检索结果-内蒙古大学图书馆

37th Chinese control Conference, CCC 2018

作者： Weidong, Liu Haiming, Liu Jinhui, Guo South China University of Technology Key Laboratory of Autonomous Systems and Networked Control Ministry of Education Guangzhou510640 China

ISBN: (纸本)9789881563941

Considering the batch assembly with multiple function requirements (FR), the multi-object selective assembly (SA) technology based on the hybrid particle swarm algorithm is introduced in this paper. Firstly, the SA model is discussed, and a multi-object optimization problem is illustrated based on the assembly chains;additionally, the hybrid particle swarm algorithm is used to solve the multi-object selective assembly problem. The matching matrix of batch parts is designed as the particle. The local non-inferior particles and the global non-inferior particles of each iteration population are calculated. The particle population is update by crossover and mutation operations. After all the iterations, the final global non-inferior particles are selected as the matching strategy of batch parts. Based on the optimized matching strategy, the assembly success rate is calculated, and each assembly accuracy and its precision is guaranteed. The process of multi-object SA based on hybrid particle swarm algorithm is introduced, and an example of batch cabin sections are illustrated to obtain the optimized matching strategy of batch parts. Contrasted to the sequential strategy and the random strategy, it can find that the multi-object SA method based on hybrid particle swarm algorithm has advantage in guaranteeing the assembly success rate, and comprehensively decreasing each assembly accuracy. © 2018 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Heun-Thought Aided ZD4NgS Method Solving Ordinary Differential Equation (ODE) Including Nonlinear ODE System

Heun-Thought Aided ZD4NgS Method Solving Ordinary Differenti...

引用

International Symposium on Computational Science and Computing, ISCSC 2018

作者： Zhang, Yunong Huang, Huanchang Li, Jian Yang, Min Wu, Sheng School of Information Science and Technology Sun Yat-sen University Guangzhou510006 China Key Laboratory of Autonomous Systems and Networked Control Ministry of Education Guangzhou510640 China SYSU-CMU Shunde International Joint Research Institute Shunde Foshan528300 China Ministry of Education Guangzhou China

ISBN: (纸本)9783030021153

In this paper, a Zhang discretization (ZD) formula with high accuracy, termed ZD 4-node g-square (ZD4NgS) formula, is presented. Resorted to this formula, a numerical method for solving the initial value problem (IVP) of ordinary differential equation (ODE) is firstly presented. Such a method is thus considered as ZD4NgS method. Then, to improve accuracy, a Heun-thought aided modification of ZD4NgS method is proposed and investigated. For comparison, the conventional Euler method is also presented. In addition, numerical experiments are carried out, and numeric results show that the modified ZD4NgS method has a best final global error (FGE) among the three methods, substantiating that the accuracy of ZD4NgS method can indeed be improved after modification. © 2019, Springer Nature Switzerland AG.

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Rate Analysis of Operators and its Applications in Linear Spaces

Research Square

引用

Research Square 2021年

作者： Zhang, Yijin Li, Honggang Jin, Maoming Lin, Zongbing Nanjing Changjiang Waterway Engineering Bureau China Key Lab of Intelligent Analysis and Decision on Complex Systems Key Laboratory of Industrial Internet of Things and Networked Control Ministry of Education Chongqing University of Posts and Telecommunications Chongqing400065 China Pass College Chongqing Technology and Business University Chongqing401520 China Institute of Nonlinear Analysis Research Changjiang Normal University Chongqing400803 China School of Mathematics and Computer Science Panzhihua University Panzhihua617000 China

In this paper, a new concept, the fuzzy rate of an operator in linear spaces is proposed for the very first time. Some properties and basic principles of it are studied. Fuzzy rate of an operator B which is specific i... 详细信息

关键词： Membership functions

来源：评论

学校读者我要写书评

暂无评论

Dynamic surface control of shape memory alloy actuating systems with inverse Duhem hysteresis compensation 15

Dynamic surface control of shape memory alloy actuating syst...

引用

15th IEEE International Conference on Mechatronics and Automation, ICMA 2018

作者： Li, Rui Feng, Ying Hu, Zedong School of Automation Science and Engineering Key Laboratory of Autonomous Systems and Networked Control South China University of Technology Guangzhou510640 China

ISBN: (纸本)9781538660720

Shape Memory Alloys actuators are a class of smart materials-based actuators, and show a good output performance with high force to mass ratio, biocompatibility and small size. However, the internal hysteresis nonlinearities between the input temperature and output displacement adversely affect the output accuracy and they cannot be mitigated directly because of the strong non-smooth feature of SMA materials. To improve the actuating ability of SMA system, an estimated hysteresis inverse is employed based on Duhem model as the compensation of SMA actuator in this paper. Considering the dynamics of the SMA actuating system and the compensation error, a dynamic surface controller (DSC) is designed. The simulation results validate the effectiveness of the proposed approach. © 2018 IEEE.

关键词： Hysteresis

来源：评论

学校读者我要写书评

暂无评论

Biologically Inspired Motion Modeling and Neural control for Robot Learning From Demonstrations

引用

IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL systems 2019年第2期11卷 281-291页

作者： Yang, Chenguang Chen, Chuize Wang, Ning Ju, Zhaojie Fu, Jian Wang, Min South China Univ Technol Coll Automat Sci & Engn Key Lab Autonomous Syst & Networked Control Guangzhou 510640 Guangdong Peoples R China Univ Plymouth Ctr Robot & Neural Syst Plymouth PL4 8AA Devon England Univ Portsmouth Sch Comp Portsmouth PO1 2DJ Hants England Wuhan Univ Technol Sch Automat Wuhan 430070 Hubei Peoples R China

In this paper, we propose a biologically inspired framework for robot learning based on demonstrations. The dynamic movement primitive (DMP), which is motivated by neurobiology and human behavior, is employed to model a robotic motion that is generalizable. However, the DMP method can only be used to handle a single demonstration. To enable the robot to learn from multiple demonstrations, the DMP is combined with the Gaussian mixture model (GMM) to integrate the features of multiple demonstrations, where the conventional GMM is further replaced by the fuzzy GMM (FGMM) to improve the fitting performance. Also, a novel regression algorithm for FGMM is derived to retrieve the nonlinear term of the DMP. Additionally, a neural network-based controller is developed for the robot to track the generated motions. In this network, the cerebellar model articulation controller is employed to compensate for the unknown robot dynamics. The experiments have been performed on a Baxter robot to demonstrate the effectiveness of the proposed methods.

关键词： Cerebellar model articulation controller (CMAC) dynamic movement primitive (DMP) fuzzy Gaussian mixture model (FGMM) Gaussian mixture regression (GMR) neural control robot learning from demonstrations (LfDs)

来源：评论

学校读者我要写书评

暂无评论

Optimal Feature Selection for EMG-Based Finger Force Estimation Using LightGBM Model 28

Optimal Feature Selection for EMG-Based Finger Force Estimat...

引用

28th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)

作者： Ye, Yuhang Liu, Chao Zemiti, Nabil Yang, Chenguang South China Univ Technol Key Lab Autonomous Syst & Networked Control Coll Automat Sci & Engn Guangzhou 510640 Peoples R China Univ Montpellier Dept Robot LIRMM CNRSUMR5506 F-34095 Montpellier France Univ West England Bristol Robot Lab Bristol BS16 1QY Avon England

ISBN: (纸本)9781728126227

Electromyogram (EMG) signal has been long used in human-robot interface in literature, especially in the area of rehabilitation. Recent rapid development in artificial intelligence (AI) has provided powerful machine learning tools to better explore the rich information embedded in EMG signals. For our specific application task in this work, i.e. estimate human finger force based on EMG signal, a LightGBM (Gradient Boosting Machine) model has been used. The main contribution of this study is the development of an objective and automatic optimal feature selection algorithm that can minimize the number of features used in the LightGBM model in order to simplify implementation complexity, reduce computation burden and maintain comparable estimation performance to the one with full features. The performance of the LightGBM model with selected optimal features is compared with 4 other popular machine learning models based on a dataset including 45 subjects in order to show the effectiveness of the developed feature selection method.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Robot Learning System Based on Adaptive Neural control and Dynamic Movement Primitives

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING systems 2019年第3期30卷 777-787页

作者： Yang, Chenguang Chen, Chuize He, Wei Cui, Rongxin Li, Zhijun South China Univ Technol Coll Automat Sci & Engn Key Lab Autonomous Syst & Networked Control Guangzhou 510640 Guangdong Peoples R China Univ Sci & Technol Beijing Sch Automat & Elect Engn Beijing 100083 Peoples R China Northwestern Polytech Univ Sch Marine Sci & Technol Xian 710072 Shaanxi Peoples R China Univ Sci & Technol China Dept Automat Hefei 230026 Anhui Peoples R China

This paper proposes an enhanced robot skill learning system considering both motion generation and trajectory tracking. During robot learning demonstrations, dynamic movement primitives (DMPs) are used to model robotic motion. Each DMP consists of a set of dynamic systems that enhances the stability of the generated motion toward the goal. A Gaussian mixture model and Gaussian mixture regression are integrated to improve the learning performance of the DMP, such that more features of the skill can be extracted from multiple demonstrations. The motion generated from the learned model can be scaled in space and time. Besides, a neural-network-based controller is designed for the robot to track the trajectories generated from the motion model. In this controller, a radial basis function neural network is used to compensate for the effect caused by the dynamic environments. The experiments have been performed using a Baxter robot and the results have confirmed the validity of the proposed methods.

关键词： Dynamic movement primitives (DMPs) Gaussian mixture model (GMM) neural network (NN) robot learning

来源：评论

学校读者我要写书评

暂无评论

Fisher Loss: A More Discriminative Feature Learning Method in Classification

Fisher Loss: A More Discriminative Feature Learning Method i...

引用

IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM)

作者： Ye, Yuhang Zhang, Tong Yang, Chenguang South China Univ Technol Key Lab Autonomous Syst & Networked Control Sch Automat Sci & Engn Guangzhou 510641 Peoples R China South China Univ Technol Sch Elect & Informat Guangzhou 510641 Peoples R China Univ West England Bristol Robot Lab Bristol BS16 1QY Avon England

ISBN: (纸本)9781728124933

Convolution neural networks(CNN) and softmax loss(cross entropy) function have been widely used in various classification tasks. It achieves better performance than MSE and other loss. However in most classification tasks, because of the high dimension, excessive noise of input samples, strong coupling of the extracted features, as well as the complicated output-input projection relationship, the features extracted by CNN have large intra-class variance and small inter-class distance, so different class of samples cannot be distinguished well, which will greatly reduce the accuracy of the classification. Aiming at these problems, we combine the Fisher discrimination criterion with the neural network and propose a more discriminative feature learning algorithm, fisher loss. In the experiment, the proposed algorithm is compared with the center loss, island loss, and other algorithms on MNIST datasets with two commonly used network architecture. It is found that our algorithm can better distinguish features and achieve higher classification accuracy.

关键词： Feature extraction Machine learning algorithms Propagation losses Neural networks Deep learning Task analysis

来源：评论

学校读者我要写书评

暂无评论

Robot learning human stiffness regulation for hybrid manufacture

引用

ASSEMBLY AUTOMATION 2018年第5期38卷 539-547页

作者： Zeng, Chao Yang, Chenguang Chen, Zhaopeng Dai, Shi-Lu South China Univ Technol Coll Automat Sci & Engn Key Lab Autonomous Syst & Networked Control Guangzhou Guangdong Peoples R China German Aerosp Ctr DLR Robot & Mech Ctr Wessling Germany

Purpose Teaching by demonstration (TbD) is a promising way for robot learning skills in human and robot collaborative hybrid manufacturing lines. Traditionally, TbD systems have only concentrated on how to enable robots to learn movement skills from humans. This paper aims to develop an extended TbD system which can also enable learning stiffness regulation strategies from humans. Design/methodology/approach Here, the authors propose an extended dynamical motor primitives (DMP) framework to achieve this goal. In addition to the advantages of the traditional ones, the authors' framework can enable robots to simultaneously learn stiffness and the movement from human demonstrations. Additionally, Gaussian mixture model (GMM) is used to capture the features of movement and of stiffness from multiple demonstrations of the same skill. Human limb surface electromyography (sEMG) signals are estimated to obtain the reference stiffness profiles. Findings The authors have experimentally demonstrated the effectiveness of the proposed framework. It shows that the authors approach could allow the robot to execute tasks in a variable impedance control mode with the learned movement trajectories and stiffness profiles. Originality/value In robot skill acquisition, DMP is widely used to encode robotic behaviors. So far, however, these DMP modes do not provide the ability to properly represent and generalize stiffness profiles. The authors argue that both movement trajectories and stiffness profiles should be considered equally in robot skill learning. The authors' approach has great potential of applications in the future hybrid manufacturing lines.

关键词： Human robot interaction Hybrid manufacturing Human-robot skill transfer Stiffness regulation

来源：评论

学校读者我要写书评

暂无评论

Position control of Continuum Manipulator with Twin-Pivot Compliant Joints 10

Position Control of Continuum Manipulator with Twin-Pivot Co...

引用

10th International Conference on Modelling, Identification and control (ICMIC)

作者： Liu, Xin Yang, Chenguang Dai, Shilu Feng, Ying South China Univ Technol Key Lab Autonomous Syst & Networked Control Sch Automat Sci & Engn Guangzhou 510641 Peoples R China

ISBN: (纸本)9781538654163

This paper proposes a novel closed-loop PD controller based on kinematic for continuum manipulator with twin-pivot compliant joints. The purpose of the twin-pivot compliant joints is to decrease the twisting angle caused by gravity of manipulator and payload. We build the forward and inverse kinematic to control the end-effector of continuum manipulator with twin-pivot compliant joints. In this paper, first we build forward and inverse kinematic of continuum manipulator with twin-pivot compliant joints. We then build the controller based on kinematic models for a continuum manipulator with 24 Degrees of Freedom (DoF). Finally, simulation studies are carried out to test the proposed approach.

关键词： Continuum manipulator Kinematics model Twin-pivot compliant joint Jacobian for hyper-redundant systems

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：