检索结果-内蒙古大学图书馆

Workshop on Predictive control of Electrical Drives and Power Electronics (PRECEDE)

作者： Rongsheng Lin Su-Dan Huang Guang-Zhong Cao Chao Wu Guangdong Key Laboratory of Electromagnetic Control and Intelligent Robots College of Mechatronics and Control Engineering Shenzhen University Shenzhen China

This paper presents model-predictive-control-based(MPC) speed control strategies of permanent magnet synchronous motors to improve the control performance of these motors. For the surface-mounted permanent magnet synchronous motors, the dynamic model is built, and the system control structure is presented. In addition, the multistep model predictive controllers are developed under the unconstrained optimal problem, and the constrained control action is performed by adding the saturation module after the control action. Moreover, four different speed control strategies are compared via simulation, including the proportional-integral(PI) speed control with PI current control, PI speed control with MPC current control, MPC speed control with PI current control, and MPC speed control with MPC current control. The comparison result reveals the improvements of model predictive control in current control compared to conventional PI control through its flexibility of cost function to optimate the control input and also demonstrates the advantages of PI control in minimizing the error with robustness and anti-disturbance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A KPRN-Based Method for Weld Seam Point Recognition with Strong Robustness

A KPRN-Based Method for Weld Seam Point Recognition with Str...

引用

International Conference on mechatronics and Machine Vision in Practice (M2VIP)

作者： Xinghua Yu Guangzhong Cao Hongjin Hu Zhiyong Hu Yu Lei Pengfei Wang Guangdong Key Laboratory of Electromagnetic Control and Intelligent Robots College of Mechatronics and Control Engineering Shenzhen University Shenzhen China

In the domain of automated welding, achieving accurate recognition of weld seam points is a formidable challenge due to the prevailing arc glare and spatter interferences. To address this challenge, a weld seam key point recognition method is proposed to improve the welding seam recognition ability of welding robots. Central to this approach is the development of an end-to-end key point regression network (KPRN), which leverages heatmaps to directly predict the coordinates of weld seam key points. The KPRN is designed with a lightweight feature extraction layer, tailored for efficient image processing in welding scenarios. Multi-scale feature fusion is employed to expand the receptive field of the network, thereby improving feature extraction. Moreover, noise interference is effectively addressed through spatial pyramid pooling (SPP) and squeeze-and-excitation (SE) modules. Notably, the network employs a heatmap as a loss function, enabling precise recognition of weld seam key points. The effectiveness of the proposed method is verified through experiments. The proposed method can accurately pinpoint weld seam key points in the presence of arc glare and spatter interference. The weld seam point recognition accuracy achieves greater than 98.6%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Recursive-Extended-Least-Squares-Based Model Predictive Position control for the Planar Switched Reluctance Motor

Recursive-Extended-Least-Squares-Based Model Predictive Posi...

引用

International Conference on Electrical Machines and Systems (ICEMS)

作者： Hong-Li Li Guang-Zhong Cao Su-Dan Huang Hong-Jin Hu Hao-Tian Wang Guangdong Key Laboratory of Electromagnetic Control and Intelligent Robots College of Mechatronics and Control Engineering Shenzhen University Shenzhen China

High-precision trajectory tracking is necessary for planar switched reluctance motors (PSRMs). In this paper, parameter identification is considered, and a model predictive position control (MPPC) algorithm is proposed based on recursive extended least squares (RELS) to enhance the trajectory tracking performance of the laboratory-developed PSRM. The mathematic model and parameter identification model of the PSRM are given. The predictive model, cost function, and control law of the MPPC based on RELS are derived. The effectiveness of the proposed RELS-based MPPC algorithm is verified via simulation and experiment.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Linear Active Disturbance Rejection controller for the 3-DOF Repulsive Magnetic Levitation System

Linear Active Disturbance Rejection Controller for the 3-DOF...

引用

International Conference on Electrical Machines and Systems (ICEMS)

作者： Ming-Hong Guo Guang-Zhong Cao Su-Dan Huang Yu Lei Hao-Tian Wang Xin Yuan Guangdong Key Laboratory of Electromagnetic Control and Intelligent Robots College of Mechatronics and Control Engineering Shenzhen University Shenzhen China

In the control of the 3-DOF repulsive magnetic levitation system, it is difficult to achieve stable levitation due to the inherent nonlinearity and instability of the system with external disturbance. To enhance the disturbance rejection ability of the system, this paper proposes a linear active disturbance rejection control (LADRC) algorithm. A linear active disturbance rejection controller is developed for the system, which consists of linear states error feedback and extended state observer. The mathematical model is established. The results of simulation and experiments verify the effectiveness and anti-turbulence of the controller.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel Sliding Mode control Method for Permanent Magnet Synchronous Motor

A Novel Sliding Mode Control Method for Permanent Magnet Syn...

引用

International Conference on Electrical Machines and Systems (ICEMS)

作者： Haohan Zhou Guangzhong Cao Hongjin Hu Haotian Wang Guangdong Key Laboratory of Electromagnetic Control and Intelligent Robots College of Mechatronics and Control Engineering Shenzhen University Shenzhen China

The permanent magnet synchronous motor (PMSM) requires a high tracking response and static accuracy. To achieve this purpure, we present a novel approach for enhancing the speed control of PMSM by integrating a sliding mode controller with an optimized proportional resonant (SMC-PR) controller. The SMC can improve the disturbance rejection performance. The optimized PR controller can achieve steady-state tracking accuracy. With the combination of these two controllers, the PMSM control system can obtain high steady-state performance, fast dynamic response, and strong robust performance. The simulation of the proposed controller is performed on the MATLAB/ Simulink platform. The efficacy of the introduced controller is verified through comprehensive simulation results and analysis.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Video2Reward: Generating Reward Function from Videos for Legged Robot Behavior Learning 27

Video2Reward: Generating Reward Function from Videos for Leg...

引用

27th European Conference on Artificial Intelligence, ECAI 2024

作者： Zeng, Runhao Zhou, Dingjie Liang, Qiwei Liu, Junlin Li, Hui Huang, Changxin Li, Jianqiang Hu, Xiping Sun, Fuchun Artificial Intelligence Research Institute Shenzhen MSU-BIT University China College of Mechatronics and Control Engineering Shenzhen University China College of Computer Science and Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Department of Computer Science and Technology Tsinghua University China

ISBN: (纸本)9781643685489

Learning behavior in legged robots presents a significant challenge due to its inherent instability and complex constraints. Recent research has proposed the use of a large language model (LLM) to generate reward functions in reinforcement learning, thereby replacing the need for manually designed rewards by experts. However, this approach, which relies on textual descriptions to define learning objectives, fails to achieve controllable and precise behavior learning with clear directionality. In this paper, we introduce a new video2reward method, which directly generates reward functions from videos depicting the behaviors to be mimicked and learned. Specifically, we first process videos containing the target behaviors, converting the motion information of individuals in the videos into keypoint trajectories represented as coordinates through a video2text transforming module. These trajectories are then fed into an LLM to generate the reward function, which in turn is used to train the policy. To enhance the quality of the reward function, we develop a video-assisted iterative reward refinement scheme that visually assesses the learned behaviors and provides textual feedback to the LLM. This feedback guides the LLM to continually refine the reward function, ultimately facilitating more efficient behavior learning. Experimental results on tasks involving bipedal and quadrupedal robot motion control demonstrate that our method surpasses the performance of state-of-the-art LLM-based reward generation methods by over 37.6% in terms of human normalized score. More importantly, by switching video inputs, we find our method can rapidly learn diverse motion behaviors such as walking and running. © 2024 The Authors.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

Comparison Analysis on control-Increment-Based and control-Quantity-Based Predictive controls of Permanent Magnet Synchronous Motors

Comparison Analysis on Control-Increment-Based and Control-Q...

引用

Workshop on Predictive control of Electrical Drives and Power Electronics (PRECEDE)

作者： Lei Ling Su-Dan Huang Guang-Zhong Cao Hong Qiu Guangdong Key Laboratory of Electromagnetic Control and Intelligent Robots College of Mechatronics and Control Engineering Shenzhen University Shenzhen China

In order to improve the robustness and to solve the parameter setting problem of PI controller in traditional vector control of permanent magnet synchronous motors, a comparison analysis on model predictive control based on control increment and based on control quantity is presented in this paper. Aiming at the problem that the output current and voltage can only be limited indirectly, model predictive controllers based on control increment or control quantity are developed for speed and current control. For the problem that the speed control cannot deal with the added load disturbance, the load disturbance observer is used for the feedforward compensation. Based on the mathematical model of permanent magnet synchronous motors, the prediction models based on control increment or control quantity are established, respectively. Then, the optimal control sequence is derived by combining the designed cost function. Finally, the proposed method is verified by simulation. The comparison analysis of the control-increment-based and control-quantity-based model predictive control methods are effectively shown through the comparison results, and the effectiveness of the proposed method is verified.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fast-terminal sliding mode control based on dynamic boundary layer for lower limb exoskeleton rehabilitation robot 11

Fast-terminal sliding mode control based on dynamic boundary...

引用

11th IEEE Annual International Conference on CYBER Technology in Automation, control, and Intelligent Systems, CYBER 2021

作者： Cao, Sheng-Bin Cao, Guang-Zhong Zhang, Yue-Peng Ling, Zi-Qin He, Bin-Bin Huang, Su-Dan Guangdong Key Laboratory of Electromagnetic Control and Intelligent Robots Shenzhen Key Laboratory of Electromagnetic Control College of Mechatronics and Control Engineering Shenzhen518060 China

ISBN: (纸本)9781665425278

Aiming at the chattering problem of sliding mode control in the trajectory tracking of lower limb exoskeleton rehabilitation robot (LLERR), this paper proposes a fast-terminal sliding mode control based on dynamic boundary layer (DFTSMC) for LLERR. First, based on the fast-terminal sliding mode surface and the double power reaching law, the compensation term of the control law is designed. Then, a dynamic boundary layer is designed to suppress the chattering of the system state. Finally, based on the virtual prototype of LLERR, a co-simulation is carried out with Matlab and Recurdyn multi-body dynamics software. The traditional PID control based on the computed torque method, the traditional fast-terminal sliding mode control (FTSMC) and the DFTSMC were compared. The control performance of fast terminal sliding mode control and the simulation results show that the DFTSMC improves the convergence speed of the system state, suppress the chattering of the sliding mode control and enhances the robust performance of LLERR. © 2021 IEEE.

关键词： Sliding mode control

来源：评论

学校读者我要写书评

暂无评论

An Improved Convolutional Neural Network for Rolling Bearing Fault Diagnosis 11

An Improved Convolutional Neural Network for Rolling Bearing...

引用

11th IEEE Annual International Conference on CYBER Technology in Automation, control, and Intelligent Systems, CYBER 2021

作者： Ling, Zi-Qin Cao, Guang-Zhong Zhang, Yue-Peng Guangdong Key Laboratory of Electromagnetic Control and Intelligent Robots Shenzhen Key Laboratory of Electromagnetic Control College of Mechatronics and Control Engineering Shenzhen518060 China

ISBN: (纸本)9781665425278

Aiming at the problems of low accuracy of the existing fault diagnosis methods for rolling bearings, an improved convolution neural network model for rolling bearing fault diagnosis is proposed. By training the sub-convolution neural network model (sub-CNN) for a single fault, the sub-CNN is combined into a sub-CNN group, and the transfer learning method is used to transfer to the combiner. The combiner is composed of several fully connected layers. The proposed neural network model solves the problem that the existing end-to-end neural network model is not accurate and improves the accuracy of fault diagnosis. The experiment results show that the classification accuracy of the improved convolution neural network is 99.95%, and the F1 value is 0.9966. Compared with existing models, the highest classification accuracy of the proposed model is improved by 11.4%, which is demonstrated that the proposed model is higher than the existing models. The superiority of our model is proved. © 2021 IEEE.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

HTEC foot:A novel foot structure for humanoid robots combining static stability and dynamic adaptability

引用

Defence Technology(防务技术) 2025年第2期44卷 30-51页

作者： Jintao Zhang Xuechao Chen Zhangguo Yu Lianqiang Han Zhifa Gao Qingrui Zhao Gao Huang Ke Li Qiang Huang School of Mechatronical Engineering Beijing Institute of TechnologyNo.5South StreetZhongguancunHaidian DistrictBeijing100081China Key Laboratory of Biomimetic Robots and Systems Ministry of EducationNo.5South StreetZhongguancunHaidian DistrictBeijing100081China School of Information Science and Technology Beijing University of TechnologyNo.100PingleyuanChaoyang DistrictBeijing100124China Innovation Center for Control Actuators Beijing Institute of Precision Mechatronics and ControlsDonggaodiFengtai DistrictBeijing100076China

Passive bionic feet,known for their human-like compliance,have garnered attention for their potential to achieve notable environmental *** this paper,a method was proposed to unifying passive bionic feet static supporting stability and dynamic terrain adaptability through the utilization of the Rigid-Elastic Hybrid(REH)dynamics ***,a bionic foot model,named the Hinge Tension Elastic Complex(HTEC)model,was developed by extracting key features from human ***,the kinematics and REH dynamics of the HTEC model were *** on the foot dynamics,a nonlinear optimization method for stiffness matching(NOSM)was ***,the HTEC-based foot was constructed and applied onto BHR-B2 humanoid *** foot static stability is *** enhanced adaptability is observed as the robot traverses square steel,lawn,and cobblestone *** proposed design method and structure,the mobility of the humanoid robot is improved.

关键词： Humanoid robot Bionic structure Passive foot structure Rigid-elastic hybrid dynamics model Optimal stiffness matching

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：