetration, increased traffic flow heightens the frequency of vehicle interactions, resulting in more pronounced variations in traffic speed. Conversely, when CAV penetration rates are elevated, there is a marked improvement in average traffic speed, alongside a significant reduction in speed fluctuations, particularly in high-density traffic situations. © 2024 Copyright held by the owner/author(s).

关键词： Automobiles

来源：评论

学校读者我要写书评

暂无评论

Simulition Study on Fatigue Life of Offshore Floating Photovoltaic DC Cable Across Floating Blocks

Simulition Study on Fatigue Life of Offshore Floating Photov...

引用

International Conference of Electrical, Electronic and Networked Energy Systems, EENES 2024

作者： Du, Xuehui Wang, Chunjie Chen, Peng Fu, Qiang School of Electrical Engineering and Automation Tianjin University of Technology Tianjin300384 China Tianjin Key Laboratory of New Energy Power Conversion Transmission and Intelligent Control Tianjin University of Technology Tianjin300384 China

ISBN: (纸本)9789819618675

In order to solve the fatigue problem of offshore floating photovoltaic direct current(DC) cable between floating blocks under the influence of wave motion, this paper proposes a method to evaluate the fatigue life of DC cable. On the basis of analyzing the fatigue damage mechanism of the DC cable, usingthe service life of the DC cable is accurately predicted by using the stress prediction method with the COMSOL finite element simulation software. By simulating stress conditions under different working conditions, the results show that: The fatigue life of DC cable across floating blocks is negatively correlated with the maximum equivalent stress, and the life decreases with the increase of displacement degree. The dangerous point of cable fatigue is near the fixed point at both ends of the cable. At the same time, the influence of different suspension lengths on the cable fatigue life is analyzed by simulation. The simulation results provide a useful design reference for optimizing cable layout and improving its service life. © Beijing Paike Culture Commu. Co., Ltd. 2025.

关键词： Fatigue damage

来源：评论

学校读者我要写书评

暂无评论

A Recurrent Neural Network Based Bicriteria Repetitive Motion Collision Avoidance Scheme for Motion Planning of Dual Redundant Manipulators 13

A Recurrent Neural Network Based Bicriteria Repetitive Motio...

引用

13th International Conference on Intelligent control and Information Processing, ICICIP 2025

作者： Chen, Shirui Gao, Huanli Hu, Shaolin Zhang, Zhijun The School of Automation Science and Engineering South China University of Technology Guangzhou510640 China The School of Automation Guangdong University of Petrochemical Technology Maoming Guangzhou525000 China The Guangzhou Key Laboratory of Brain-Computer Interaction and Applications Guangzhou China The Key Library of Autonomous Systems and Network Control Ministry of Education The School of Automation Science and Engineering South China University of Technology Guangzhou510640 China Guangzhou510555 China The Jiangxi Thousand Talents Plan Nanchang University Nanchang330031 China The College of Computer Science and Engineering Jishou University Jishou416000 China Guangzhou510335 China The Shaanxi Provincial Key Laboratory of Industrial Automation School of Mechanical Engineering Shaanxi University of Technology Hanzhong723001 China The School of Information Science and Engineering Changsha Normal University Changsha410100 China The School of Automation Science and Engineering Maoming525000 China The Institute of Artificial Intelligence and Automation Guangdong University of Petrochemical Technology Maoming525000 China

ISBN: (纸本)9798331516147

To achieve low joint-angle drift and avoid mutual collision between dual redundant manipulators (DRMs) when they are doing collaboration works, a recurrent neural network based bicriteria repetitive motion collision avoidance (BRMCA) scheme is proposed for motion planning of DRMs. By designing a combined optimization objective encompassing both repetitive motion criterion and collision avoidance criterion, the BRMCA scheme has larger feasible region and less constraint contradiction issues compared with traditional inequality constraints based method. Furthermore, by incorporating velocity-level kinematic model and physical limits of DRMs into the scheme, a time varying quadratic programming (TVQP) problem is formulated. The linear variational inequality-based primal–dual neural network (LVI-PDNN) is used to solve the proposed scheme due to the high accuracy and low computation complexity. Finally, through comparison simulations of tracking Circle-shape and C-shape trajectories between BRMCA scheme and minimum velocity norm (MVN) scheme, it exhibits that the proposed BRMCA scheme can achieve low joint-angle drift, collision avoidance and high tracking accuracy when DRMs are doing cooperative tasks. © 2025 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Adaptive Prescribed Finite-Time Bipartite Consensus control for Nonaffine Nonlinear MASs Under Structurally Unbalanced Topology

引用

IEEE Transactions on Systems, Man, and Cybernetics: Systems 2025年第5期55卷 3532-3541页

作者： Wang, Xiaomei Song, Yongduan Zhao, Xudong Wang, Huanqing Wang, Ding Niu, Ben Chongqing University School of Automation Chongqing400044 China Shandong Normal University School of Information Science and Engineering Shandong Jinan250014 China Dalian University of Technology School of Control Science and Engineering Liaoning Dalian116023 China Bohai University College of Mathematical Sciences Liaoning Jinzhou121013 China Beijing University of Technology Faculty of Information Technology Beijing100124 China Sichuan University School of Electrical Engineering Chengdu610065 China

This article investigates an adaptive bipartite consensus tracking control algorithm for a class of heterogeneous nonaffine nonlinear multiagent systems (MASs) with prescribed finite-time tracking performance under an unbalanced communication topology. In the case of an unbalanced digraph, a novel locally optimal bipartition strategy is proposed to transform the unbalanced communication topology into a structurally balanced one, thereby enabling the implementation of bipartite consensus tracking control. To achieve the expected tracking performance, the design philosophy focuses on developing a prescribed finite-time performance function (PFTPF), capable of preassigning the convergence time and accuracy precisely beforehand. The explored adaptive control algorithm can ensure that the whole signals concerning the closed-loop MASs remain bounded while the bipartite consensus errors converge to a predetermined range around zero within the prescribed finite time. Ultimately, the simulation results on robotic systems prove the availability of the developed design solution. © 2013 IEEE.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Brittle-plastic evolution mechanism and crack propagation behavior of fluormica glass-ceramics during scratching

引用

Ceramics International 2025年

作者： Li, Hongshuang Ma, Lianjie Li, Jinhao Jiang, Yinming Tang, Benjia Sun, Yang Tan, Yanqing Zhou, Yunguang School of Mechanical Engineering & Automation Northeastern University Shenyang110819 China School of Control Engineering Northeastern University at Qinhuangdao Qinhuangdao066004 China

The application of fluormica glass-ceramics in fields such as new energy, precision instruments, and aerospace necessitates stringent requirements for their ultra-precision manufacturing. However, the ambiguity surrounding the transition threshold between brittleness and toughness in fluormica glass-ceramics, coupled with the characteristics of crack propagation, poses significant challenges to the accuracy and efficiency of their manufacture. Therefore, an in-depth study of the brittle-ductile evolution, surface damage characteristics, and crack propagation behavior of fluormica glass-ceramics is crucial for enhancing its quality and manufacturing efficiency. This study employed the Smoothed particle hydrodynamics (SPH) and Finite element (FE) method to investigate the properties of fluormica glass-ceramics, further elucidating their brittle-ductile evolution mechanism and crack growth characteristics. As the scratching depth increases, a transition is observed from pure plastic removal to shear-crack removal, eventually leading to brittle removal. Reducing scratching depth and increasing scratching speed can effectively hinder crack propagation, facilitate the transformation of mixed-mode cracks into mode II cracks, and shift workpiece removal from tensile stress failure to shear failure. Scratch tests were conducted to delve into the impact of process parameters on brittle-ductile evolution, crack growth, and surface damage. The results verified the model. With increasing scratching depth, the layered tearing structure after scratching undergoes transitions from plastic removal to cracking and eventually complete brittle spallation. This study advances the understanding of surface damage and crack growth in fluormica glass-ceramics, providing valuable theoretical guidance for achieving high-quality and efficient material surface processing. © 2025

关键词： Glass ceramics

来源：评论

学校读者我要写书评

暂无评论

High-order Differential Feedback control and Quantitative Analysis for High-spinning Flight Vehicles

引用

IEEE Transactions on Aerospace and Electronic Systems 2025年

作者： Hu, Yuhui Liu, Yingxin Shen, Kai Zhang, Xinye Shi, Jingyu Beijing Institute of Technology School of Automation Beijing100081 China Beijing Institute of Control Engineering Beijing100190 China

High-spinning flight vehicles (HFVs) offer significant advantages for modern flight systems, including low cost and high-precision guidance. With the advancement of high-performance angular accelerometers, direct perception and feedback of angular acceleration have become a promising approach. In this paper, a two-loop acceleration autopilot with high-order feedback of angular acceleration (AFAA) is proposed to replace the traditional feedback of angular rate (AFAR). Both autopilots are synthesized via linear quadratic output feedback tracking (LQ OFT) approach with direct feedthrough component, incorporating frequency constraints. A hierarchical quantitative analysis framework including matrix pseudospectra-based robustness indices, degree of output controllability (DOC), null controllable region, and stability region, is developed to evaluate the performance of the proposed AFAA structure. Numerical simulations, accounting for sensor dynamics, are conducted to compare the frequency-domain characteristics and hierarchical quantitative parameters of HFVs with varying static stability properties. The results demonstrate the superiority of AFAA over AFAR and highlight the enhanced control performance achieved by static anti-stable HFVs. © 2025 IEEE.

关键词： controllability

来源：评论

学校读者我要写书评

暂无评论

Design and Analysis of a Resonant Current Regulator for Permanent Magnet Synchronous Motors 19th

Design and Analysis of a Resonant Current Regulator for Perm...

引用

19th Annual Conference of China Electrotechnical Society, ACCES 2024

作者： XiaoFeng, Chai Yang, Lei Qiang, Hao HaiTao, Yang Shuo, Ma China North Vehicle Research Institute Beijing100072 China School of Automation Beijing Institute of Technology Beijing100081 China School of Electrical and Control Engineering North China University of Technology Beijing100144 China

ISBN: (纸本)9789819613786

In a permanent magnet synchronous motor (PMSM) vector control system, a proportional-integral (PI) regulator is generally used for implementing closed-loop current control in the synchronous rotating coordinate system. In this algorithm, a rotating coordinate transformation is necessary for both stator current and reference voltage commands, resulting in relatively high computational complexity. With reference to the design principle of traditional PI current regulators, a reduced-order resonant current controller was developed in this study. This controller only involves a single-time rotating coordinate transformation of the reference current command, thus significantly reducing the computational workload. In addition, to facilitate the practical application, a gain-parameter analytical calculation formula applied in the design of the resonant current regulator is presented in this paper. Given accurate model parameters, the proposed resonant current regulator exhibits a dynamic performance similar to that of a traditional PI current regulator. In addition, with the presence of parameter errors, this resonant current regulator exhibits superior decoupling control performance. The effectiveness and feasibility of the proposed regulator have been verified with the simulation and experimental test results. © Beijing Paike Culture Commu. Co., Ltd. 2025.

关键词： Permanent magnets

来源：评论

学校读者我要写书评

暂无评论

Bearing fault diagnosis in gas turbine generators through MSP data-enhanced deep pyramidal residual networks

引用

International Journal of Data Science and Analytics 2025年 1-14页

作者： Xu, Xiaozhuo Li, Zhiyuan Zhao, Yunji Henan International Joint Laboratory of Direct Drive and Control of Intelligent Equipment School of Electrical Engineering & Automation Henan Polytechnic University Jiaozuo454003 China Henan Key Laboratory of Intelligent Detection and Control of Coal Mine Equipment School of Electrical Engineering & Automation Henan Polytechnic University Jiaozuo454003 China

Accurate diagnosis of bearing faults in gas turbines is essential to ensure the proper functioning of the system. However, the harsh operating conditions of gas turbines result in fault data characterized by high dimensionality, strong coupling and noise. In real-world scenarios, especially when faced with limited fault samples, traditional methods are hampered by these factors while striving for optimal diagnostic accuracy. Furthermore, simply increasing the network depth to improve decoupling capabilities can lead to the disappearance or explosion of gradients in deeper network layers. To overcome these challenges, this study proposes a method that combines MSP data enhancement for preprocessing with pyramidal bottleneck residual networks for fault diagnosis. Specifically, the method uses mix-up and random scaling to augment the data, followed by principal component analysis to extract the principal components. The augmented samples are then fed into pyramidal bottleneck residual networks for training. Primarily, the method enhances defect features through preprocessing, allowing the model to establish smoother decision boundaries and improved generalization within the constraints of limited samples. Subsequently, the specialized structure of the pyramidal bottleneck residual networks enhances decoupling capabilities and reduces computational complexity. The effectiveness and superiority of the proposed method are demonstrated through algorithm validation on the CWRU and XJTU public datasets, together with practical engineering verification using BaiChuan gas turbine bearing monitoring data. The method is shown to have high practical value. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： Principal component analysis

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：