检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Ren, Zihao Wang, Lei Yi, Xinlei Wang, Xi Yuan, Deming Yang, Tao Wu, Zhengguang Shi, Guodong State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University Hangzhou310027 China College of Electronics and Information Engineering Tongji University China School of Electrical Engineering Telecommunications University of New South Wales Sydney Australia School of Automation Nanjing University of Science and Technology China State Key Laboratory of Synthetical Automation for Process Industries Northeastern University China Australian Centre for Robotics School of Aerospace Mechanical and Mechatronic Engineering The University of Sydney SydneyNSW2006 Australia

Several data compressors have been proposed in distributed optimization frameworks of network systems to reduce communication overhead in large-scale applications. In this paper, we demonstrate that effective information compression may occur over time or space during sequences of node communications in distributed algorithms, leading to the concept of spatio-temporal compressors. This abstraction classifies existing compressors as spatio-temporal compressors, with their effectiveness described by constructive stability criteria from nonlinear system theory. Subsequently, we apply these spatio-temporal compressors to standard continuous-time consensus flows and distributed prime-dual flows, establishing conditions ensuring convergence. Additionally, we introduce a novel observer-based distributed primal-dual continuous flow integrated with spatio-temporal compressors, which provides broader convergence conditions. These continuous flows achieve exponential convergence to the global optimum when the objective function is strongly convex and can be discretized using Euler approximations. Finally, numerical simulations illustrate the versatility of the proposed spatio-temporal compressors and verify the convergence of algorithms. Copyright © 2024, The Authors. All rights reserved.

关键词： Stability criteria

来源：评论

学校读者我要写书评

暂无评论

An Optimization Method for SLAM Feature Point Extraction in Fuzzy Scenes

An Optimization Method for SLAM Feature Point Extraction in ...

引用

Electrical Engineering and Automation (IFEEA), International Forum on

作者： Yunmeng Wang Long Cui Zaoming Liu Nailong Liu State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Shenyang China University of Chinese Academy of Sciences Beijing China Science and Technology on Space Intelligent Control Laboratory Beijing Institute of Control Engineering Beijing China

In order to solve the problem that image blur is easily caused by camera shaking of micro-robots during surgical navigation, which leads to the accumulation of SLAM errors, this paper studies the feature point extraction optimization method based on deep learning in fuzzy scenes, proposes an improved defuzzification network, and finally applies the network to the front end of SLAM, and conducts experimental verification on the open data set TUM. The results show that the proposed algorithm significantly improves the accuracy of front-end feature extraction and matching.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptive Learning-Based Mpc Strategy for Drift Vehicles

SSRN

引用

SSRN 2024年

作者： Zhou, Bei Hu, Cheng Zeng, Jun Shi, Yao Xie, Lei Su, Hongye The State Key Laboratory of Industrial Control Technology Zhejiang University 38 Zheda Road Xihu District Hang zhou Zhejiang310027 China Hybrid Robotics Group the Department of Mechanical Engineering UC Berkeley United States

Drift vehicle control offers valuable insights to support safe autonomous driving in extreme conditions, which hinges on tracking a particular path while maintaining the vehicle states near the drift equilibrium points (DEP). However, conventional tracking methods are not adaptable for drift vehicles due to their opposite steering angle and yaw rate. In this paper, we propose an adaptive path tracking (APT) control method to dynamically adjust drift states to follow the reference path, improving the commonly utilized predictive path tracking methods with released computation burden. Furthermore, existing control strategies necessitate a precise system model to calculate the DEP, which can be more intractable due to the highly nonlinear drift dynamics and sensitive vehicle parameters. To tackle this problem, an adaptive learning-based model predictive control (ALMPC) strategy is proposed based on the APT method, where an upper-level Bayesian optimization is employed to learn the DEP and APT control law to instruct a lower-level MPC drift controller. This hierarchical system architecture can also resolve the inherent control conflict between path tracking and drifting by separating these objectives into different layers. The ALMPC strategy is verified on the Matlab-Carsim platform, and simulation results demonstrate its effectiveness in controlling the drift vehicle to follow a clothoid-based reference path even with the misidentified road friction parameter. © 2024, The Authors. All rights reserved.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

An Attention-LSTM-based Fault Diagnosis Method for Satellite Attitude control System

An Attention-LSTM-based Fault Diagnosis Method for Satellite...

引用

Fully Actuated System Theory and Applications (CFASTA), Conference on

作者： Siyuan Ma Sheng Gao Xiaozhong Zuo Zhengyang Lv Chenyang Zou State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China China-Portugal Belt and Road Joint Laboratory on Space & Sea Technology Advanced Research Shanghai China College of Electrical and Control Engineering Shenyang Jianzhu University Shenyang China

ISBN: (数字)9798350373691

ISBN: (纸本)9798350373707

This study proposes a fault diagnosis method based on attention-LSTM for the satellite attitude control system. First, the hidden correlation information between high-dimensional variables is exploited through the variable attention layer. Then, deep temporal features are extracted with using the LSTM network layer. Finally, the time attention layer is introduced to increase the weight of important temporal information, effectively avoiding the problem of being forgotten due to too long input sequence and too many deep temporal features. The identification accuracy of slow fault in satellite attitude control system can be improved. The method is validated using data from the satellite semi-physical simulation platform, which demonstrates the effectiveness of this method.

关键词： Fault diagnosis Analytical models Visualization Satellites Recurrent neural networks Correlation Attitude control

来源：评论

学校读者我要写书评

暂无评论

Health monitoring of pressure transmitter sensing line based on convolutional neural network

Health monitoring of pressure transmitter sensing line based...

引用

12th International Conference on Quality, Reliability, Risk, Maintenance, and Safety Engineering (QR2MSE 2022)

作者： T. He A. Xu K. Wang P. Zeng Laboratory of Industrial Control Network and System State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang People's Republic of China

Blockages of pressure transmitter sensing line are a recurring problem in nuclear plants. The traditional solution is to purge them with nitrogen periodically, which is time consuming and radiation intensive. It is thus desirable to monitor the status of sensing lines on-site. The noise analysis method is a promising method for sensing line health monitoring. However, the existing noise analysis methods, which evaluate the sensing line status by analyzing time domain or frequency domain features of process noise signal, are susceptible to working conditions of pressure transmitters. Further, blockage degree of the sensing line can not be determined by existing methods. Therefore, this paper proposes a machine learning based noise analysis method for health monitoring of pressure transmitter sensing line, in which 1-D Convolutional Neural Network (CNN) is used to extract features from process noise signals. Experimental results show that the proposed method achieved satisfactory results in diagnosis accuracy, false alarm rate and robustness of the model under different working conditions. Further, blockage degree of sensing line can also be evaluated

关键词：

来源：评论

学校读者我要写书评

暂无评论

Intelligent electricity consumption forecasting and electricity-theft analysis method based on deep learning

Intelligent electricity consumption forecasting and electric...

引用

Electronic Information Engineering and Computer Technology (EIECT), International Conference on

作者： Shimao Yu Chunhe Song Pengpei Gao Haiyang Zheng Key Laboratory of Networked Control Systems Shenyang Institute of Automation 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

Residential electricity consumption data have great mining value for electricity-theft analysis and electricity consumption forecasting. This paper designs an intelligent electricity consumption forecasting and electricity-theft analysis method based on deep learning. Firstly, the power consumption data of a single user is converted into multi-period data through preprocessing, and the data forecasting is realized by designing a deep neural network model. The electricity-theft data are first amplified through user’s power data and electricity-theft labels. And then the time series are converted into two-dimensional tensors for classification and recognition by deep CNN. The classification accuracy of electricity-theft reaches 92.2% compared with RNN method.

关键词： Deep learning Training Analytical models Power demand Tensors Computational modeling Time series analysis

来源：评论

学校读者我要写书评

暂无评论

Real-Time Marker Localization Learning for GelStereo Tactile Sensing

Real-Time Marker Localization Learning for GelStereo Tactile...

引用

2022 IEEE International Conference on robotics and Biomimetics, ROBIO 2022

作者： Liu, Shujuan Cui, Shaowei Zhang, Chaofan Cai, Yinghao Wang, Shuo University of Science and Technology Beijing China Institute of Automation Chinese Academy of Sciences State Key Laboratory of Management and Control for Complex Systems Beijing100190 China University of Chinese Academy of Sciences School of Artificial Intelligence Beijing100049 China Chinese Academy of Sciences Institute of Automation Beijing100190 China The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China The Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Shanghai200031 China

ISBN: (纸本)9781665481090

Visuotactile sensing technology is becoming more popular in tactile sensing, but the effectiveness of the existing marker detection/localization methods remains to be further explored. Instead of contour-based blob detection, this paper presents a learning-based marker localization network for GelStereo visuotactile sensing called Marknet. Specifically, the Marknet presents a grid regression architecture to incorporate the distribution of the GelStereo markers. Furthermore, a marker rationality evaluator (MRE) is modelled to screen suitable prediction results. The experimental results show that the Marknet combined with MRE achieves 93.90% precision for irregular markers in contact areas, which outperforms the traditional contour-based blob detection method by a large margin of 42.32%. Meanwhile, the proposed learning-based marker localization method can achieve better realtime performance beyond the blob detection interface provided by the OpenCV library through GPU acceleration, which we believe will lead to considerable perceptual sensitivity gains in various robotic manipulation tasks. © 2022 IEEE.

关键词： Chemical detection

来源：评论

学校读者我要写书评

暂无评论

Accelerated identification method of industrial instrument based on yolov5

Accelerated identification method of industrial instrument b...

引用

Image Processing, Computer Vision and Machine Learning (ICICML), International Conference on

作者： Shimao Yu Haiyang Zheng Chunhe Song Pengpei Gao Key Laboratory of Networked Control Systems Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Shenyang China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781665464697

There are many problems in industrial instrument detection, such as complex background and visual Angle, etc. Traditional machine learning methods are difficult to achieve high-precision object detection and real-time monitoring applications. This paper proposes an accelerated identification method of industrial instruments based on YOLOv5. First, sample data are collected on site for image annotation, and YOLOv5 network structure is designed for transfer learning training, so as to realize image recognition of four types of industrial instruments. After that, the model is accelerated based on TensorRT on Jetson TX2 platform. The speed of instrument online detection reached 30 fps and mAP0.5 is 0.989.

关键词： Training Visualization Computer vision Image recognition Instruments Computational modeling Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Design of Cascaded Model Predictive controller for Modular Robot Joints

Design of Cascaded Model Predictive Controller for Modular R...

引用

第34届中国控制与决策会议

作者： Wang Bolun Zhang Tao Shi Zhengjin Zhang Hualiang School of Automation and Electrical Engineering Shenyang University of Technology Shenyang Institute of Automation Chinese Academy of Sciences Key Laboratory of Networked Control Systems Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences

As the core driving force providers in the robot system of next generation,modular robot joint's motion and power performance directly affects the overall motion control effect of robot *** design starts from the servo control of the modular robot joint and follows the principle of model predictive control to devise a cascaded model predictive controller based on the mathematical model of a permanent magnet synchronous motor for the joint to substitute for the traditional dual-loop PI controller with current and velocity loops in the closed-loop vector control *** design also employs the MATLAB/Simulink platform to simulate the control *** simulation experiments illuminate that the design of the cascaded model predictive controller has better dynamic response performance than the traditional PI controller and effectively enhances system robustness.

关键词： Modular Robot Joints Motor servo control Model predictive control

来源：评论

学校读者我要写书评

暂无评论

Imitation Learning of Human Operation Based on Visual Demonstration 3

Imitation Learning of Human Operation Based on Visual Demons...

引用

3rd International Conference on control and Computer Vision, ICCCV 2020

作者： Tong, Xunwei Li, Ruifeng Ge, Lianzheng Zhao, Lijun Wang, Ke State Key Laboratory of Robotics and Systems Harbin Institute of Technology Harbin China

ISBN: (纸本)9781450388023

In this paper, we propose an imitation learning method based on the optimization of the dynamic movement primitives (DMPs). The DMPs framework is one of the common methods of imitation learning because of its adaptability in time and space. On the basis of the traditional framework, we add the consideration of the dynamic performance of the robot during the reproduction process. We optimize the learned parameters (via DMPs) to reduce the average torque of robot joints while keeping the trajectory error small. The proposed method is evaluated with an experiment where a 6-degrees of freedom (6-DOF) robot learned a pick-place task from the visual demonstration of a human teacher. The experimental results show that our method reduced the average torque of robot joints by 73.4 N.m, which proves the effectiveness of the proposed method. © 2020 ACM.

关键词： 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：