检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Yang, Zhipeng Wang, Ruoyu Tan, Yang Xie, Liping The Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education School of Automation Southeast University Nanjing210096 China Southeast University Shenzhen Research Institute Shenzhen518063 China

Online action detection (OAD) aims to identify ongoing actions from streaming video in real-time, without access to future frames. Since these actions manifest at varying scales of granularity, ranging from coarse to fine, projecting an entire set of action frames to a single latent encoding may result in a lack of local information, necessitating the acquisition of action features across multiple scales. In this paper, we propose a multi-scale action learning transformer (MALT), which includes a novel recurrent decoder (used for feature fusion) that includes fewer parameters and can be trained more efficiently. A hierarchical encoder with multiple encoding branches is further proposed to capture multi-scale action features. The output from the preceding branch is then incrementally input to the subsequent branch as part of a cross-attention calculation. In this way, output features transition from coarse to fine as the branches deepen. We also introduce an explicit frame scoring mechanism employing sparse attention, which filters irrelevant frames more efficiently, without requiring an additional network. The proposed method achieved state-of-the-art performance on two benchmark datasets (THUMOS’14 and TVSeries), outperforming all existing models used for comparison, with an mAP of 0.2% for THUMOS’14 and an mcAP of 0.1% for TVseries. Copyright © 2024, The Authors. All rights reserved.

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

Broadband Vibration Reduction of Cylindrical Shell Structures with Circumferential Taper Resonators

SSRN

引用

SSRN 2024年

作者： Zhang, Sen Ding, Liangzhu Wu, Xinwei Ma, Yongbin Deng, Zichen School of Mechanics Civil Engineering and Architecture Northwestern Polytechnical University Xi'An710072 China MIIT Key Laboratory of Dynamics and Control of Complex Systems Northwestern Polytechnical University Xi'An710072 China

In this study, a resonator with circumferential taper was proposed to achieve broadband vibration reduction of the circular cylindrical shell. The structural damping characteristics and vibration response of the circular cylindrical shell structure with circumferential taper resonators were conducted by an analytical wave propagation model developed based on the symplectic method. The taper resonator was segmented uniformly by using the Gaussian discretization method based on power law, which can accurately and efficiently handle the non-uniform characteristics of the taper resonator and the amplitude of each uniform segment was evaluated by using the analytical wave propagation model. In numerical examples, the accuracy and effectiveness of the homogenization approximation of the analytical model were validated by the finite element method. Meanwhile, the forced vibration response and damping properties of the circular cylindrical shell structure with uniform and taper resonators and with various boundary conditions were also investigated. The results showed that compared with uniform resonator, the taper resonator provided much larger damping, which its special damping capacity can even reach about 6 times of the uniform resonator. Therefore, even if the length of the taper resonator was relatively small, significant broadband vibration suppression in the primary circular cylindrical shell can also be achieved. In addition, under any boundary condition, the same parameters taper resonator can achieve broadband vibration reduction effects on circular cylindrical shell, and the distance between the excitation source and the position of the resonator can affect the vibration attenuation effect of the circular cylindrical shell. © 2024, The Authors. All rights reserved.

关键词： Resonators

来源：评论

学校读者我要写书评

暂无评论

Vibration and Acoustic Radiation Suppression of Multi-Layer Composite Sandwich Plates with Imperfect Acoustic Black Hole

SSRN

引用

SSRN 2024年

作者： Zhang, Sen Wu, Xinwei Ding, Liangzhu Ma, Yongbin Deng, Zichen School of Mechanics Civil Engineering and Architecture Northwestern Polytechnical University Xi'An710072 China MIIT Key Laboratory of Dynamics and Control of Complex Systems Northwestern Polytechnical University Xi'An710072 China

Acoustic black holes (ABHs) had been recently revealed as an effective vibration control technology. However, due to inherent defects such as weakened stiffness, structural discontinuity and manufacturing difficulties, the practical application of ABH had been limited. Therefore, a multi-layer composite sandwich plate with filled imperfect-ABH (F-IABH) was proposed in this study to attenuate the vibration and sound radiation of the multi-layer sandwich plate, and could also enhance the bearing capacity of the structure and maintain its topological continuity. The structural damping characteristics and vibroacoustic response of the F-IABH were conducted by a semi-analytical wave propagation model developed based on the symplectic method and acoustic radiation mode method. In numerical examples, the accuracy and effectiveness of the analytical model were validated by the finite element method. The results showed that F-IABH can achieve broadband vibration attenuation and noise reduction effects. Especially at low frequencies, its vibration and noise reduction effect were significantly better than ABH structures. Meanwhile, the wave damping characteristics of uniform plate, ABH plate, and F-IABH plate were analyzed. The results showed that the wave damping of F-IABH was much higher than those of uniform plate, and they can generate more propagative waves to dissipate energy. In addition, the wave damping characteristics of F-IABH and ABH plate had very similar trends. However, at lower frequencies, due to the large variation range of wave mode damping characteristics of F-IABH, its control effect on structural vibration and acoustic radiation was more significant than that of ABH plate. © 2024, The Authors. All rights reserved.

关键词： Acoustic wave propagation

来源：评论

学校读者我要写书评

暂无评论

Power System Events Classification Technology Based on Deep-Learning

Power System Events Classification Technology Based on Deep-...

引用

IEEE International Symposium on Circuits and systems (ISCAS)

作者： Xin Lei Hongwei Ma Bin Liu Zhen Li School of Automation and Key Laboratory for Intelligent Control & Decision on Complex Systems Beijing Institute of Technology Beijing China College of Information Science and Engineering China University of Petroleum (Beijing) Beijing China

ISBN: (数字)9798350330991

ISBN: (纸本)9798350331004

As the complexity of the power system continues to increase, the frequency of the power system anomalies is on the rise. These anomalies have significant and widespread impacts on the stability of the power grid. Therefore, the rapid and accurate classification of these anomalies is crucial in preventing their further propagation and mitigating potential economic losses. This study presents an algorithm based on Phasor Measurement Unit (PMU) data for monitoring the state of power systems and identifying the types of anomalies. First, a dataset for anomaly event classification is created based on PMU data, which is used to train and validate the anomaly event classification model. Subsequently, a robust anomaly event classification model is constructed, consisting of a residual module with one-dimensional Convolutional Neural Networks (CNN) and a cascaded fully connected neural network classifier. This algorithm has undergone rigorous testing in the IEEE New England 39 bus test system, demonstrating exceptional event recognition accuracy.

关键词： Accuracy Power system stability Propagation losses Phasor measurement units Data models Stability analysis Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

The control and Application of a 2D-Motion Platform

The Control and Application of a 2D-Motion Platform

引用

第34届中国控制与决策会议

作者： Ziyao Wang Yiye Wang Kanjian Zhang Haikun Wei Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of EducationSchool of AutomationSoutheast University

Natural Locomotion interface(NLI) is critical to expanding the users' exploration of scenes in virtual reality and improving user *** on the 2D motion platform,users can achieve a natural locomotion experience in a limited physical *** a small-scale 2D motion platform,an ideal situation is that the velocity of the platform can always be synchronized with the user's actual intended velocity,so that the user's center of mass is kept at the center of the *** puts a brand new requirement on the performance of the platform *** paper designs an acceleration-level state feedback controller for the small-scale 2D motion *** the user's intended acceleration as an external disturbance,it is estimated by introducing a disturbance state observer;for the user' s velocity on the platform,a linear state observer is used to estimate it;then takes the estimated values as feedforward terms to compensate the *** with the HCMK1 2D motion platform,we implemented the controller and verified it to be *** recording the data of the user walking along the circle and the square trajectory,it was verified that the designed controller has good control performance for the user's motion and the state observers a great performance to quickly track the user's intended acceleration and the user's velocity on the platform.

关键词： Virtual Reality Nature Locomotion Interface State Observer 2D-Motion Platform

来源：评论

学校读者我要写书评

暂无评论

Temperature control System of Thermoelectric Cooler Based on Improved ADRC

Temperature Control System of Thermoelectric Cooler Based on...

引用

第34届中国控制与决策会议

作者： Xiyuan Shan Tao Cai Zhicheng Zong Hongbo Mu School of Automation Beijing Institute of Technology State Key Laboratory of Intelligent Control and Decision of Complex Systems

Aiming at the problems containing complex working conditions,modeling difficulties and long-time delay of thermoelectric cooler temperature control system,an improved ADRC control method combining ADRC and Smith predictor is proposed in this *** deals with the disturbances and uncertain dynamics in the system,SP compensates the time delay to improve the control *** with the traditional PID controller,the proposed control method has faster response speed and stronger anti-disturbance ability,meanwhile,overcomes the dependence of Smith predictor on object parameters to a certain *** simulation and experimental verification,a good control effect is obtained,which provides a positive guidance of the related application of thermoelectric cooler.

关键词： Thermoelectric cooler(TEC) Active Disturbance Rejection control(ADRC) Smith Predictor(SP) Temperature control System

来源：评论

学校读者我要写书评

暂无评论

Two-Phase Hybrid Fuzzy Clustering Approach Using Membership Fusion

Two-Phase Hybrid Fuzzy Clustering Approach Using Membership ...

引用

第34届中国控制与决策会议

作者： Tian Gao Qinglin Wang Yaping Dai School of Automation Beijing Institute of Technology State Key Laboratory of Intelligent Control and Decision of Complex Systems

In order to solve the problem that the clustering number in Fuzzy C-Means(FCM) needs to be set manually in advance,a two-phase hybrid fuzzy clustering approach using membership fusion(TPHFC) is *** the first phase,conventional FCM is used for *** the second phase,the results obtained by pre-clustering are fused according to the relationship between the membership of samples to different clusters and the membership threshold.A density-based clustering validity measurement is established for this *** proposed method obtains better clustering effect with setting fewer *** on synthetic datasets conforming to Gaussian distribution and UCI datasets demonstrate the effectiveness of the proposed clustering *** clustering number and clustering centers can be obtained adaptively.

关键词： Fuzzy Clustering Fuzzy C-Means Two-Stage Clustering Adaptive Parameter Adjustment

来源：评论

学校读者我要写书评

暂无评论

GAT-Net:A Network using Grid Attention and Transformer for Dynamic Facial Expression Recognition

GAT-Net:A Network using Grid Attention and Transformer for D...

引用

第34届中国控制与决策会议

作者： Wenxin Dai Yaping Dai Kaoru Hirota Shuai Shao School of Automation Beijing Institute of Technology State Key Laboratory of Intelligent Control and Decision of Complex Systems

Dynamic facial expression recognition(DFER) in the wild has received widespread attention *** are complex factors such as face occlusion and pose variation in the *** expression recognition has a subtle competition between capturing local features of a human face and obtaining a global feature *** paper proposes an end-to-end DFER network GAT-Net based on the grid attention module and Transformer,which improves the robustness and accuracy of DFER in the ***,GAT-Net is divided into two components:spatial feature extraction and temporal feature *** grid attention module of the spatial feature extraction component guides the network to pay attention to the local salient features of the face,which reduces the interference of field occlusion and non-frontal *** Transformer in the temporal feature processing component guides the network to learn the temporal relationship of high-level semantic features and the global representation of facial expression *** two components balance the subtle competition between local features and global feature representations of facial *** ablation experiment has proved the effectiveness of the grid attention module and *** demonstrate that our GAT-Net outperforms state-of-the-art methods on DFEW and AFEW benchmarks with accuracies of 67.53%,and 50.14% respectively.

关键词： Facial Expression Recognition Deep Learning Attention Mechanism Transformer

来源：评论

学校读者我要写书评

暂无评论

Automatic Reading System of Pointer Meters in Gas Gathering Stations

Automatic Reading System of Pointer Meters in Gas Gathering ...

引用

第34届中国控制与决策会议

作者： Yaqing Chang Kanjian Zhang Haikun Wei Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of EducationSchool of AutomationSoutheast University

In gas gathering stations,pointer meters are usually read by workers,which takes high labor costs and has low *** solve these problems and build intelligent gas gathering stations,this paper proposes an automatic reading system for real-time and accurate pointer meter reading.A new dataset is first constructed,which consists of700 pointer meter images with different angles,illumination and *** on the dataset,the deep learning model YOLOv5 is trained for dial and pointer *** the pointer mask output by YOLOv5,image preproces sing is used to separate the pointer from the background and generate the pure *** improved skeleton extraction algorithm and the Hough line detection algorithm are combined to extract the pointer center *** the dial image output by YOLOv5,feature matching and perspective transformation are adopted for position ***,pointer reading is obtained by applying the angle method to the corrected dial and the pointer center *** experiments demonstrate the high accuracy and efficiency of the proposed *** strong robustness to various interference factors in complex environments are also validated.

关键词： Pointer Meter Automatic Reading YOLOv5 Object Detection Skeleton Extraction

来源：评论

学校读者我要写书评

暂无评论

Distributed Active Disturbance Rejection control of Multiple Mobile Robots for Online Workload Partition

Distributed Active Disturbance Rejection Control of Multiple...

引用

2023 China Automation Congress, CAC 2023

作者： Li, Xin Zhai, Chao Zhang, Hehong China University of Geosciences School of Automation Wuhan Campus Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China School of Computer and Data Science Fuzhou University Fuzhou China

ISBN: (纸本)9798350303759

Considering the actual multi-agent coverage process, the motion trajectories are seriously affected by disturbances and noise. In this paper, a cooperative control method based on active disturbance rejection controller (ADRC) for multiple mecanum-wheeled robots (MWMR) is proposed to improve its robustness. In particular, to suppress the total disturbances during the running of each robot and reduce large computation and observation cost of high order ADRC, a reduced-order cascaded ADRC (RC-ADRC) is proposed. Moreover, distributed controller is proposed to track the expected trajectories of multiple mecanum-wheeled robots under disturbances. Compared with the proposed RC-ADRC based cooperative control scheme and PID based cooperative control one, the favorable motion trajectory tracking performance is obtained. Simulation results verify the superiority of the method. © 2023 IEEE.

关键词： controllers

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：