检索结果-内蒙古大学图书馆

Acoustic black hole effect enhanced micromanipulator

Microsystems & Nanoengineering 2024年第5期10卷 345-352页

作者： Qiu Yin Haoyong Song Zhaolong Wang Zhichao Ma Wenming Zhang State Key Laboratory of Mechanical System and Vibration Shanghai Jiao Tong UniversityShanghaiChina institute of Medical Robotics School of Biomedical EngineeringShanghai Jiao Tong UniversityShanghaiChina College of Mechanical and Vehicle Engineering Hunan UniversityChangshaChina School of Energy Science and Engineering Harbin Institute of TechnologyHarbinP.R.China

Microparticle manipulation is a critical concern across various felds including microfabrication,flexible electronics and tissue ***-activated sharp structures have been designed as simple and flexible tools to manipulate microparticles with their good compatibility,fast response,and broad ***,there still lacks rational acoustic-structure design for effective energy concentration at the acoustic-activated sharp structures for microparticle ***,we present the acoustic black hole(ABH)effect as enhancement for the acoustic *** provides great reliability,simplicity and ease of use,supporting custom design of high-throughput patterning ***,compared to commonly used configurations,such as cylindrical or conical microneedles,those microneedles with ABH profle exhibit superior acoustic energy focusing at the tip and induce stronger acoustofluidic *** average acoustic flow velocity induced by the ABH microneedle is 154 times greater than that of the conical one and 45 times greater than that of the cylindrical ***,the average acoustic radiation force(ARF)produced by the ABH microneedle against acrylic microparticles is about 319 times greater than that of the cylindrical one and 16 times greater than that of the conical *** results indicate that ABH design significantly enhances microparticle *** demonstrate this concept with ABH effect enhanced microparticle manipulation and study the parameters influencing its performance including operating frequency,operating voltage and particle ***,considering the flexibility of this system,we employ it for various patterning and high-throughput microparticle *** work paves the way for controllable microparticle manipulation,holding great potential for applications in microfabrication and biomedicine.

关键词： cylindrical Acoustic simplicity

来源：评论

学校读者我要写书评

暂无评论

Adaptive inter-intradomain alignment network with class-aware sampling strategy for rolling bearing fault diagnosis

引用

Science China(Technological Sciences) 2023年第10期66卷 2862-2870页

作者： GAO QinHe HUANG Tong ZHAO Ke SHAO HaiDong JIN Bo LIU ZhiHao WANG Dong National Key Discipline Laboratory of Armament Launch Theory&Technology Rocket Force University of EngineeringXi’an 710025China Key Laboratory of Road Construction Technology&Equipment Ministry of Education Chang’an UniversityXi’an 710054China College of Mechanical and Vehicle Engineering Hunan UniversityChangsha 410082China Institute of Systems and Robotics Department of Electrical and Computer EngineeringUniversity of CoimbraCoimbra 3030-290Portugal

Existing unsupervised domain adaptation approaches primarily focus on reducing the data distribution gap between the source and target domains,often neglecting the influence of class information,leading to inaccurate alignment *** by this observation,this paper proposes an adaptive inter-intra-domain discrepancy method to quantify the intra-class and inter-class discrepancies between the source and target ***,an adaptive factor is introduced to dynamically assess their relative *** upon the proposed adaptive inter-intradomain discrepancy approach,we develop an inter-intradomain alignment network with a class-aware sampling strategy(IDAN-CSS)to distill the feature *** classaware sampling strategy,integrated within IDAN-CSS,facilitates more efficient *** multiple transfer diagnosis cases,we comprehensively demonstrate the feasibility and effectiveness of the proposed IDAN-CSS model.

关键词： unsupervised domain adaptation inter-class domain discrepancy intra-class domain discrepancy class-aware sampling strategy

来源：评论

学校读者我要写书评

暂无评论

RDDS: Road Disease Detection Model Based on YOLOv5 14

RDDS: Road Disease Detection Model Based on YOLOv5

引用

14th IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems, CYBER 2024

作者： Han, Zhiqiang Gong, Jun Qiao, Yu School of Vehicle and Transportation Engineering Taiyuan University of Science and Technology Taiyuan030024 China Shenyang Institute of Automation Chinese Academy of Sciences State Key Laboratory of Robotics Shenyang110016 China

ISBN: (纸本)9798331506056

The utilization of intelligent vehicles for detecting road anomalies has become a relatively common phenomenon. The existing road disease detection workload is large, the robustness is not high, and small diseases are easily ignored, which brings huge challenges to road disease detection. A road disease detection model named RDDS based on YOLOv5 is proposed. Based on the YOLOv5 algorithm, we incorporate Transformer encoder blocks into the head part to form Transformer Prediction Heads (TFE), expanding their number to four. This enhancement aims to improve the model's capability to detect small targets and road diseases of different scales. In addition, we introduce the convolutional block attention model (CBAM) to make the network pay more attention to important channels and spatial locations, thereby improving the performance and generalization ability of the model. Aiming at the problems of low resolution and insufficient data volume in current road disease data sets, we propose a new road disease detection data set RDDSC. Finally, we conducted experiments on the RDDSC data set. The experimental results showed that compared with the original YOLOv5, the RDDS parameters increased slightly, while the detection accuracy was significantly improved. Compared with existing detection algorithms, RDDS has obvious advantages in road disease detection. © 2024 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

STAPointGNN: Spatial-Temporal Attention Graph Neural Network for Gesture Recognition Using Millimeter-Wave Radar 19th

STAPointGNN: Spatial-Temporal Attention Graph Neural Network...

引用

19th EAI International Conference on Collaborative Computing: Networking, Applications and Worksharing, CollaborateCom 2023

作者： Zhang, Jun Wang, Chunyu Wang, Shunli Zhang, Lihua Academy for Engineering and Technology Fudan University Shanghai China Jilin Provincial Key Laboratory of Intelligence Science and Engineering Changchun China Engineering Research Center of AI and Robotics Ministry of Education Shanghai China Engineering Research Center of AI and Unmanned Vehicle Systems of Jilin Province Changchun China

ISBN: (纸本)9783031545276

Gesture recognition plays a pivotal role in enabling natural and intuitive human-computer interaction (HCI), finding applications in diverse domains such as smart homes, robot control, and virtual reality. Thanks to advances in computer vision, the most popular method currently is to use the camera for gesture recognition. However, the camera struggles to function properly in poor lighting and inclement weather, and risks invading privacy. Due to the robust and non-invasive features of millimeter-wave radar, gesture recognition based on millimeter-wave radar has received extensive attention from researchers in recent years. In this paper, we propose a novel graph neural network named STAPointGNN for gesture recognition using millimeter-wave radar. In order to better extract features in the spatial and temporal dimensions of point clouds collected by millimeter-wave radar, we designed a spatial-temporal attention mechanism based on graph neural network. We also propose a novel point flow embedding method to capture the motion features of the point clouds in adjacent frames. To verify the superiority of our method, we conduct experiments on two public millimeter-wave radar gesture recognition datasets. The results show that our model outperforms existing mainstream algorithms. © ICST Institute for Computer Sciences, Social Informatics and Telecommunications engineering 2024.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

Fuzzy-NMS: Improving 3D Object Detection With Fuzzy Classification in NMS

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent vehicles 2024年 1-15页

作者： Wang, Li Zhang, Xinyu Zhao, Fachuan Wu, Chuze Wang, Yichen Song, Ziying Yang, Lei Xu, Bin Li, Jun Ge, Shuzhi Sam School of Machanical Engineering Beijing Institute of Technology Beijing China School of Vehicle and Mobility Tsinghua University Beijing China School of Computer and Information Technology Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing China Department of Electrical and Computer Engineering Interactive Digital Media Institute Social Robotics Laboratory National University of Singapore Singapore

Non-maximum suppression (NMS) is an essential post-processing module in many 3D object detection frameworks to remove overlapping candidate bounding boxes. However, an overreliance on classification scores and difficulties in determining appropriate thresholds can affect the resulting accuracy directly. To address these issues, we introduce fuzzy learning into NMS and propose a novel generalized Fuzzy-NMS module to achieve finer candidate bounding box filtering. The proposed Fuzzy-NMS module combines the volume and clustering density of candidate bounding boxes, refining them with a fuzzy classification method and optimizing the appropriate suppression thresholds to reduce uncertainty in the NMS process. Adequate validation experiments use the mainstream KITTI and large-scale Waymo 3D object detection benchmarks. The results of these tests demonstrate the proposed Fuzzy-NMS module can improve the accuracy of numerous recently NMS-based detectors significantly, including PointPillars, PV-RCNN, and IA-SSD, etc. This effect is particularly evident for small objects such as pedestrians and bicycles. As a plug-and-play module, Fuzzy-NMS does not need to be retrained and produces no obvious increases in inference time. IEEE

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Multiple People Continuous Tracking and Identification Using Millimeter-wave Radar 8

Multiple People Continuous Tracking and Identification Using...

引用

8th International Symposium on Advances in Electrical, Electronics, and Computer engineering, ISAEECE 2023

作者： Wang, Chunyu Zhang, Jun Liu, Yang Zhang, Lihua Academy for Engineering and Technology Fudan University Shanghai China Ji Hua Laboratory Foshan China Engineering Research Center of AI and Robotics Ministry of Education China Engineering Research Center of AI and Unmanned Vehicle Systems of Jilin Province Changchun China

ISBN: (纸本)9781510666290

Automatic people tracking and identification have a lot of application prospects in access control, intelligent monitoring, personalized service, etc. Although the primary sensors used now are cameras, they are challenging to cope with low light conditions, adverse weather conditions, and clothing changes. The privacy risks brought by cameras cannot be ignored with people's increasing awareness of privacy. In this paper, we use a commercial millimeter-wave radar to track and identify multiple people indoors. The mmWave radar can "see" objects even in the dark and protects people's private information. We propose PPMM mechanism to solve the problem of tracking multiple people walking at close distances. What's more, we design transformer for mmWave radar pointclouds (TMP) based on transformer architecture. Finally, we evaluate our model and demonstrate the results on our dataset, which involved 6 people. Our method can track up to 3 people simultaneously. We achieve the best identification accuracy of 86.34% overall different numbers of people scenarios, and the accuracy of single, two, and three people scenarios are 87.93%, 87.00%, and 64.98%. © 2023 SPIE. All rights reserved.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Improved YOLOv5s Network for Traffic Object Detection with Complex Road Scenes 13

Improved YOLOv5s Network for Traffic Object Detection with C...

引用

13th IEEE International Conference on CYBER Technology in Automation, Control, and Intelligent Systems, CYBER 2023

作者： Cao, Yi Wang, Yuning Fan, Huijie Dalian University of Technology Faculty of Vehicle Engineering and Mechanics Da Lian China Unit 32681 PLA Tieling China Shenyang Institute of Automation State Key Laboratory of Robotics Chinese Academy of Sciences Shenyang China

ISBN: (纸本)9798350315196

Aiming at the problems of low target detection accuracy and prone to false detection and missed detection in complex traffic scenes, a road target detection algorithm based on improved YOLOv5s is proposed. Firstly, a feature extraction layer based on Spatial Pyramid Pooling(SPP) is adopted for increasing shallow feature receptive fields named as Multi-scale SPP module (M-SPP). M-SPP is designed to fully integrate feature information of different scales for improving feature extraction ability of our network. Secondly, a Global Context Attention Module(GCAM) is proposed, in focusing on important features in channel and spatial dimensions, allowing the network to focus on more useful information. Finally, experimental results show that detection accuracy of the improved YOLOv5s model we proposed on the UA-DETRAC dataset, compared with the original algorithm, improved by 1.83% and 2.54% respectively. Our improved model abtain good detection accuracy while ensuring real-time performance, and solves problem of missed detection and false detection of small targets in complex road scenes to a certain extent. © 2023 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Kinematics Analysis and Singularity Avoidance of a Parallel Mechanism with Kinematic Redundancy

引用

Chinese Journal of Mechanical engineering 2022年第5期35卷 244-261页

作者： Chaoyu Shen Haibo Qu Sheng Guo Xiao Li Robotics Research Center School of MechanicalElectronic and Control EngineeringBeijing Jiaotong UniversityBeijing 100044China China Waterborne Transport Research Institute Beijing 100088China Key Laboratory of Vehicle Advanced Manufacturing Measuring and Control TechnologyMinistry of EducationBeijing Jiaotong UniversityBeijing 100044China

The kinematic redundancy is considered as a way to improve the performance of the parallel *** this paper,the kinematics performance of a three degree-of-freedom parallel mechanism with kinematic redundancy(3-DOF PM-KR)and the influence of redundant parts on the PM-KR are ***,the kinematics model of the PM-KR is *** inverse solutions,the Jacobian matrix,and the workspace of the PM-KR are ***,the influence of redundancy on the PM-KR is *** there exists kinematic redundancy,the PM-KR possesses fault-tolerant *** locking one actuating joint or two actuating joints simultaneously,the fault-tolerant workspace is *** the position of the redundant part is changed,the workspace and singularity will be *** results show that kinematic redundancy can be used to avoid ***,the simulations are performed to prove the theoretical analysis.

关键词： Parallel mechanism Kinematic redundancy Singularity Simulation analysis

来源：评论

学校读者我要写书评

暂无评论

Dynamics Analysis of a Symmetric 3-R(SRS)RP Multi-loop Mechanism 1

引用

23rd IFToMM China International Conference on Mechanism and Machine Science and engineering, IFToMM CCMMS 2022

作者： Li, Chuanyang Qin, Zhongbao Hu, Changhua Liu, Rongqiang Liu, Ruiwei Song, Xiaoke PLA Rocket Force University of Engineering Xi’an710025 China State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin150080 China College of Naval Architecture and Ocean Engineering Guangzhou Maritime University GuangZhou510725 China School of Mechatronics and Vehicle Engineering East China Jiaotong University Nanchang330013 China

ISBN: (数字)9789811993985

ISBN: (纸本)9789811993978

The 3-R(SRS)RP multi-loop Mechanism is regarded as one module of a multi-stage manipulator for space manipulation operations, such as capturing free-flying objects. The mechanism has two rotational and one translational degrees of freedom, as well as includes coupled kinematic chains, which can be constructed to the modular system for space operation. The dynamics analysis of the mechanism is the basis of its structural design and actuation control. In this paper, the twist shaping matrix between the twists of links and the input rate array is derived by decoupling the mechanism and motion analysis. Based on the Newton–Euler equation, the dynamics model of the mechanism is established. the theoretical values of actuation power consumption on the certain motion modes is calculated via programming, then being compared with the simulation values obtained through ADAMS model. The results are basically consistent, which verifies the correctness of the dynamics analysis of the mechanical system. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Dynamics

来源：评论

学校读者我要写书评

暂无评论

Continuous Path Tracking of Robots Based on Positioning Error Compensation With Iterative Learning Control

引用

IEEE Transactions on Instrumentation and Measurement 2025年 74卷

作者： Liu, Ying Li, Yuwen Shanghai University Shanghai Key Laboratory of Intelligent Manufacturing and Robotics School of Mechatronic Engineering and Automation Shanghai201900 China East China Jiaotong University School of Mechatronics and Vehicle Engineering Nanchang330013 China

Due to the inaccuracy of absolute positioning, it is still challenging to apply industrial robots for precise and efficient tracking of the end-effector tool along a continuous path, especially for those frequently changing robotic operations within low-volume and high-mix scenarios. To overcome this problem, this work proposes a method of continuous path tracking of robots with iterative learning control (ILC) such that the pose errors of the tool along the path can be compensated by the robot. An optical tracking system is integrated to measure the tool pose. Developed from a comprehensive kinematic error model that incorporates errors in the Denavit-Hartenberg (D-H) parameters and errors induced by the installation of the robot base and the tool, the ILC algorithm can convert the tool pose error into the joint angle compensation for the robot. The robustness of the algorithm is analyzed to prove that the compensated path approaches the desired path as the number of iterations increases. An experimental test of continuous path tracking has been performed with a UR10 robot to validate the proposed method. It is demonstrated that the average and maximum position errors can be reduced from 14.57 and 20.31 to about 0.26 and 0.78 mm, respectively. The average and maximum orientation errors are reduced from 0.66° and 0.94° to about 0.08° and 0.20°, respectively. For a test of robotic laser cutting, the average dimensional accuracy of the rectangular workpiece can be reduced from 0.416 to about 0.154 mm, and the average shape accuracy is reduced from 0.101° to about 0.059°. Using the ILC algorithm and the measurement with the optical tracking system, our method can significantly enhance the tracking accuracy of the end-effector tool along continuous paths by autonomous adjustment of the joint angles without the need for human teaching. © 2025 IEEE.

关键词： Industrial robots

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：