检索结果-内蒙古大学图书馆

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

作者： Xu, Shuiqing Dai, Haosong Huang, Darong Tao, Songbing Hu, Chong Hefei Univ Technol Coll Elect Engn & Automat Hefei 230009 Peoples R China Anhui Univ Sch Artificial Intelligence Hefei 230601 Peoples R China Anhui Lingkun Intelligent Technol Bengbu 233000 Peoples R China Chongqing Micro Stand Technol Co Ltd Chongqing 401121 Peoples R China

ISBN: (纸本)9798350321050

In this paper, the problem of fault estimation for a class of nonlinear systems with time delay is studied. First, an iterative learning observer and an exponential function-based fault estimation law are designed to improve the accuracy of fault estimation results. Then, we use the lambda-norm method to derive the convergence conditions for the proposed fault estimator and provide the corresponding proof of convergence. Finally, the simulation results are presented to demonstrate the effectiveness of the proposed fault estimation method, which shows that it can accurately reconstruct the fault signal.

关键词： Fault estimation Nonlinear system Iterative learning scheme

来源：评论

学校读者我要写书评

暂无评论

data-driven Rational Feedforward Tuning Algorithm Based on Self-adaptive Hybrid Self-learning TLBO 12

Data-driven Rational Feedforward Tuning Algorithm Based on S...

引用

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

作者： Chen, Siwen Liu, Yang Song, Fazhi Harbin Inst Technol Minist Ind & Informat Technol Key Lab Ultra Precis Intelligent Instrumentat Harbin 150001 Peoples R China Huazhong Univ Sci & Technol State Key Lab Digital Mfg Equipment & Technol Wuhan 430074 Peoples R China

ISBN: (纸本)9798350321050

data-driven feedforward tuning algorithm, extensively used in ultra-precision motion stage, can significantly compensate tracking errors and optimize task ***, the rational basis based feedforward optimization usually faces non-convex optimization, numerical stability and initial value problems. The purpose of this paper is to propose a feedforward tuning algorithm based on the heuristic method self-adaptive hybrid self-learning TLBO. The algorithm can converge to the ideal feedforward parameter, so that the system can achieve high tracking accuracy, and has good numerical properties and low initial value requirements. The effectiveness and superiority of the proposed method are verified by simulation.

关键词： Feedforward control Rational Basis Function Self-adaptive Hybrid Self-learning TLBO

来源：评论

学校读者我要写书评

暂无评论

Adaptive Estimation and control With Online data Memory: A Historical Perspective

引用

ieee control systems LETTERS 2024年 8卷 267-278页

作者： Pan, Yongping Shi, Tian Sun Yat sen Univ Sch Adv Mfg Shenzhen 518100 Peoples R China Sun Yat Sen Univ Sch Comp Sci & Engn Guangzhou 510006 Peoples R China

Online data memory is essential for adaptive estimation and control as it can enhance the performance and robustness of adaptive systems compared to adaptive systems without data memory. We provide an overview of four data memory-driven parameter estimation schemes for adaptive systems from a historical perspective, including forgetting-data memory regression extension (MRE), full-data MRE, discrete-data MRE, and interval-data MRE. For clear presentation and better understanding, a general class of nonlinear systems with linear-in-the-parameter uncertainties is applied as a unifying framework to demonstrate the motivation, synthesis, and characteristics of each MRE scheme for parameter estimation in adaptive control. Intensive comparisons of the four MRE schemes are provided to reveal their technical natures, and real-world applications are discussed to show their practicability. It is concluded that all the MRE schemes can achieve exponential parameter convergence under relaxed excitation conditions rather than the classical condition of persistent excitation which is too stringent to satisfy in practice. The distinctive features of interval-data MRE termed composite learning are highlighted with respect to computational simplicity, estimation accuracy, robustness against perturbations, and widespread real-world applications to robot learning and control. Possible directions for future research in this area are suggested to conclude this survey.

关键词： Composite learning model learning for control parameter convergence regression extension

来源：评论

学校读者我要写书评

暂无评论

Robust learning-Based control for Uncertain Nonlinear systems With Validation on a Soft Robot

引用

ieee TRANSACTIONS ON NEURAL NETWORKS AND learning systems 2025年第1期36卷 510-524页

作者： Han, Minghao Wong, Kiwan Euler-Rolle, Jacob Zhang, Lixian Katzschmann, Robert K. ETH Soft Robot Lab CH-8092 Zurich Switzerland Harbin Inst Technol Dept Control Sci & Technol Harbin 150001 Peoples R China

Existing modeling and control methods for real-world systems typically deal with uncertainty and nonlinearity on a case-by-case basis. We present a universal and robust control framework for the general class of uncertain nonlinear systems. Our data-driven deep stochastic Koopman operator (DeSKO) model and robust learning control framework guarantee robust stability. DeSKO learns the uncertainty of dynamical systems by inferring a distribution of observables. The inferred distribution is used in our robust and stabilizing closed-loop controller for dynamical systems. We also develop a model predictive control framework with integral action to compensate for run-time parametric uncertainty, such as manipulating unknown objects. Modeling and control experiments in simulation show that our presented framework is more robust and scalable for robotic systems than state-of-the-art controllers using deep Koopman operators and reinforcement learning (RL) methods. We demonstrate that our method resists previously unseen uncertainties, such as external disturbances, at a magnitude of up to five times the maximum control input. Furthermore, we test our DeSKO-based control framework on a real-world soft robotic arm. It shows that our framework outperforms model-based controllers that have full knowledge of the model parameters, and the controller can conduct object pick-and-place tasks without further training. Our approach opens up new possibilities in robustly managing internal or external uncertainty while controlling high-dimensional nonlinear systems in a learning framework. This approach serves as a foundation to greatly simplify high-level control and decision-making for robots.

关键词： Uncertainty Artificial neural networks Probabilistic logic Soft robotics Predictive models Nonlinear systems Mathematical models Koopman operator (KO) robust learning-based control soft robots stability guarantee uncertain nonlinear systems

来源：评论

学校读者我要写书评

暂无评论

Event-triggered finite-time control design for positive systems based on linear programming approach 12

Event-triggered finite-time control design for positive syst...

引用

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

作者： Li, Shuo Li, Liang Cui, Mingzhe Tian, Yu-Ping Wang, Jinling Hangzhou Dianzi Univ Sch Automat Hangzhou 310018 Peoples R China Anhui Agr Univ Sch Sci Hefei 230036 Peoples R China

ISBN: (纸本)9798350321050

This paper addresses the finite-time control design for a class of positive systems based on event-triggered mechanisms via a linear programming(LP) approach. Firstly, a new event-triggering condition in the form of vector 1 norm is proposed for positive systems. Then, sufficient conditions of positivity, finite-time stability and finite-time boundedness are provided for the closed-loop system under the designed LP-based event-triggered finite-time control law by applying the matrix decomposition technology. Finally, an example with comparison is given to illustrate the validity of the results.

关键词： Event-triggered finite-time control Linear programming(LP) Positivity Finite-time stability and boundedness

来源：评论

学校读者我要写书评

暂无评论

Predictive Active Disturbance Rejection Attitude control for 2-DOF Unmanned Helicopter with Three Typical Uncertainties 12

Predictive Active Disturbance Rejection Attitude Control for...

引用

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

作者： Yang, Jinwei China West Normal Univ Sch Elect Informat Engn Nanchong 637009 Peoples R China

ISBN: (纸本)9798350321050

This paper considers the attitude control for 2-DOF unmanned helicopter. To handle the nonlinear uncertainties in helicopter system, active disturbance rejection control (ADRC) based attitude controller is designed. Compared with the conventional ADRC, the proposed ADRC design contains an additional predictive part for the estimated value from ESO. By utilizing the estimated value and its derivative, the predictive values of total disturbance and unmeasured angular velocity are calculated based on Taylor expansion. The presented predictive design can cancel the hysteresis phenomenon of estimation in ESO, which results in the more accurate estimation. Due to the precise estimation for total disturbance and unmeasured angular velocity, the satisfied tracking performance of presented method is validated. In simulations, the estimating and tracking performance of the presented method is shown for three typical uncertainties: step disturbances, ramp disturbances and nonlinear uncertainties.

关键词： Unmanned helicopter Active disturbance rejection control Extended state observer Predictive

来源：评论

学校读者我要写书评

暂无评论

Features Masked Auto-Encoder-Based Anomaly Detection in Process Industry 12

Features Masked Auto-Encoder-Based Anomaly Detection in Proc...

引用

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

作者： Hu, Junhao Jia, Mingwei Yang, Qinmin Liu, Yi Zhejiang Univ Technol Inst Proc Equipment & Control Engn Hangzhou 310023 Peoples R China Zhejiang Univ State Key Lab Ind Control Technol Hangzhou 310027 Peoples R China

ISBN: (纸本)9798350321050

With the development of the modern process industry, accurate anomaly detection methods are increasingly needed. However, identifying anomalies from high-dimensional data continues to be a challenge for the process industry. In this work, a feature masked autoencoder (FMAE) method is proposed to meet this challenge. As a masked-reconstruction task, a high mask rate is first adopted to mask the feature of data. Then, the intrinsic information of unmasked features is extracted through the encoder and masked features are recovered through the decoder. This task forces the intrinsic information learned by the model to increase while alleviating the high-dimensional problem. Additionally, anomaly tends to be reconstructed to a normal by FMAE because only normal data is used for training. Thus, anomalies are detected and localized by computing input-output residuals. Finally, the effectiveness of the model is verified on the Lublin Sugar Factory dataset.

关键词： anomaly detection data masked unsupervised learning attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Power Quality Assessment and Optimization in FUZZY-driven Healthcare Devices

引用

ieee ACCESS 2025年 13卷 9679-9688页

作者： Nishad, Dinesh Kumar Khalid, Saifullah Singh, Rashmi IBM Multi Act Co Ltd Khartoum 11115 Sudan

The advent of FUZZY technology has revolutionized healthcare, empowering smarter medical devices and equipment. However, the successful operation of these FUZZY-driven systems is contingent on high power quality. This paper introduces an innovative FUZZY-driven energy management system that combines convolutional neural networks (CNNs) for real-time power quality event detection, long short-term memory (LSTM) networks for predictive analytics, and reinforcement learning for optimized control. Through extensive simulations on an ieee 13-bus test feeder, we demonstrate the system's superior performance in detecting and mitigating power quality disturbances. The CNN-based detection achieves 97% accuracy in classifying events, while the LSTM enables 95% accurate prediction of emerging issues. The reinforcement learning controller achieves 50% faster voltage sag restoration, 20% greater harmonic reduction, and 30% faster critical load recovery during outages compared to conventional methods. Key challenges, including data quality concerns, cybersecurity risks, and integration with legacy infrastructure, are discussed. This work represents a significant advancement in applying FUZZY technology to healthcare power quality management, offering a comprehensive solution that balances efficiency, reliability, and patient safety. The proposed system provides a scalable framework for modernizing power quality monitoring and control in healthcare facilities.

关键词： FUZZY convolutional neural networks (CNN) cyber security deep learning energy management healthcare technology intrusion detection system (IDS) IoT security long short-term memory (LSTM) machine learning microgrids neural networks power quality reinforcement learning smart grids healthcare technology intrusion detection system (IDS) IoT security long short-term memory (LSTM) machine learning microgrids neural networks power quality reinforcement learning smart grids

来源：评论

学校读者我要写书评

暂无评论

Physics-Informed Weakly-Supervised learning for Quality Prediction of Manufacturing Processes

引用

ieee TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING 2025年 22卷 2006-2019页

作者： Alenezi, Dhari F. Biehler, Michael Shi, Jianjun Li, Jing Georgia Inst Technol H Milton Stewart Sch Ind & Syst Engn Atlanta GA 30332 USA Kuwait Univ Dept Ind & Management Syst Engn Safat 13060 Kuwait

In manufacturing processes, a multitude of sensors are typically deployed to collect data of process parameters. While this provides an opportunity to better predict and control the quality of the final product, the relationship between the process variables and the desired final quality is often not well-understood. To establish this relationship, machine learning (ML) models can be used. However, collecting large, labeled datasets to train the ML model can be difficult, as creating such datasets typically involves costly or destructive end-of-line quality testing of the products. To overcome this challenge, we propose a novel framework called Physics-informed Weakly-supervised learning (PWL) that integrates physics-based models with data-driven ML models. By leveraging physical knowledge and using the outputs of physics-based models as weak labels, PWL offers an alternative to traditional methods that require large, labeled datasets. Our approach simultaneously optimizes the data-driven ML model, as well as the discrepancy and calibration parameters of the physics-based model, resulting in superior predictive performance compared to either model used alone. We demonstrate the effectiveness of PWL through simulation experiments, comparisons with existing methods, and two real-world case studies, highlighting its potential for improving quality prediction in various manufacturing systems. Note to Practitioners-The proposed method in this paper, Physics-informed Weakly-supervised learning (PWL), addresses a common problem in manufacturing processes, where obtaining large, labeled datasets can be costly or not always possible. By integrating physics-based models with data-driven ML models, PWL leverages available physical knowledge to improve the predictive performance of product quality in manufacturing systems. This enables practitioners to better understand and optimize their manufacturing processes even with limited labeled datasets, leading to improved product qu

关键词： Weakly-supervised learning physics-informed machine learning manufacturing processes quality prediction

来源：评论

学校读者我要写书评

暂无评论

ADRC with built-in RLC control scheme for uncertain systems with periodic reference input 12

ADRC with built-in RLC control scheme for uncertain systems ...

引用

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

作者： Li, Xiangyang Huang, Jian Tian, Senping Ai, Wei South China Univ Technol Sch Automat Sci & Engn Key Lab Autonomous Syst & Network Control Minist Educ Guangzhou 510641 Peoples R China Kunming Shipborne Equipment Res & Test Ctr Kunming 650051 Yunnan Peoples R China

ISBN: (纸本)9798350321050

Active disturbance rejection control (ADRC) method has shown strong capabilities to handle system uncertainties. As for dealing with the periodic reference input signal, the repetitive learning control (RLC) method is often applied in practice to improve the system performance. In this paper, a distinct framework is proposed for the design and implementation of integrating the advantages of RLC and ADRC for uncertain systems with periodic reference input. An extra control input produced by built-in RLC scheme is added to the state error feedback (SEF) part of ADRC system. The stability of ADRC with built-in RLC scheme is proved. Simulations show that the proposed method is effective and can achieve better performance than the classic ADRC.

关键词： Repetitive learning control (RLC) active disturbance rejection controller (ADRC) extended state observer (ESO) state error feedback (SEF) uncertain system periodic reference input

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：