检索结果-内蒙古大学图书馆

A Fault Detection Approach for Nonlinear systems Based on Deep learning-Aided Kernel Representations

ieee TRANSACTIONS ON INDUSTRIAL INFORMATICS 2025年

作者： Wu, Shimeng Zhu, Yimin Luo, Hao Wang, Hao Zhang, Jiusi Qiao, Xinyu Tian, Jilun Harbin Inst Technol Dept Control Harbin 150001 Peoples R China Harbin Inst Technol Simulat Ctr Harbin 150001 Peoples R China Harbin Inst Technol Natl Key Lab Complex Syst Control & Intelligent Ag Harbin 150001 Peoples R China Harbin Inst Technol Harbin 150001 Peoples R China Univ Elect Sci & Technol China Sch Automat Engn Chengdu 611731 Peoples R China

This article focuses on utilizing process data to detect faults in nonlinear systems. To accomplish this, stable image/kernel representation is learned for nonlinear systems using deep neural networks, which serve as the basis for residual generators and fault detection. First, the closed-loop image representation of nonlinear systems is identified using gate recurrent units and fully connected neural networks. The involved network topology is designed to learn the nonlinear mapping in the form of linear time-varying state space, allowing the extension of existing linear methods to nonlinear systems. Then, with the identified image representation, the data-driven realization of kernel representation is derived. Finally, the residual generator is developed utilizing the system's kernel representation to enable precise fault detection in nonlinear systems. The effectiveness of our study is demonstrated through a numerical benchmark study and an actual experiment on a real Mecanum-wheeled vehicle platform.

关键词： Nonlinear systems Fault detection Image representation Generators Fault diagnosis Deep learning Linear systems Computational modeling Training Knowledge based systems data-driven fault detection kernel representation neural networks nonlinear systems

来源：评论

学校读者我要写书评

暂无评论

Safe data-driven Predictive control

引用

ieee Transactions on Automation Science and Engineering 2025年 22卷 14422-14435页

作者： Vahidi-Moghaddam, Amin Chen, Kaian Zhang, Kaixiang Li, Zhaojian Wang, Yan Wu, Kai Michigan State University Department of Mechanical Engineering East LansingMI48824 United States Ford Motor Company Research and Advanced Engineering DearbornMI48121 United States

In the realm of control systems, model predictive control (MPC) has exhibited remarkable potential;however, its reliance on accurate models and substantial computational resources has hindered its broader application, especially within real-time nonlinear systems. This study presents an innovative control framework to enhance the practical viability of the MPC. The developed safe data-driven predictive control aims to eliminate the requirement for precise models and alleviate computational burdens in the nonlinear MPC (NMPC). This is achieved by learning both the system dynamics and the control policy, enabling efficient data-driven predictive control while ensuring system safety. The methodology involves a spatial temporal filter (STF)-based concurrent learning for system identification, a robust control barrier function (RCBF) to ensure the system safety amid model uncertainties, and a RCBF-based NMPC policy approximation. An online policy correction mechanism is also introduced to counteract performance degradation caused by the existing model uncertainties. Demonstrated through simulations on two applications, the proposed approach offers comparable performance to existing benchmarks with significantly reduced computational costs. © 2004-2012 ieee.

关键词： Predictive control Uncertainty Safety Computational modeling System identification Adaptation models Trajectory System dynamics Robust control Predictive models

来源：评论

学校读者我要写书评

暂无评论

The Q-Fractionalism Reasoning learning Method

引用

ieee TRANSACTIONS ON NEURAL NETWORKS AND learning systems 2025年第1期36卷 1568-1582页

作者： Mazandarani, Mehran Jianfei, Pan Shenzhen Univ Dept Mechatron & Control Engn Shenzhen 518060 Peoples R China

As the title suggests, in this work, a modern machine learning method called the Q-fractionalism reasoning is introduced. The proposed method is founded upon a synergy of the Q-learning and fractional fuzzy inference systems (FFISs). Unlike other approaches, the Q-fractionalism reasoning not only incorporates the knowledge base to understand how to perform but also explores a reasoning mechanism from the fractional order to justify what it has performed. This method suggests that the agent choose actions aimed at the characterization of reasoning. In fact, the agent deals with states termed as primary and secondary fuzzy states. The primary fuzzy states are unobservable and uncertain, for which the agent chooses actions. However, the projection of primary fuzzy states onto the knowledge base results in secondary fuzzy states, which are observable by the agent, allowing it to detect primary fuzzy states with degrees of detectability. With a practical experiment implemented on a linear switched reluctance motor (LSRM), the results demonstrate that the application of the Q-fractionalism reasoning in the real-time position control of the LSRM leads to a remarkable improvement of about 70% in the accuracy of the control objective compared with a typical fuzzy inference system (FIS) under the same setting.

关键词： Artificial intelligence computational intelligence data-driven control systems fuzzy systems reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Applications of data-driven Dynamic Modeling of Power Converters in Power systems: An Overview

引用

ieee TRANSACTIONS ON INDUSTRY APPLICATIONS 2025年第2期61卷 2434-2456页

作者： Subedi, Sunil Gui, Yonghao Xue, Yaosuo Oak Ridge Natl Lab Electrificat & Energy Infrastruct Div Oak Ridge TN 37831 USA

Power electronic converter (PEC)-based resources are growing ubiquitously in power systems and there is a vital necessity for precise dynamic models to comprehend their dynamics to different events and control strategies. Inaccurate modeling can lead to instability, higher costs, and reliability issues. Anticipating the increase in PECs in the near future, detailed modeling becomes computationally and mathematically complex, requiring extensive computing power and knowledge of vendor-specific PECs. To overcome these challenges, data-driven machine learning/artificial intelligence (ML/AI) approaches are widely used, tracking the dynamic responses of PECs operating in various modes with limited knowledge. These models find applications in protection, stability, fault diagnosis, optimization, control and monitoring, and power quality. While the literature on power systems often emphasizes the advantages of data-driven modeling, an in-depth look at the limitations, challenges, and opportunities related to converter-dominated grids is still lacking. The purpose of this survey is to conduct a comprehensive review of ML/AI methodologies in PECs and investigate their applications in power systems. The article introduces various PEC types, their roles, and modeling approaches. It then provides an in-depth overview of how ML/AI can be applied to PECs in power systems. Finally, the survey highlights gaps in the field's knowledge and suggests potential directions for future research.

关键词： Power system stability Power system dynamics Computational modeling Reviews Hidden Markov models Vehicle dynamics Topology Load modeling Matrix converters Dynamic scheduling Artificial intelligence converter-dominated data-driven modeling dynamics fault diagnosis power electronic converter power quality protection stability

来源：评论

学校读者我要写书评

暂无评论

data-driven Iterative learning Temperature control for Rubber Mixing Processes

引用

ieee TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING 2025年 22卷 10274-10286页

作者： Chi, Ronghu Zhou, Zhihao Zhang, Huimin Lin, Na Huang, Biao Qingdao Univ Sci & Technol Coll Automat & Elect Engn Qingdao 266061 Peoples R China Shandong Technol & Business Univ Sch Informat & Elect Engn Yantai 264005 Peoples R China Univ Alberta Dept Chem & Mat Engn Edmonton T6G 2G6 AB Canada

Considering the four challenges of non-identical initial states, non-repetitive uncertainties, different batch lengths, and unavailable mathematical model of a rubber mixing process (RMP), this article proposes a data-driven iterative learning temperature control (DDILTC) for the RMP. Specifically, an iterative linear data model (iLDM) is developed to formulate the iterative dynamics of RMP and is further used as a one-step iterative linear predictive model to estimate the RMP's temperature that is unavailable when the current batch length is shorter than the desired one. The unknown parameters of the iLDM are estimated iteratively by designing an iterative adaption law. Further, an iterative learning based observer is designed to estimate the non-repetitive uncertainties and non-identical initial states as an extended state. The proposed DDILTC is a data-driven method and the iLDM is only used to formulate the iterative relationship of the input-output between two batches instead of a mathematical model of the RMP with physical meanings. Simulation study verifies the results. Note to Practitioners-The mixing temperature of a rubber mixing process (RMP) is a critical variable, ensuring the desired plasticity and viscosity of the rubber compounds. Indeed, RMP is a typical batch process performing repetitively over the finite time interval. However, no ILC results about the RMP temperature control have been reported even though ILC can learn the control experience from the past batches to improve control performance. The main reason lies in that the practical environments of RMP make it impossible to satisfy the strictly repetitive conditions, i.e., the initial states, disturbances, and batch lengths are all iteration-varying. Furthermore, it is difficult to establish a mathematical model of the RMP due to its large production scale and complex dynamics along both time and iteration directions. Therefore, the main motivation of this paper is to study the iterative lea

关键词： Temperature control Iterative methods Uncertainty Rubber Mathematical models Batch production systems Process control Hands Compounds Artificial neural networks Rubber mixing process non-identical initial states nonrepetitive uncertainties different batch lengths data-driven control iterative learning temperature control

来源：评论

学校读者我要写书评

暂无评论

Adaptive Fuzzy Iterative learning control of Constrained systems With Arbitrary Initial State Errors and Unknown control Gain

引用

ieee TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING 2025年 22卷 6439-6450页

作者： Shi, Huihui Chen, Qiang Hong, Yihuang Ou, Xianhua He, Xiongxiong Zhejiang Univ Technol Coll Informat Engn Data Driven Intelligent Syst Lab Hangzhou 310023 Zhejiang Peoples R China

An adaptive fuzzy iterative learning control(AFILC) method is presented to address the state tracking issue of constrained systems with arbitrary initial state errors and unknown control gain. A novel desired error trajectory is systematically developed in the polynomial form to relax the identical initial condition, which allows for arbitrary setting of initial values for all the system state errors. The proposed desired error trajectory can also relax the iteration-invariance restriction on the reference signals due to the independence of the reference trajectories. An asymmetric integral fractional barrier Lyapunov function is developed, keeping the tracking error within the preassigned boundary. Moreover, there is no need to estimate the unknown control gain function in the controller design, reducing computation burden. Numerical simulations and experiments in the permanent magnet synchronous motor experimental platform are provided to illustrate the efficacy of the proposed method.

关键词： Trajectory Iterative learning control Adaptive systems Process control Polynomials Lyapunov methods Fuzzy logic Adaptive fuzzy iterative learning control integral barrier Lyapunov function desired error trajectory unknown control gain

来源：评论

学校读者我要写书评

暂无评论

Finite-Horizon Optimal control for Nonlinear Multi-Input systems With Online Adaptive Integral Reinforcement learning

引用

ieee TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING 2025年 22卷 802-812页

作者： Lv, Yongfeng Zhang, Wan Zhao, Jun Zhao, Xiaowei Taiyuan Univ Technol Coll Elect & Power Engn Taiyuan 030024 Peoples R China Shandong Univ Sci & Technol Coll Transportat Qingdao 266590 Peoples R China Univ Warwick Sch Engn Coventry CV4 7AL W Midlands England

In this paper, a novel adaptive integral reinforcement learning (AIRL) is utilized to online handle the finite-horizon optimum control policies of the partially unknown multi-input nonlinear system. Firstly, the concept of Nash equilibrium is introduced to make the multiple cost functions reach the saddle point. Then, dual neural networks (NNs) are applied to approach the performance index functions based on the integral reinforcement signal. Simultaneously, two novel learning algorithms are proposed to update the NN weights, in which the convergence of weights is proved. Then, the optimal strategies can be obtained by using the obtained weights. The designed controllers based on the data-driven AIRL scheme can avoid the internal state of the system and the derivatives of NN activations in the weight learning process. Finally, the stability of the controlled system is analyzed. An F-16 aircraft model and another nonlinear system are utilized to prove the validity and rationality of the algorithm. Note to Practitioners-There exist many multi-input systems in practical engineering, which includes multi-engine driven F-16 aircraft, large radar servo system and large artillery systems, etc. The finite-horizon optimal control of these systems is crucial for the better performance of system state. However, an accurate engineering model is difficult to obtain, and the finite-horizon cannot generally be achieved. To address these issues, this paper proposes the finite-horizon optimal control for these systems based on a novel adaptive integral reinforcement learning (AIRL). The AIRL can realize an optimal performance for these multi-input systems in finite-time without internal system dynamics, which is a good development for the multi-input system in practical engineering.

关键词： Integral reinforcement learning finite horizon optimal control multi-input system Nash equilibrium adaptive law

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

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

Efficient Replay Deep Meta-Reinforcement learning for Active Fault-Tolerant control of Solid Oxide Fuel Cell systems Considering Multivariable Coordination

引用

ieee TRANSACTIONS ON TRANSPORTATION ELECTRIFICATION 2025年第1期11卷 4803-4817页

作者： Li, Jiawen Zhou, Tao Shanghai Univ Elect Power Sch Elect & Informat Engn Shanghai 201306 Peoples R China Shanghai Jiao Tong Univ Sch Elect Informat & Elect Engn Dept Elect Engn Shanghai 200240 Peoples R China

A data-driven integrated active fault-tolerant control (IAFT) strategy for controlling the solid oxide fuel cell (SOFC) output voltage is proposed, which maintains satisfactory dynamic performance and eliminates constraint violations in the event of system failure. In addition, this article introduces an efficient replay deep meta-deterministic policy gradient (ER-DMDPG) for IAFTs, which combines priority experience replay and meta-learning techniques to improve the robustness and multitask cooperative learning capability of the IAFTs. The algorithm combines the controllers of the fuel reformer and direct current-direct current (dc-dc) converter into a single independent agent, which is trained by a cooperative meta-learner and a base learner to achieve multiobjective optimal active fault-tolerant control (FTC). It is experimentally demonstrated that the proposed method can maintain better dynamic performance and prevent constraint violations of fuel utilization across a wide range of working conditions.

关键词： Fault tolerant systems Fault tolerance Hydrogen Voltage control Fuels Fuel cells Temperature control Prediction algorithms Heuristic algorithms Genetic algorithms Active fault-tolerant integrated control constraint violations deep meta-reinforcement learning (DMRL) fuel utilization solid oxide fuel cell (SOFC)

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：