检索结果-内蒙古大学图书馆

ieee 12th data driven control and learning systems conference (DDCLS)

作者： Zang, Yunge Li, Yan Duan, Yuting Li, Xiangyu Chang, Xi Li, Zhen Beijing Aerosp Automat Control Inst Beijing Peoples R China Natl Key Lab Sci & Technol Aerosp Intelligence Co Beijing Peoples R China Beijing Aerosp Inst Metrol & Measurement Technol Beijing Peoples R China Beijing Inst Technol Sch Automat Beijing 100081 Peoples R China Beijing Inst Technol Key Lab Intelligent Control & Decis Complex Syst Beijing 100081 Peoples R China

ISBN: (纸本)9798350321050

To facilitate ground station monitoring and command uploading, unmanned aerial vehicles (UAVs) need to frequently exchange individual state data between units. However, this results in a significant usage of communication bandwidth. To address this issue, on the basis of an event-triggered strategy, this paper proposes an Extended Kalman Filter (EKF). aimed at reducing the communication burden of UAVs while maintaining high accuracy. Specifically, a state measurement triggered by an event is selected for filtering only if it contains innovation, thereby reducing the amount of data that needs to be communicated. Since UAV systems are nonlinear, EKF is adopted to fully utilize the information obtained from event-triggered strategies, thereby enhancing the estimation performance. In this paper, a physical UAV was used to verify the proposed algorithm, and it proved to have robust dynamic performance and to effectively reduce the communication rate.

关键词： Event-trigger strategy real-time state estimation communication rate extended Kalman filter (EKF) unmanned aerial vehicles (UAVs)

来源：评论

学校读者我要写书评

暂无评论

Impedance Profile Prediction for Grid-Connected VSCs With data-driven Feature Extraction

引用

ieee TRANSACTIONS ON POWER ELECTRONICS 2025年第2期40卷 3043-3061页

作者： Wu, Yang Wu, Heng Cheng, Li Zhou, Jianyu Zhou, Zichao Chen, Minjie Wang, Xiongfei Aalborg Univ AAU Energy DK-9220 Aalborg Denmark KTH Royal Inst Technol Div Elect Power & Energy Syst S-10044 Stockholm Sweden Princeton Univ Andlinger Ctr Energy & Environm Dept Elect & Comp Engn Princeton NJ 08544 USA Aalborg Univ Dept Energy DK-9220 Aalborg Denmark

data-driven approach is promising for predicting impedance profile of grid-connected voltage source converters (VSCs) under a wide range of operating points (OPs). However, the conventional approaches rely on a one-to-one mapping between operating points and impedance profiles, which, as pointed out in this article, can be invalid for multiconverter systems. To tackle this challenge, this article proposes a stacked-autoencoder-based machine learning framework for the impedance profile predication of grid-connected VSCs, together with its detailed design guidelines. The proposed method uses features, instead of OPs, to characterize impedance profiles, and hence, it is scalable for multiconverter systems. Another benefit of the proposed method is the capability of predicting VSC impedance profiles at unstable OPs of the grid-VSC system. Such prediction can be realized solely based on data collected during stable operation, showcasing its potential for rapid online state estimation. Experiments on both single-VSC and multi-VSC systems validate the effectiveness of the proposed method.

关键词： Impedance Power conversion Converters Impedance measurement Feature extraction Perturbation methods Voltage control Principal component analysis Power system stability Neurons grid-connected voltage source converter (VSC) impedance profile machine learning

来源：评论

学校读者我要写书评

暂无评论

Time series data augmentation classifier for industrial process imbalanced fault diagnosis 12

Time series data augmentation classifier for industrial proc...

引用

ieee 12th data driven control and learning systems conference (DDCLS)

作者： Shen, Bingbing Yao, Le Jiang, Xiaoyu Yang, Zeyu Zeng, Jiusun Hangzhou Normal Univ Sch Math Hangzhou 311121 Peoples R China Zhejiang Univ Coll Control Sci & Engn State Key Lab Ind Control Technol Hangzhou Peoples R China Huzhou Univ Sch Engn Huzhou Peoples R China

ISBN: (纸本)9798350321050

Fault classification is a common problem in industrial fault diagnosis. Usually, classifiers are built assuming an equal amount of data across different classes. However, the amount of normal data and fault data collected from industrial processes is often imbalanced. Intrinsically, the fault classification is also an imbalanced data classification problem. To address this issue, data augmentation methods can be used to effectively generate more data and achieve data balance. While the performance of classification is greatly influenced by the generated data. The quality of the generated data can greatly impact the classification performance. To ensure the stability of the generated data, this paper extends the generation of single data to the generation of time series data using a time variational autoencoder. Using the generated time series data, a new classifier called the Time Series data Augmentation Classifier (TSDAC) is proposed to solve the imbalanced fault classification problem. After that, the TSDAC is applied to Tennessee Eastman (TE) benchmark process. The results show that the TSDAC is recommended for imbalanced fault classification.

关键词： Fault classification Imbalanced data Generated data Time variational autoencoder Time series data augmentation

来源：评论

学校读者我要写书评

暂无评论

Robust Adaptive control for Robotic Manipulator with Output Constraints 13

Robust Adaptive Control for Robotic Manipulator with Output ...

引用

13th ieee data driven control and learning systems conference, DDCLS 2024

作者： Chen, Lei Liu, Xiangbin Zou, Lang Zhang, Min School of Automation and Intelligence Beijing Jiaotong University Beijing China

ISBN: (纸本)9798350361674

This paper investigates the control problem of robotic manipulator subjected to uncertain dynamics and output constraints. The robotic manipulator system is described as a Lagrangian system with parameterized uncertainties and external disturbances. To deal with these uncertain terms, a robust adaptive control scheme is proposed to ensure the system with desired performance. Furthermore, the Barrier Lyapunov Function is introduced into the controller design to guarantee the output of the robotic manipulators satisfy the constraints. Finally, the effectiveness of the proposed control scheme is demonstrated by a numerical simulation. © 2024 ieee.

关键词： Lyapunov functions

来源：评论

学校读者我要写书评

暂无评论

Multi-Abstractive Neural controller: An Efficient Hierarchical control Architecture for Interactive Driving

引用

ieee ROBOTICS AND AUTOMATION LETTERS 2023年第8期8卷 4737-4744页

作者： Li, Xiao Gilitschenski, Igor Rosman, Guy Karaman, Sertac Rus, Daniela MIT Comp Sci & Artificial Intelligence Lab Cambridge MA 02139 USA Univ Toronto Toronto ON M5T 3A1 Canada Toyota Res Inst Chicago IL 60637 USA MIT Lab Informat & Decis Syst Cambridge MA 02139 USA

As learning-based methods make their way from perception systems to planning/control stacks, robot control systems have started to enjoy the benefits that data-driven methods provide. Because control systems directly affect the motion of the robot, data-driven methods, especially black box approaches, need to be used with caution considering aspects such as stability and interpretability. In this letter, we describe a differentiable and hierarchical control architecture. The proposed representation, called multi-abstractive neural controller, uses the input image to control the transitions within a novel discrete behavior planner (referred to as the visual automaton generative network, or vAGN). The output of a vAGN controls the parameters of a set of dynamic movement primitives which provides the system controls. We train this neural controller with real-world driving data via behavior cloning and show improved explainability, sample efficiency, and similarity to human driving.

关键词： Autonomous driving path planning robot learning

来源：评论

学校读者我要写书评

暂无评论

Distributed Event-Triggered Iterative learning control for Multiple High-Speed Trains With Switching Topologies: A data-driven Approach

引用

ieee TRANSACTIONS ON INTELLIGENT TRANSPORTATION systems 2023年第10期24卷 10818-10829页

作者： Yu, Wei Huang, Deqing Wang, Qingyuan Cai, Liangcheng Southwest Jiaotong Univ Key Lab Railway Ind Adv Energy Tract & Comprehens Chengdu 610031 Peoples R China Southwest Jiaotong Univ Sch Elect Engn Chengdu 610031 Peoples R China

This paper studies the distributed data-driven event-triggered model free adaptive iterative learning control (ETMFAILC) of multiple high-speed trains (MHSTs) under iteration-varying topologies, which breaks away from the dependence on the train dynamics. Firstly, the nonlinear MHSTs with unknown dynamics are converted into a linear model. Then, combining the proposed event-based triggering condition and the linear model, the ETMFAILC scheme under the fixed topology is designed. Next, theoretical analysis proves the bounded input bounded output (BIBO) stability of MHSTs. Finally, the study is extended to the switching topologies and the validity of the ETMFAILC is verified by a numerical example.

关键词： data-driven control event-triggered control iterative learning control high-speed train control switching topology

来源：评论

学校读者我要写书评

暂无评论

Distributed control of Multiple Quadruped Robots Based on Leader-Following Consensus Strategy 13

Distributed Control of Multiple Quadruped Robots Based on Le...

引用

13th ieee data driven control and learning systems conference, DDCLS 2024

作者： Ren, Ye Sun, Haoyang Wang, Li Liu, Shida School of Electronics & Control Engineering North China University of Technology Beijing100043 China

ISBN: (纸本)9798350361674

This paper discusses the leader-follower consistency problem in multi-quadruped robot systems. Initially, the dynamics of quadruped robots are modeled as a first-order integral model. Then, a PD-type distributed protocol is proposed as the controller for the following quadruped robots. Finally, the feasibility of this protocol is verified through a joint MATLAB and CoppeliaSim simulation. The simulation uses a multi-quadruped robot system consisting of one leading quadruped robot and three following quadruped robots. The simulation outcomes validate the efficacy of the proposed control protocol. © 2024 ieee.

关键词： Multipurpose robots

来源：评论

学校读者我要写书评

暂无评论

Adaptive Input Shaping control Based on RLS for Harvesting Mechanical Arm 12

Adaptive Input Shaping Control Based on RLS for Harvesting M...

引用

ieee 12th data driven control and learning systems conference (DDCLS)

作者： Sun, Mingming Liu, Dexin Univ Sci & Technol Beijing Basic Expt Ctr Nat Sci Beijing 100083 Peoples R China Univ Sci & Technol Beijing Sch Automat & Elect Engn Beijing 100083 Peoples R China Beijing Union Univ Beijing Key Lab Informat Serv Engn Beijing 100101 Peoples R China Beijing Union Univ Coll Robot Beijing 100101 Peoples R China

ISBN: (纸本)9798350321050

In this paper, a direct method of adaptive input shaping algorithm for a harvesting mechanical arm clamps the tomato bunches is proposed to achieved zero residual vibration. The traditional input shaping would lose its vibration suppressing function when the system parameter changed during mechanical arm's load varied. The adaptive input shaping algorithm based on recursive least square method (RLS) requires no system identification. The residual vibration of output signal is used as the input of the algorithm to calculate the impulse time and amplitude of shaper. An adaptive forgetting factor updating algorithm is proposed to improve the control performance in variable load condition. The experimental results show that the adaptive forgetting factor input shaper greatly reduces the residual vibration.

关键词： Adaptive Input Shaping Harvesting Mechanical Arm Residual Vibration Load Varied and RLS

来源：评论

学校读者我要写书评

暂无评论

A data-driven Residual Life Prediction Method For Rolling Bearings 12

A Data-Driven Residual Life Prediction Method For Rolling Be...

引用

ieee 12th data driven control and learning systems conference (DDCLS)

作者： Li, Shangrui Li, Meng Liu, Zhilong Li, Minggang Univ Elect Sci & Technol China Sch Automat Engn Chengdu 611730 Peoples R China Nucl Power Inst China Inst Reactor Power Engn Chengdu 610000 Peoples R China

ISBN: (纸本)9798350321050

Rolling bearing is a key component of rotating machinery, which affects the reliability of the equipment. In order to make the equipment intelligent, facilitate the maintenance of the equipment, and improve the operation efficiency of the equipment, a data-driven residual life prediction method of rolling bearing is proposed, which is used to intelligently predict the remaining service life of the equipment, providing great convenience for the maintenance of the equipment. First, wavelet packet de-noising method is used to remove the noise in the original signal, and then extract the time-domain and frequency-domain features of the de-noised signal, after that PCA is used to reduce the dimension of the feature information and fuse it into the comprehensive life characteristics of the bearing. Last, with the input of the subsequent life prediction features, the residual life prediction model based on PCA-SVR is finally constructed. The experimental results show that the residual life prediction model based on PCA-SVR has low error rate and high accuracy which can accurately predict the residual life of rolling bearings.

关键词： Support Vector Machine Residual Life Prediction Principal Component Analysis Rolling Bearing

来源：评论

学校读者我要写书评

暂无评论

Guided Bayesian Optimization: data-Efficient controller Tuning With Digital Twin

引用

ieee TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING 2025年 22卷 11304-11317页

作者： Nobar, Mahdi Keller, Jurg Rupenyan, Alisa Khosravi, Mohammad Lygeros, John Swiss Fed Inst Technol Automatic Control Lab CH-8092 Zurich Switzerland FHNW Automat Inst CH-5210 Windisch Switzerland Zurich Univ Appl Sci ZHAW Ctr AI CH-8401 Winterthur Zurich Switzerland Delft Univ Technol Delft Ctr Syst & Control NL-2628 CD Delft Netherlands

This article presents the guided Bayesian optimization (BO) algorithm as an efficient data-driven method for iteratively tuning closed-loop controller parameters using a digital twin of the system. The digital twin is built using closed-loop data acquired during standard BO iterations, and activated when the uncertainty in the Gaussian Process model of the optimization objective on the real system is high. We define a controller tuning framework independent of the controller or the plant structure. Our proposed methodology is model-free, making it suitable for nonlinear and unmodelled plants with measurement noise. The objective function consists of performance metrics modeled by Gaussian processes. We utilize the available information in the closed-loop system to progressively maintain a digital twin that guides the optimizer, improving the data efficiency of our method. Switching the digital twin on and off is triggered by our data-driven criteria related to the digital twin's uncertainty estimations in the BO tuning framework. Effectively, it replaces much of the exploration of the real system with exploration performed on the digital twin. We analyze the properties of our method in simulation and demonstrate its performance on two real closed-loop systems with different plant and controller structures. The experimental results show that our method requires fewer experiments on the physical plant than Bayesian optimization to find the optimal controller parameters. Note to Practitioners-Industrial applications typically are difficult to model due to disturbances. Bayesian optimization is a data-efficient iterative tuning method for a black box system in which the performance can only be measured given the control parameters. Iterative measurements involve operational costs. We propose a guided Bayesian optimization method that uses all information flow in a system to define a simplified digital twin of the system using out-of-the-box methods. It is continuously u

关键词： Tuning Digital twins Bayes methods control systems Measurement Cost function Uncertainty learning control systems iterative methods database systems control systems optimization methods

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：