检索结果-内蒙古大学图书馆

2019 IEEE International Conference on Robotics and Biomimetics, ROBIO 2019

作者： Xiang, Hongbiao Zhang, Tilei Li, Mengwei Wang, Shoujun Yang, Xiuping Tianjin University of Technology Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin300384 China National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin University of Technology Tianjin300384 China

ISBN: (纸本)9781728163215

The actuation and control of mini-scale swimming robots have exhibit promising potential in limited and constrained environments, such as biomedical, micro-assembly and microfluidic applications. However, closed-loop control is still a challenging for the precision and repeatability in those applications. In this paper, a new type of soft-micro swimming robot based on magnetoelastic composite material is designed, and the swimmer can move freely on the water surface controlled by a rotating magnetic field with visual servoing. The visual feedback control strategy is proposed based on Mean Shift Algorithm and Fast Template Matching. The algorithm includes three parts: prediction, template matching, target positioning and template updating. To understand the characteristics of the swimmer, the relationship between swimming speed and magnetic field strength and frequency is verified by the algorithm in experiments. Furthermore, the proposed path following method with visual servoing applied in this control system. The experimental results show that the algorithm runs fast, has high accuracy and good real-time performance, and can provide great potential in mini-scale robot applications. © 2019 IEEE.

关键词： Visual servoing

来源：评论

学校读者我要写书评

暂无评论

Iterative rational krylov algorithms for model reduction of a class of constrained structural dynamic system with engineering applications

arXiv

引用

arXiv 2021年

作者： Du, Xin Uddin, Mohammad Monir Fony, A. Mostakim Hossain, Md. Tanzim Shuzan, Md. Nazmul Islam School of Mechatronic Engineering and Automation Shanghai University Shanghai200072 China Key Laboratory of Modern Power System Simulation and Control & Renewable Energy Technology Ministry of Education Northeast Electric Power University Jilin132012 China Department of Mathematics and Physics North south University Dhaka1229 Bangladesh Department of Mathematics Chittagong University Chittagong Bangladesh Department of Electrical and Computer Engineering North South University Dhaka1229 Bangladesh

This paper discusses model order reduction of large sparse second-order index-3 differential algebraic equations (DAEs) by applying Iterative Rational Krylov Algorithm (IRKA). In general, such DAEs arise in constraint mechanics, multibody dynamics, mechatronics and many other branches of sciences and technologies. By deflecting the algebraic equations the second-order index-3 system can be altered into an equivalent standard second-order system. This can be done by projecting the system onto the null space of the constraint matrix. However, creating the projector is computationally expensive and it yields huge bottleneck during the implementation. This paper shows how to find a reduce order model without projecting the system onto the null space of the constraint matrix explicitly. To show the efficiency of the theoretical works we apply them to several data of second-order index-3 models and experimental resultants are discussed in the paper. © 2021, CC BY.

关键词： Differential equations

来源：评论

学校读者我要写书评

暂无评论

Swimming Characteristics of Soft robot with Magnetoelastic Material

Swimming Characteristics of Soft robot with Magnetoelastic M...

引用

IEEE International Conference on Robotics and Biomimetics

作者： Hongbiao Xiang Mengwei Li Tilei Zhang Shoujun Wang Xiuping Yang Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin China

Cable-less micro-robots have exhibit great capabilities for remote applications in small and constrained environments, especially in biotechnology and healthcare. This paper presents a swimmer propelled by its undulatory deformation using magnetoelastic composite material. The robot can move freely on water surface driven through a function of magnetic field, such as forward, backward and steering with different velocity. The magnetic field is generated by 3D Helmholtz coils, and the locomotion of the micro swimming robot is controlled by different applied magnetic field. To understand the characteristics of the swimmer, the force balance equation is established, and the morphologies of swimmer with different magnetic field are analyzed and described through finite element analysis method. Furthermore, we discuss and analyze relationship between the parameters of magnetic field and the speed of the swimmer. The experimental results verified the speed model of the swimming robot, which is influenced by the frequency and strength of magnetic field.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Feedforward control Based on Robot Dynamics Parameters Identification

Research on Feedforward Control Based on Robot Dynamics Para...

引用

IEEE International Conference on mechatronics and Automation

作者： Xingmao Shao Shoujun Wang Liusong Yang Nan Liu Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control Tianjin University of Technology Tianjin China National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin University of Technology Tianjin China CITIC Heavy Industries Company Ltd. Luoyang China

ISBN: (数字)9781728164168

ISBN: (纸本)9781728164175

Accurate robot dynamics model can effectively improve the motion control performance of robot, and accurate dynamics parameters are the basis for establishing dynamics model. This paper discusses the parameter identification method of the tandem manipulator and the feedforward control scheme based on dynamics. First, we deduced the basic parameters of the first three joints of the UR5 manipulator, and identified the parameters through experimental sampling and calculation. Secondly, we established a feedforward control mechanism based on dynamics using the Simulink platform, and simulated and verified the feedforward control of the robot three-axis system. The experimental results show that the feedforward control scheme based on robot dynamics can effectively improve the error convergence performance, which proves the effectiveness of the method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SI-YOLO: A Deep Learning Algorithm Suitable for Surgical Instrument Detection

SSRN

引用

SSRN 2022年

作者： Liu, Zhenzhong Zhou, Yifan Sun, Qiyuan Wang, Yan Polat, Kemal Nour, Majid Alenezi, Fayadh Alhudhaif, Adi Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin300384 China Tianjin300384 China Department of Electrical and Electronics Engineering Bolu Abant Izzet Baysal University Bolu14280 Turkey Department of Electrical and Computer Engineering Faculty of Engineering King Abdulaziz University Jeddah21589 Saudi Arabia Department of Electrical Engineering College of Engineering Jouf University 72238 Saudi Arabia Department of Computer Science College of Computer Engineering and Sciences in Al-kharj Prince Sattam bin Abdulaziz University P.O. Box 151 Al-Kharj 11942 Saudi Arabia

Surgical instrument detection and tracking is one of the core technologies of surgical robots, which can assist clinicians in completing operations. However, existing methods need further improvement in terms of real-time performance and accuracy. We propose a deep learning algorithm, SI-YOLO, for detection of surgical instruments. SimAM attention mechanism is used to improve the feature extraction ability of YOLOv5. Replacing PANet with BiFPN in the neck network improves the feature fusion strategy. The α-IoU loss function is used to improve the regression accuracy of detection boxes. The mAP and FPS of the SI-YOLO reach 99.2% and 120 frames/sec, respectively. Aiming at the problem of ID transformation in the disappearance and occlusion of surgical instruments, the Inception-ResNet-v2 structure is added on the basis of the appearance feature extraction network Cosine of the DeepSort tracking algorithm. Combining SI-YOLO with the improved DeepSort implements the Tracking by Detection (TBD) algorithm. In the case of device disappearance or occlusion, the frequency of ID transitions is reduced by approximately 30%. Finally, we built a simulated surgery experimental platform, established our own data set, and realized the preliminary application of the proposed algorithm. © 2022, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Robust Tensor Principal Component Analysis Based on F-norm

Robust Tensor Principal Component Analysis Based on F-norm

引用

IEEE International Conference on mechatronics and Automation

作者： Weimin Ge Jinxiang Li Xiaofeng Wang National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin University of Technology Binshui Xidao 391 Xiqing District Tianjin China Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control Tianjin University of Technology Binshui Xidao 391 Xiqing District Tianjin China

ISBN: (数字)9781728164168

ISBN: (纸本)9781728164175

Tensor principal component analysis (TPCA) has been widely used to extract appearance features of colour objects or colour scenes presented in tensor form. Using L 1 -norm as the distance metric, the existing TPCA-L 1 with its greedy (TPCA-L 1 -G) and non-greedy (TPCA-L 1 -NG) algorithms were proposed to reduce the sensitivity to outliers. The two algorithms, however, only derived TPCA solution in a form of two-dimensional matrix without actually extending them to the tensor subspaces and without performing experimental verification for tensor data. Simultaneously, the spatial correlations between pixels of the raw tensor data cannot be effectively preserved. To solve the problems, a robust tensor principal component analysis algorithm based on F-norm distance metric is proposed in this paper, which not only preserves the spatial structure of the raw data, but also reduces the sensitivity to outliers in tensor data. Experiments on reconstruction error and classification rate show that the proposed algorithm is effective and superior to other tensor algorithms in performances.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Incremental Feature Extraction Method for Weld Surface Defect Recognition

An Incremental Feature Extraction Method for Weld Surface De...

引用

IEEE International Conference on mechatronics and Automation

作者： Jun Liu Keguang Ren Xiaofeng Wang Weimin Ge National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin University of Technology Binshui Xidao 391 Xiqing District Tianjin China Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control Tianjin University of Technology Binshui Xidao 391 Xiqing District Tianjin China

ISBN: (数字)9781728164168

ISBN: (纸本)9781728164175

To meet the requirements of online feature extraction for weld defect recognition, an Incremental 2DPCA algorithm (I2DPCA) without estimating the covariance matrix of weld surface images is firstly proposed. A set of weld features with multiple orthogonal principal components can be obtained by a recursive estimation method, instead of the eigenvalue decomposition method or the singular value decomposition method. The computational complexity will be greatly reduced and the online feature extraction speed will be improved. To extract more structure features and reduce the dimension of weld images, an Incremental row-column Bidirectional PCA (IBDPCA) algorithm is presented based on I2DPCA, which preserves the weld features in the horizontal and vertical directions of weld images, and realizes the incremental feature extraction and data dimensionality reduction in the row and column directions. Finally, a series of comparative experiments are performed on the collected weld defect dataset. The results show that the proposed algorithm is superior to other PCA algorithms in convergence rate, classification rate, and complexity. The convergence rate is more than 99%, the classification rate can reach 96%, which can meet the online feature extraction requirements for weld defect recognition.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Manipulator of robust fuzzy adaptive compensation control 3

Manipulator of robust fuzzy adaptive compensation control

引用

3rd Asia-Pacific Conference on Intelligent Robot systems, ACIRS 2018

作者： Yangjian, Wang Xiaofei, Chen Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineeringline Binshui Xidao 391 Tianjin China

ISBN: (纸本)9781538672266

Dynamics system for reconfigurable manipulator of uncertainty, based on the fuzzy adaptive algorithm is proposed to approach the system control law from adaptation to friction and external disturbance, the compensation control of the reconfigurable robot arm. At the same time in order to improve the control law of compensation precision and anti-interference performance, reduce the approximation error of the algorithm and the robust items added in the control law. By Lyapunov stability theory proves that the proposed fuzzy adaptive robust fuzzy control law and the adaptive control law can be in reconfigurable manipulator dynamics contained in friction and the external disturbance to ensure the stability of the system. Last three do f reconfigurable robot arm as an example to design a reconfigurable robotic arm controller, the simulation results show that the algorithm has good trajectory tracking performance, and proves the feasibility and effectiveness of the algorithm. © 2018 IEEE.

关键词： Friction

来源：评论

学校读者我要写书评

暂无评论

Research on Stress-Relaxation Property of Different Layers ment under Compression 16

Research on Stress-Relaxation Property of Different Layers m...

引用

16th IEEE International Conference on mechatronics and Automation, ICMA 2019

作者： Zhou, Jinlai Song, Yang Shi, Xue Xu, Chenguang Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control Tianjin University of Technology School of Mechanical Engineering Tianjin University of Technology Tianjin300384 China National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin University of Technology China Periodontitis Department Tianjin Stomatological Hospital Tianjin300041 China

ISBN: (纸本)9781728116983

As a connective tissue connecting teeth and alveolar bone, periodontal ligament (PDL) has the mechanical properties of nonlinearity, viscoelasticity, anisotropy. In this paper, the pig mandibular central incisors were taken as subjects, a loading machine(CARE-MI00) was used to perform compression tests and the PDL stress-relaxation characteristics under different strain conditions were obtained. The stress-time curves and the relaxation modulus curves were obtained. The three-parameters Zener model and five-parameter generalized Maxwell model proposed by the author were used to fit the data. The experimental results show that the elastic modulus of PDL decreases gradually in the apex(ranges from 2.64 to 3.06 MPa), cervical margin(ranges from 1.44 to 1.76 MPa) and midroot (ranges from 1.03 to 1. 06MPa). Zener model has a relatively high fitting degree, and the squared correction coefficient is about 0.98, however, the adjusted R square of the five-parameter model was above 0.99. Compared with the Zener model, the five-parameter model can better reflect the sudden drop of relaxation modulus at the initial stage, which is more suitable for describing stress-relaxation in viscoelastic behavior of PDL. The advantage of this paper is to compare the descriptive ability of three-parameter and five-parameter generalized Maxwell equation to the mechanical properties of PDL and to provide an effective procedure for the preparation of PDL specimens. © 2019 IEEE.

关键词： Elastic moduli

来源：评论

学校读者我要写书评

暂无评论

Comparing WiFi RSS Filtering for Wireless Robot Location system

引用

Procedia Manufacturing 2019年 30卷 143-150页

作者： T. Thewan C. Seksan S. Pramot A.H. Ismail K. Terashima Faculty of Engineering Pathumwan Institute of Technology Bangkok Thailand Faculty of Engineering Kasem Bundit University Bangkok Thailand School of Mechatronic Engineering Universiti Malaysia Perlis Malaysia System and Control Laboratory Toyohashi University of Technology Japan

Wireless infrastructure such as WiFi gained wide interest by researchers and private companies to determine the location of a target object in a building. Hence, we observe an increase in popularity of in building WiFi solutions. However, significant fluctuations in WiFi signal strength are affecting the measurement quality and as a result the fingerprinting positioning approach. The accuracy of the positioning will be improved if the RSS measured at different distances between transmitter (Tx) to receiver (Rx) is distinctly different. Several filtering methods may be applied to reduce the data noise for estimating. Many methods demonstrate great noise reduction. The time taken to compute data becomes limited to mobile robot application since real-time is required. The requirement for real time data singles out mobile robot application as an effective solution. In this paper, the focus will be on the difference of RSS measurements with varying Tx-Rx distances, following the design of experiment (DoE). Further we include a comparison between the Kalman filtering and weight fusion, which is Weight-Average of the Top-n Populated values model (WATP). Errors in estimation and reduction in computation time are taken into consideration.

关键词： WiFi RSS Kalman filter Weight fusion Indoor Positioning system Weight-Average of the Top-n Populated values model

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：