检索结果-内蒙古大学图书馆

IEEE International Conference on Real-time Computing and robotics (RCAR)

作者： Lina Tong Decheng Cui Chen Wang Liang Peng School of Mechanical Electronic and Information Engineering China University of Mining and Technology Beijing Beijing China State Key Laboratory of Management and Control for Complex Systems (SKLMCCS) Institute of Automation Chinese Academy of Science Beijing China

The traditional dynamical models show lower accuracy when predicting joint movement, and should be compensated. This paper proposed a model combined with the convolutional network(CNN) and temporal convolutional network(TCN) to compensate for the joint torque prediction values that are calculated from the sensing information. The experiments on the Cooperative Universal Robotic Assistant 6 DoF(CURA6) open dataset, including multi-load and multi-velocity, showed the prediction error can be reduced by 20% compared to other network models. Since there are many kinds of joint movement information, the input data form of the deep learning model should be improved. Thus, the kinetic linearization model is proposed to modify the input of sensing data. According to the different motion types of the CURA6 dataset, comparative experiments were taken, and the mean absolute error was less than 6.8%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Position control of X-Y Precision Motion Stage Based on Iterative Learning and Model Prediction

Position Control of X-Y Precision Motion Stage Based on Iter...

引用

Chinese control and Decision Conference, CCDC

作者： Guopeng Zhang Tao Zhang Qingxin Li Li Chen Hualiang Zhang Jingzhe Fang Yiqiang Zhang School of Artificial Intelligence Shenyang University of Technology Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang Institute of Automation Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China School of Artificial Intelligence Shenyang University of Technology Shenyang China School of Electrical Engineering Shenyang University of Technology Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China

ISBN: (数字)9798350387780

ISBN: (纸本)9798350387797

The X-Y precision planar motion stage is a highly advanced motion control device that has been widely utilized in various precision motion control fields. This platform achieves precise positioning and control of objects through precise motion along the X and Y axes, providing an outstanding solution for scientific research, industrial production, and other applications. The X-Y platform consists of two permanent magnet synchronous linear motors. In the three-loop control of the motor, when the current loop uses a PID controller, there is a problem in tuning the parameters. This paper replaces the original PID controller in the current loop with a model predictive controller. Simultaneously, addressing the issue of improving the tracking accuracy of the X-Y precision planar motion stage, a forgetting high-order variable gain PD-type iterative learning control is proposed. Subsequently, both of these control methods are applied to the Simulink model of the X-Y precision motion stage motor. This not only solves the complex problem of tuning the motor current loop parameters but also improves the tracking accuracy of the X-Y precision motion stage. The results indicate that when using both model predictive controllers and forgetting high-order variable gain PD-type iterative learning controllers for motor control, not only can the tuning of current loop parameters be omitted, but also tracking errors can be effectively reduced, and the system convergence speed can be accelerated.

关键词： Tracking loops Trajectory tracking Predictive models Motors Mathematical models Motion control Tuning

来源：评论

学校读者我要写书评

暂无评论

Research on Distributed Intelligent Protection Strategy of distribution network based on Reinforcement Learning

Research on Distributed Intelligent Protection Strategy of d...

引用

Information Technology,Big Data and Artificial Intelligence (ICIBA), International Conference on IEEE International Conference on

作者： Shijie Cui Peng Zeng Ende Hu State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China University of Chinese Academy of Sciences Beijing China State Grid Shaoxing Power Supply Company Shaoxing China

ISBN: (纸本)9781665428781

In the context of building a new power system with new energy as the main part, the operation mode of distribution network is more complex, and the traditional distribution network protection strategy can hardly meet the demand, so this paper proposes a distributed intelligent protection strategy for distribution network based on reinforcement learning. This paper analyzes the impact of new energy resources access on distribution network relay protection, and presents an intelligent protection algorithm model based on deep reinforcement learning. The structure of intelligent protection device is designed, and the distribution network distributed protection scheme based on intelligent protection device is proposed. Finally, the algorithm training process is given, and the experimental environment is built.

关键词： Training Uncertainty Power supplies Protective relaying Distribution networks Reinforcement learning Power system stability

来源：评论

学校读者我要写书评

暂无评论

Simulation of Liquid Level Cascade control System Based on Genetic Fuzzy PID

Simulation of Liquid Level Cascade Control System Based on G...

引用

robotics, control and Automation Engineering (RCAE), International Conference on

作者： Jizhi Mao Zhijia Yang Shusheng Zhang College of Automation and Electrical Engineering Shenyang Ligong University Shenyang China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China

ISBN: (数字)9781665459419

ISBN: (纸本)9781665459426

The model design and basic principle of liquid level control system are described. In order to improve the dynamic response of liquid level control, the overshoot and steady-state error accuracy of the system are improved. In this paper, we apply the conventional PID controller to the single-loop system and the cascade system respectively, and introduce the fuzzy control algorithm based on the conventional PID control algorithm to design a cascade parameter self-adjusting fuzzy PID controller, Then use genetic algorithm to optimize fuzzy control rules to generate genetic fuzzy PID controller. The MATLAB/Simulink simulation results show that, compared with the traditional PID control, the genetic fuzzy PID control has better control effect and anti-interference ability, and has good control performance.

关键词： Fuzzy control PI control Liquids Automation Heuristic algorithms Transfer functions Genetics

来源：评论

学校读者我要写书评

暂无评论

Research on optical properties of human hepatoma cells using terahertz time-domain spectroscopy

Research on optical properties of human hepatoma cells using...

引用

Ultrafast Phenomena and Terahertz Waves (ISUPTW), 2023 International Symposium on

作者： Hanxiao Guan Weihang Qiu Yehao Ma Liangfei Tian Yuqi Cao Guangxin Zhang State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Hangzhou People’s Republic of China College of Biomedical Engineering and Instrument Science Zhejiang University Hangzhou People’s Republic of China Robotics Institute Ningbo University of Technology Ningbo China

Terahertz technology is a non-invasive and label-free inspection method, promising for applications in various fields, especially in biomedical diagnosis. Terahertz radiation is capable for cell physiological and pathological status recognition due to its sensitivity to cell composition and structural information of biomacromolecular. In this paper, the transmission properties of glass, polymethyl methacrylate and polypropylene in THz regime were compared and polypropylene was selected as the petri dish material for cell adhesion due to its high transmission of terahertz wave. The time-domain and frequency-domain spectra, refractive index and absorption coefficient of hepatoma cell line Huh7 and normal cell line MIHA were analyzed. The experimental results showed significant distinction between the terahertz characteristic spectra of hepatoma cells and normal cells. This work can be helpful for applying terahertz technology in cancer detection at the cellular level.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Intelligent Protection Technology for Distribution Network with Distributed Generation

Research on Intelligent Protection Technology for Distributi...

引用

IEEE Advanced Information Technology, Electronic and Automation control Conference (IAEAC)

作者： Shijie Cui Peng Zeng Zhongfeng Wang Chunhe Song State Key Laboratory of Robotics Chinese Academy of Sciences Shenyang China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China University of Chinese Academy of Sciences Beijing China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China

ISBN: (数字)9781728180281

ISBN: (纸本)9781728180298

Connecting large-scale distributed generation to a distribution network is complex as it is difficult to set the current protection limit within a traditional distribution network. This paper proposes a distributed protection and control scheme based on reinforcement learning for a distribution network connected to a distributed generation system. This research introduces the idea of transforming this distribution network protection problem into a multi-agent reinforcement learning problem. The concrete construction method of the reinforcement learning environment and deep Q-learning network is described. The algorithm training process is presented and the algorithm training and verification environment is built.

关键词： Training Uncertainty Power supplies Distribution networks Reinforcement learning Power system stability Distributed power generation

来源：评论

学校读者我要写书评

暂无评论

Simultaneously Calibration of Multi Hand-Eye Robot System Based on Graph

arXiv

引用

arXiv 2023年

作者： Zhou, Zishun Ma, Liping Liu, Xilong Cao, Zhiqiang Yu, Junzhi The Institute of Automation Chinese Academy of Sciences Beijing100190 China The College of Electrical Engineering and Computer Science Australian National University Canberra2601 Australia The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China The School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China The State Key Laboratory for Turbulence and Complex System Department of Advanced Manufacturing and Robotics BIC-ESAT College of Engineering Peking University Beijing100871 China

Precise calibration is the basis for the vision-guided robot system to achieve high-precision operations. systems with multiple eyes (cameras) and multiple hands (robots) are particularly sensitive to calibration errors, such as micro-assembly systems. Most existing methods focus on the calibration of a single unit of the whole system, such as poses between hand and eye, or between two hands. These methods can be used to determine the relative pose between each unit, but the serialized incremental calibration strategy cannot avoid the problem of error accumulation in a large-scale system. Instead of focusing on a single unit, this paper models the multi-eye and multi-hand system calibration problem as a graph and proposes a method based on the minimum spanning tree and graph optimization. This method can automatically plan the serialized optimal calibration strategy in accordance with the system settings to get coarse calibration results initially. Then, with these initial values, the closed-loop constraints are introduced to carry out global optimization. Simulation experiments demonstrate the performance of the proposed algorithm under different noises and various hand-eye configurations. In addition, experiments on real robot systems are presented to further verify the proposed method. © 2023, CC BY-SA.

关键词： Multipurpose robots

来源：评论

学校读者我要写书评

暂无评论

Flight Transition control for Ducted Fan UAV with Saturation on control Surfaces

Flight Transition Control for Ducted Fan UAV with Saturation...

引用

2021 International Conference on Unmanned Aircraft systems, ICUAS 2021

作者： Cheng, Zihuan Pei, Hailong College of Automation Science and Engineering South China University of Technology Guangzhou510640 China Key Laboratory of Autonomous Systems and Networked Control Unmanned Aerial Vehicle Systems Engineering Technology Research Center of Guangdong College of Automation Science and Engineering South China University of Technology Ministry of Education Guangzhou510640 China

ISBN: (纸本)9780738131153

In this paper, we focus on the hover/high-speed-cruising transition flight control of a ducted fan unmanned aerial vehicle (UAV), in which saturation on control surfaces is taken into consideration. To achieve full-envelope flight control, we propose an adaptive cascaded structure on the velocity tracking control for the nonlinear aircraft system. By introducing adaptive neural network, the closed-loop system tracks a prescribed reference system with all the nonlinear tracking errors well canceled. In the meanwhile, to tackle the control surface saturation, we propose a control effectiveness enhancement (CEE) algorithm in attaining sufficient control moment to the ducted fan vehicle. Under the proposed cascaded adaptive control scheme in conjunction with the CEE algorithm, the state tracking performance is proved to be bounded when encountering surface saturation. Finally, comparison experiments in terms of the forward and backward flight transition are conducted on the ducted fan UAV. The results are satisfactory and convincing in exhibiting the flight transition course that demonstrates the effectiveness of the proposed method. © 2021 IEEE.

关键词： Closed loop systems

来源：评论

学校读者我要写书评

暂无评论

Generating Datasets for Real-Time Scheduling on 5g New Radio

SSRN

引用

SSRN 2022年

作者： Jin, Xi Chai, Haoxuan Xia, Changqing Xu, Chi Zeng, Peng Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang110016 China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China University of Chinese Academy of Sciences Beijing100049 China

5G is an advanced solution for industrial wireless motion control. However, since the scheduling model of 5G new radio (NR) is more complicated than those of other wireless networks, existing real-time scheduling algorithms cannot be used to improve the 5G performance. This results in NR resources not being fully available for industrial systems. Supervised learning has been widely used to solve complicated problems, and its advantages have been demonstrated in multiprocessor scheduling. One of the main reasons why supervised learning has not been used for 5G NR scheduling is the lack of training datasets. Therefore, in this paper, we propose two methods based on optimization modulo theories (OMT) and satisfiability modulo theories (SMT) to generate training datasets for 5G NR scheduling. Our OMT-based method contains fewer variables than existing work so that the Z3 solver can find optimal solutions quickly. To further reduce the solution time, we transform the OMT-based method into an SMT-based method and tighten the search space of SMT based on three theorems and an algorithm. Finally, we conduct extensive evaluations. The evaluation results indicate that our SMT-based method reduces the solution time by 74.7% compared to existing ones. © 2022, The Authors. All rights reserved.

关键词： Scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

LinK3D: Linear keypoints Representation for 3D LiDAR Point Cloud

arXiv

引用

arXiv 2022年

作者： Cui, Yunge Zhang, Yinlong Dong, Jiahua Sun, Haibo Chen, Xieyuanli Zhu, Feng The Key Laboratory of Opto-Electronic Information Processing Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China The Key Laboratory of Networked Control Systems Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China The State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Science Shenyang China The Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110016 China The University of Chinese Academy of Sciences Beijing101408 China The Shanghai Institute of Microsystem and Information Technology Chinese Academy of Sciences Shanghai China The College of Intelligence Science and Technology National University of Defense Technology Changsha China

Feature extraction and matching are the basic parts of many robotic vision tasks, such as 2D or 3D object detection, recognition, and registration. As is known, 2D feature extraction and matching have already achieved great success. Unfortunately, in the field of 3D, the current methods may fail to support the extensive application of 3D LiDAR sensors in robotic vision tasks due to their poor descriptiveness and inefficiency. To address this limitation, we propose a novel 3D feature representation method: Linear keypoints representation for 3D LiDAR point cloud, called LinK3D. The novelty of LinK3D lies in that it fully considers the characteristics (such as the sparsity and complexity) of LiDAR point clouds and represents the keypoint with its robust neighbor keypoints, which provide strong constraints in the description of the keypoint. The proposed LinK3D has been evaluated on three public datasets, and the experimental results show that our method achieves great matching performance. More importantly, LinK3D also shows excellent real-time performance, faster than the sensor frame rate at 10 Hz of a typical rotating LiDAR sensor. LinK3D only takes an average of 30 milliseconds to extract features from the point cloud collected by a 64-beam LiDAR and takes merely about 20 milliseconds to match two LiDAR scans when executed on a computer with an Intel Core i7 processor. Moreover, our method can be extended to LiDAR odometry task, and shows good scalability. We release the implementation of our method at https://***/YungeCui/LinK3D. Copyright © 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

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：