检索结果-内蒙古大学图书馆

Data-Driven Learning and control with Event-Triggered Measurements

IEEE Transactions on Automatic control 2025年

作者： Feng, Shilun Shi, Dawei Chen, Tongwen Shi, Ling Beijing Institute of Technology State Key Laboratory of Intelligent Control and Decision of Complex Systems MIIT Key Laboratory of Servo Motion System Drive and Control School of Automation Beijing100081 China University of Alberta Department of Electrical and Computer Engineering EdmontonABT6G 1H9 Canada Hong Kong University of Science and Technology Department of Electronic and Computer Engineering Clear Water Bay Kowloon Hong Kong

Event-triggered control has attracted considerable attention for its effectiveness in resource-restricted applications. To make event-triggered control as an end-to-end solution, a key issue is how to effectively learn unknown system dynamics from event-triggered measurements and consequently, develop a learning-based event-triggered controller. Existing works learn system dynamics based on periodic time-triggered measurements, and it is yet to know how to learn a controller with performance guarantee based on event-triggered measurements. To address this issue, we consider the problem of learning an event-triggered state feedback controller for an unknown linear system based on event-triggered state measurements in this work. In particular, we first analyze the event-triggered measurements within a set-membership framework. We prove that the estimation error belongs to a bounded ellipsoid determined by the historical measurements and the event-triggering condition. Subsequently, we demonstrate that all admissible systems compatible with the collected data samples can be explicitly represented in the form of quadratic matrix inequalities using the state estimates. With the acquired set of admissible systems, a co-design problem for the data-driven controller and event-triggering condition is solved using the linear matrix inequality technique, with guaranteed closed-loop stability and L2-gain performance. Finally, numerical examples and comparisons are provided to illustrate the effectiveness of the proposed event-triggered learning and control approach. © 1963-2012 IEEE.

关键词： Networked control systems

来源：评论

学校读者我要写书评

暂无评论

A Multi-Kernel Principal Component Analysis Method for Quality-Related Fault Detection

A Multi-Kernel Principal Component Analysis Method for Quali...

引用

Youth Academic Annual Conference of Chinese Association of automation (YAC)

作者： Lingxia Mu Biyu Lei Ding Liu School of Automation and Information Engineering Xi’an University of Technology Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi’an University of Technology Xi’an China

ISBN: (纸本)9781665465373

In this paper, a multi-kernel principal component analysis (MKPCA) method for quality-related fault detection is proposed. The initial space is firstly mapped to a new space. The correlated information between the new space and output quality is then obtained by the kernel function. Meanwhile, with consideration of the advantage of global function and local function, a weight factor which combines them together is introduced to construct a multi-kernel function. In this way, the algorithm achieves better learning ability. The new space is projected to two mutually orthogonal subspaces, i.e., quality-related part and quality-unrelated part. In each subspace, fault information is expressed by different statistical indicators. The numerical example is presented to evaluate the performance of the MKPCA. The results show better reliability and high fault detection rate through proper spatial decomposition and kernel function construction.

关键词： Correlation automation Fault detection Feature extraction Eigenvalues and eigenfunctions Reliability Matrix decomposition

来源：评论

学校读者我要写书评

暂无评论

Chinese Character Style Transfer Based on the Fusion of Multi-scale Content and Style Features

Chinese Character Style Transfer Based on the Fusion of Mult...

引用

第40届中国控制会议

作者： Xiaoxue Zhou Ziying Zhang Xin Chen Mengxi Qin School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems School of Arts and Communication China University of Geosciences

Style transfer has received much attention, and Chinese character style transfer is an important application. In the previous Chinese character style transfer methods, most of the methods separately establish a mapping from source font to target Chinese character for each specific target font. It is impossible to extend a single model to other styles. The model training is based on the amount of Chinese character data from a single font, and the demand of the character is greater. In fact, different font style transfer tasks have certain commonalities. Therefore, we use multiple fonts in the data set and combine these fonts into multiple sets of Chinese character style transfer tasks. These tasks will be trained at the same time, instead of that only one font style transfer task training is achieved at a time like the previous work. In order to achieve the purpose of extracting and fusing the content features and style feature, we propose a style transfer network composed of content encoder, style encoder, feature fusion module, and decoder, based on the fusion of multi-scale content and style features. Through the experimental results, it can be found that, using our method, training the style transfer of multiple fonts at the same time can help any one of them to generate better results with only a few samples.

关键词： Chinese characters style transfer Generative adversarial networks Content and style features

来源：评论

学校读者我要写书评

暂无评论

Reconstruction of Spectral Reflectance Based on Fusion Convolution Neural Network 2020

Reconstruction of Spectral Reflectance Based on Fusion Convo...

引用

Proceedings of the 2020 9th International Conference on Computing and Pattern Recognition

作者： Lijun Zhang Xiangguo Wang Jingjing Zhang Jinlong Qiao Penghui Li School of Automation China University of Geosciences Wuhan P. R. China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems

ISBN: (纸本)9781450387835

An improved method for spectral reflectance reconstruction from the RGB response of the digital camera is proposed by deep convolution neural network. The proposed method learns a fusion mapping theory that represents the basic characteristics of spectral reflectance, including spectral nonlinear mapping and spatial similarity. The deep residual network greatly deepens the network structure and improves the performance of the model, enabling the recovery network to make full use of the sample structure information to accurately recover the spectral reflectance. The performance of the method is compared with several existing methods in the cases of the same experimental data set. Experimental results show that the proposed method has the best accuracy in estimating spectral reflectance and colorimetric values in most cases in comparison with existing methods.

关键词： Spectral reflectance reconstruction spatial similarity deep convolution neural network spectral nonlinear mapping

来源：评论

学校读者我要写书评

暂无评论

Optimization of Robot End-Effector Load Gravity Compensation for Unmanned Live Work in Electric Power Distribution Networks Based on Improved PSO Algorithm

Optimization of Robot End-Effector Load Gravity Compensation...

引用

Chinese automation Congress (CAC)

作者： Jinge Chen Xin Chen Chenyu Hu Guangxian Huang Shu Sun Xu Jian School of Automation China University of Geosciences Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China Engineering-Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China Distribution Department State Grid Hubei Electric Power Co. Ltd. Xianning Power Supply Company Xianning China Equipment Technology Center State Grid Hubei Electric Power Co. Ltd. Electric Power Science Research Institute Wuhan China

In the field of electric power distribution network operation, most tasks involve contact operations. A key technology to enable the flexible operation of robots in live distribution network tasks is the installation of six-dimensional force sensors on the robot's end flange. These sensors allow the robot to perceive external environmental contact forces. However, the presence of the end load interferes with the accurate perception of external forces. Aiming at the gravity compensation of robot end load, an optimization algorithm of gravity compensation based on particle swarm optimization is proposed. In this method, the optimal solution model is established with the objective of minimum sum of squared errors, and the particle swarm optimization algorithm is used to estimate the mounting declination angle of the force sensor and improve the precision of gravity compensation. The experiments show that the proposed method can effectively reduce the maximum gravity compensation error and the average gravity compensation error in each direction after optimization, in which the maximum gravity compensation error of the resultant force is reduced by 9.11% and the average gravity compensation error of the resultant force is reduced by 12.34%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An IMU Error Correction Method Based on Multithreshold ZV Detection and SRCKF

An IMU Error Correction Method Based on Multithreshold ZV De...

引用

Cyber-Physical Social Intelligence (ICCSI), International Conference on

作者： Jialiang Luo Shichao Chen Yisheng Lv Wenqiao Sun Fan Yang Ruijie Xu The State Key Laboratory for Management and Control of Complex System State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences School of Information Engineering China University of Geosciences Beijing China The State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences The Center of National Railway Intelligent Transportation System Engineering and Technology China Academy of Railway Sciences Corporation Limited Beijing China The State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China Transportation and Economics Research Institute and the Center of National Railway Intelligent Transportation System Engineering and Technology China Academy of Railway Sciences Corporation Limited China The State Key Laboratory for Management and Control of Complex System State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences College of Rail Transit Shan Dong JiaoTong University Jinan China Department of Aeronautical and Aviation Engineering The Hong Kong Polytechnic University Hong Kong China

With the rapid development and widespread application of Inertial Measurement Units (IMUs), IMU-based human localization has become critically important in environments lacking Global Navigation Satellite systems (GNSS) signals. Methods such as UWB/WIFI and other anchor-based localization have been employed to enhance the positioning accuracy. However, these methods are susceptible to the environmental interference and increased costs. In contrast, SINS-based localization methods eliminate reliance on the external data. However, this method can suffer from drift errors due to cumulative integration errors. Inertial navigation error correction techniques like Zero Detection Update Technology (ZUPT) provide potential solutions to address drift errors. This paper proposes an error correction method based on the multithreshold zero-velocity detection and Square Root Cubature Kalman Filter (SRCKF) updates. Compared to the single fixed threshold detection, the multi-threshold zero-velocity detection reduces the likelihood of missed zero velocity detection and false alarms, providing accurate time intervals for error correction. Experimental results demonstrate that the SRCKF-based algorithm reduces position deviation to approximately 0.3146 meters, corresponding to an error ratio of1.14%. The proposed method enables cost-effective and accurate pedestrian localization, driving advancements in the field.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Robust Multi-AGV Cooperative Path Planning Method Considering Spatiotemporal Distance

A Robust Multi-AGV Cooperative Path Planning Method Consider...

引用

Computer Engineering and intelligent control (ICCEIC) International Conference on

作者： Maolin Chen Songhang Chen Mingchang Lian School of Advanced Manufacturing Fuzhou University Quanzhou China Fujian Institute of Research on the Structure of Matter Chinese Academy of Sciences Fuzhou China Fujian Provincial Key Laboratory of Intelligent Identification and Control of Complex Dynamic System Quanzhou China Fujian College University of Chinese Academy of Sciences Fuzhou China Fujian Science & Technology Innovation Laboratory for Optoelectronic Information of China Fuzhou China

ISBN: (数字)9798331507992

ISBN: (纸本)9798331508005

With the widespread application of Automated Guided Vehicles (AGVs) in warehousing and logistics systems, the optimization of multi-AGV path planning has become a critical issue. Current methods primarily focus on minimizing operating time and energy consumption but often overlook spatiotemporal distances between paths, leading to frequent path conflicts and interferences in the system. This paper proposes a neural network based time window estimation model, designed to generate time windows that better align with dynamic environments. Based on this model, we introduce a collaborative multi-AGV path planning method that optimizes spatiotemporal distances between paths. Compared to the Conflict-Based Search (CBS) method, this approach significantly improves the spatiotemporal distance between AGVs during task execution, enhancing the robustness of AGV clusters while only marginally increasing time costs.

关键词： Energy consumption Costs Remotely guided vehicles Neural networks Warehousing Estimation Collaboration Path planning Spatiotemporal phenomena Vehicle dynamics

来源：评论

学校读者我要写书评

暂无评论

A Multi-feature Extraction-based Image Identification Method for Rock Debris in The Drilling Process

A Multi-feature Extraction-based Image Identification Method...

引用

Chinese automation Congress (CAC)

作者： Pengju Xu Chao Gan Luzhao Wang Weihua Cao School of Automation China University of Geosciences Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China Ministry of Education Engineering Research Center of Intelligent Technology for Geo-Exploration Wuhan China No.3 Exploration Institute of Geology and Mineral Resources of Shandong Province Yantai China

In this paper, a multi-feature extraction-based image identification method for rock debris in the drilling process is proposed, involving three main parts (trainable feature extractor, strong feature extraction, and classification). In trainable feature extractor, abstract features are obtained by extracting the full connection layer of Convolutional Neural Network (CNN). In strong feature extraction, the method uses Gray-Level Co-occurrence Matrix (GLCM) and Color Coherence Vector (CCV) to get the strong feature. In classification, the extracted abstract features and strong features are concatenated and fed into the Support Vector Machine (SVM). Comparison results with two well-known methods indicated the effectiveness of the proposed method.

关键词： Support vector machines Drilling Measurement Image color analysis Neural networks Feature extraction Rocks

来源：评论

学校读者我要写书评

暂无评论

A Reinforcement Learning Approach for Robust Restoration of Generators in Power system

A Reinforcement Learning Approach for Robust Restoration of ...

引用

Chinese automation Congress (CAC)

作者： Huimiao Li Xiaozhou Yang Chao Zhai School of Automation China University of Geosciences Wuhan Campus Hubei Key Laboratory of Advanced Control and Intelligent Automation fo Complex Systems Ministry of Education Engineering Research Center of Intelligent Technology for Geo-Exploration Wuhan China Singapore-ETH Centre CREATE Campus Future Resilient Systems Singapore

In the past decades, cascading blackouts have caused serious damages to power systems and affected the normal operation of society, so it is crucial to quickly restore the damaged power system to normal state. In this paper, a reinforcement learning (RL) approach is developed to achieve the robust restoration of generators in power systems. Firstly, the performance recovery of damaged power system is modeled as markov decision process, and constraints such as line voltage and active power output of generators are considered. Secondly, a RL algorithm is proposed to search the optimal control strategy for generator units recovery. Based on the proposed restoration approach, Q-learning algorithm is employed to obtain the optimal strategy for power supply of generaors in power grids. Finally, numerical simulations are carried out on IEEE 9-bus system under different scenarios of external disturbances and certainties. The simulation results demonstrate the effectiveness and feasibility of the proposed approach.

关键词： Q-learning Power supplies Simulation Power system protection Generators Explosions Power systems

来源：评论

学校读者我要写书评

暂无评论

Design and Development of Big Data system for Blast Furnace Ironmaking

Design and Development of Big Data System for Blast Furnace ...

引用

Industrial Cyber-Physical systems (ICPS)

作者： Qifu Chen Jinhua She Min W Zhuofu Zhang Zhenhong Liao School of Future Technology China University of Geosciences Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China Engineering Research Center of Intelligent Technology for Geo-Exploration. Ministry of Education Wuhan China Hunan Valin Lianyuan Iron and Steel Co. Ltd. Loudi China School of Engineering Tokyo University of Technology Tokyo Japan School of Automation. China University of Geosciences Wuhan China

The process of blast furnace ironmaking is com-posed of several sub-processes. The process of blast furnace smelting is complicated and the data of each sub-process are scattered and not concentrated. The traditional working mode of subjective judgment based on manual experience is not conducive to the stable production of the blast furnace. Therefore, this paper develops a big data system for the production process of blast furnace, which is of great significance to realize the digital production and intelligent production of blast furnace. According to the system architecture of blast furnace ironmaking, this paper mainly designs and develops the data acquisition layer, data storage layer, data analysis layer and data application layer of the big data system.

关键词： Software design Data acquisition Smelting Memory systems architecture Production User interfaces

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：