检索结果-内蒙古大学图书馆

3rd International Conference on Computer, Artificial Intelligence and control Engineering, CAICE 2024

作者： Chen, Wei Wan, Haiying Luan, Xiaoli Liu, Fei Key Laboratory of Advanced Process Control for Light Industry Institute of Automation Jiangnan University Wuxi China

ISBN: (纸本)9798400716942

In this research, we introduce a novel model-free self-triggered control strategy for linear systems, employing a hierarchical reinforcement learning approach. This strategy establishes a dual-Actor Critic hierarchical architecture, utilizing two neural networks that guide each other's decision-making to simulate the triggering and control strategies in self-triggered control. The triggering strategy, serving as the top-level policy, aims to find the maximum triggering interval that maintains system stability based on the initial control strategy. The control strategy, as the bottom-level policy, under the guidance of the triggering strategy, takes the optimization of control performance considering the impact of triggering intervals as a sub-goal. This approach reduces the exploration space of the bottom-level policy and accelerates the reinforcement learning process. In the implementation of the dual-Actor Critic algorithm, the Critic network employs recurrent neural networks to capture the temporal dependencies of expected rewards, thereby enhancing the efficiency and accuracy in approximating the Q-function. The efficacy of our proposed method is demonstrated through a series of numerical simulations. Theory of computation∼Theory and algorithms for application domains∼Machine learning theory∼Reinforcement learning∼Sequential decision making. © 2024 ACM.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Electrical Scheme Digitization Using Deep Learning Methods 46

Electrical Scheme Digitization Using Deep Learning Methods

引用

46th ICT and Electronics Convention, MIPRO 2023

作者： Putak, Marko Baksa, Vatroslav Zuppa Bednjanec, Andrea Zagreb University of Applied Sciences/Automation and Process Control Engineering Zagreb Croatia

ISBN: (纸本)9789532331042

The use of software tools and applications progressively became a standard in both education and industry. A solution for hand-drawn electrical scheme digitization has been proposed to match the fast-paced dynamic of the modern world in the field of electrical engineering. The aim is to notably reduce time-consuming and error-prone electrical scheme tracing from hand-drawn to simulating software. The means have been achieved through the usage of state-of-the-art deep learning model YOLOv5 for electrical elements detection along with Python and OpenCV library for data processing. The user's input is an image of a hand-drawn circuit, and the end result is an LTspice digitized electrical scheme ready for simulation. © 2023 MIPRO Croatian Society.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Data-based prediction of the correction roll intermesh in industrial hot-dip galvanizing lines

Data-based prediction of the correction roll intermesh in in...

引用

2023 IEEE Conference on control Technology and Applications, CCTA 2023

作者： Marko, Lukas Kugi, Andreas Steinboeck, Andreas Tu Christian Doppler Laboratory for Intelligent Process Control for High-Quality Steel Products Automation and Control Institute Wien Austria Tu Automation and Control Institute Wien Austria

ISBN: (纸本)9798350335446

In the continuous hot-dip galvanizing process, the final zinc coating thickness is heavily influenced by the distance between the strip surface and the gas wiping dies which blow off excess zinc. To this end, establishing a flat, non-curved strip is a key prerequisite to minimize coating thickness deviations and inhomogeneities. A common way to influence the lateral strip profile is to introduce a controlled plastic deformation of the strip at the guiding rolls in the zinc bath. This motivates a data-based study of the optimal roll intermesh value of the zinc bath rolls to achieve a flat (zero-crossbow) strip profile during the galvanizing process. Based on this analysis, a data-based algorithm for the online prediction of the optimal roll intermesh value at the head end of each strip is developed and implemented in an industrial processing line. The prediction results from 1045 strips demonstrate the feasibility and accuracy of the proposed prediction algorithm. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Adaptive Optimal Output Regulation of Interconnected Singularly Perturbed Systems With Application to Power Systems

引用

IEEE/CAA Journal of Automatica Sinica 2024年第3期11卷 595-607页

作者： Jianguo Zhao Chunyu Yang Weinan Gao Linna Zhou Xiaomin Liu the Engineering Research Center of Intelligent Control for Underground Space Ministry of EducationChina University of Mining and TechnologyXuzhou 221116 the School of Information and Control Engineering China University of Mining and TechnologyXuzhou 221116 IEEE the State Key Laboratory of Synthetical Automation for Process Industries Northeastern UniversityShenyang 110819China

This article studies the adaptive optimal output regulation problem for a class of interconnected singularly perturbed systems(SPSs) with unknown dynamics based on reinforcement learning(RL).Taking into account the slow and fast characteristics among system states,the interconnected SPS is decomposed into the slow time-scale dynamics and the fast timescale dynamics through singular perturbation *** the fast time-scale dynamics with interconnections,we devise a decentralized optimal control strategy by selecting appropriate weight matrices in the cost *** the slow time-scale dynamics with unknown system parameters,an off-policy RL algorithm with convergence guarantee is given to learn the optimal control strategy in terms of measurement *** combining the slow and fast controllers,we establish the composite decentralized adaptive optimal output regulator,and rigorously analyze the stability and optimality of the closed-loop *** proposed decomposition design not only bypasses the numerical stiffness but also alleviates the *** efficacy of the proposed methodology is validated by a load-frequency control application of a two-area power system.

关键词： Adaptive optimal control decentralized control output regulation reinforcement learning(RL) singularly perturbed systems(SPSs)

来源：评论

学校读者我要写书评

暂无评论

Graph-guided masked autoencoder for process anomaly detection

引用

process Safety and Environmental Protection 2024年 186卷 1345-1357页

作者： Jia, Mingwei Xu, Danya Yang, Tao Yao, Yuan Liu, Yi Institute of Process Equipment and Control Engineering Zhejiang University of Technology Hangzhou310023 China State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang110819 China Department of Chemical Engineering National Tsing Hua University Hsinchu300044 Taiwan

Developing an accurate and reliable anomaly detection model is of great significance for safe operation in the process industry. To minimize false positives, it is crucial to accurately model the intricate topological and nonlinear connections among variables. In this study, a process anomaly detection method based on graph-guided masked autoencoder (GGMAE) is proposed by introducing the concept of the graph to the process industry. GGMAE first constructs a topology graph according to the process flowchart. Then, the patch and mask mechanism forces GGMAE to learn the process intrinsic information to reconstruct the input according to the variable topological relationship and temporal characteristics. Additionally, Kullback-Leibler divergence is used as the loss to ensure that the distribution of input and output is consistent. Experiments on two publicly available anomaly detection benchmarks demonstrate the superiority of GGMAE over existing methods. Visualization of the results demonstrates the physically compliant reconstruction logic. © 2024 The Institution of Chemical Engineers

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Consistency before Availability: Network Reference Point based Failure Detection for controller Redundancy 28

Consistency before Availability: Network Reference Point bas...

引用

28th IEEE International Conference on Emerging Technologies and Factory automation, ETFA 2023

作者： Johansson, Bjarne Rågberger, Mats Papadopoulos, Alessandro V. Nolte, Thomas ABB Process Automation Process Control Platform Västerås Sweden Mälardalen University Västerås Sweden

ISBN: (纸本)9798350339918

Distributed control systems constitute the automation solution backbone in domains where downtime is costly. Redundancy reduces the risk of faults leading to unplanned downtime. The Industry 4.0 appetite to utilize the device-to-cloud continuum increases the interest in network-based hardware-agnostic controller software. Functionality, such as controller redundancy, must adhere to the new ground rules of pure network dependency. In a standby controller redundancy, only one controller is the active primary. When the primary fails, the backup takes over. A typical network-based failure detection uses a cyclic message with a known interval, a.k.a. a heartbeat. Such a failure detection interprets heartbeat absences as a failure of the supervisee;consequently, a network partitioning could be indistinguishable from a node failure. Hence, in a network partitioning situation, a conventional heartbeat-based failure detection causes more than one active controller in the redundancy set, resulting in inconsistent outputs. We present a failure detection algorithm that uses network reference points to prevent network partitioning from leading to dual primary controllers. In other words, a failure detection that prioritizes consistency before availability. © 2023 IEEE.

关键词： controllers

来源：评论

学校读者我要写书评

暂无评论

Dependability and Security Aspects of Network-Centric control 28

Dependability and Security Aspects of Network-Centric Contro...

引用

28th IEEE International Conference on Emerging Technologies and Factory automation, ETFA 2023

作者： Leander, Björn Johansson, Bjarne Lindström, Tomas Holmgren, Olof Nolte, Thomas Papadopoulos, Alessandro V. Process Control Platform ABB Process Automation Västerås Sweden Mälardalen University Västerås Sweden

ISBN: (纸本)9798350339918

Industrial automation and control systems are responsible for running our most important infrastructures, providing electricity and clean water, producing medicine and food, along with many other services and products we take for granted. The safe and secure operation of these systems is therefore of great *** of the emerging trends in industrial automation systems is the transition from static hierarchical controller-centric systems to flexible network-centric systems. This transition has a great impact on the characteristics of industrial automation systems. In this article we describe the network-centric design strategy for industrial automation systems and describe the impact on dependability and security aspects that this strategy brings, looking at both challenges and possibilities. © 2023 IEEE.

关键词： Hierarchical systems

来源：评论

学校读者我要写书评

暂无评论

Model-Free H2/H∞ Predictive control for Discrete-Time System via Q-Learning 13

Model-Free H2/H∞ Predictive Control for Discrete-Time Syste...

引用

13th IEEE Data Driven control and Learning Systems Conference, DDCLS 2024

作者： Lin, Yihong He, Peng Wan, Haiying Liu, Zhuangyu Luan, Xiaoli Liu, Fei Institute of Automation Jiangnan University Key Laboratory of Advanced Process Control for Light Industry Ministry of Education Wuxi214122 China

ISBN: (纸本)9798350361674

This paper presents a model-free H2/H∞ Q-learning predictive control strategy for linear discrete-time systems. To design predictive controller with the system measured states, a policy iteration solution algorithm is employed to approximate the control inputs. Specifically, the developed algorithm is formulated in the form of linear matrix inequalities, designed to stabilize the system with mixed H2/H∞ control performance. Additionally, to improve robust performance under system disturbance variations, we introduce the receding horizon optimization into the Q-learning based predictive control. Finally, simulation results demonstrate the effectiveness of the proposed approach. © 2024 IEEE.

关键词： H2/H∞ performance index Model-free predictive control Q-learning Receding horizon optimization Unknown discrete-time systems

来源：评论

学校读者我要写书评

暂无评论

Bayesian Filtering for High-Dimensional State-Space Models With State Partition and Error Compensation

引用

IEEE/CAA Journal of Automatica Sinica 2024年第5期11卷 1239-1249页

作者： Ke Li Shunyi Zhao Biao Huang Fei Liu Key Laboratory of Advanced Process Control for Light Industry(Ministry of Education) Institute of AutomationJiangnan UniversityWuxi 214122China Department of Chemical and Materials Engineering University of AlbertaEdmonton AB T6G 2G6Canada

In the era of exponential growth of data availability,the architecture of systems has a trend toward high dimensionality,and directly exploiting holistic information for state inference is not always computationally *** paper proposes a novel Bayesian filtering algorithm that considers algorithmic computational cost and estimation accuracy for high-dimensional linear *** high-dimensional state vector is divided into several blocks to save computation resources by avoiding the calculation of error covariance with immense *** that,two sequential states are estimated simultaneously by introducing an auxiliary variable in the new probability space,mitigating the performance degradation caused by state ***,the computational cost and error covariance of the proposed algorithm are analyzed analytically to show its distinct features compared with several existing *** results illustrate that the proposed Bayesian filtering can maintain a higher estimation accuracy with reasonable computational cost when applied to high-dimensional linear systems.

关键词： filtering estimation error

来源：评论

学校读者我要写书评

暂无评论

OPC UA PubSub and Industrial controller Redundancy

OPC UA PubSub and Industrial Controller Redundancy

引用

International Conference on Emerging Technologies and Factory automation (ETFA)

作者： Bjarne Johansson Olof Holmgren Martin Dahl Hakan Forsberg Thomas Nolte Alessandro V. Papadopoulos ABB Process Automation Process Control Platform Vasteras Sweden ABB Process Automation Process Control Platform Minden Germany Mälardalen University Vasteras Sweden

ISBN: (数字)9798350361230

ISBN: (纸本)9798350361247

Industrial controllers constitute the core of numerous automation solutions. Continuous control system operation is crucial in certain sectors, where hardware duplication serves as a strategy to mitigate the risk of unexpected operational halts due to hardware failures. Standby controller redundancy is a commonly adopted strategy for process automation. This approach involves an active primary controller managing the process while a passive backup is on standby, ready to resume control should the primary fail. Typically, redundant controllers are paired with redundant networks and devices to eliminate any single points of failure. The process automation domain is on the brink of a paradigm shift towards greater interconnectivity and interoperability. OPC UA is emerging as the standard that will facilitate this shift, with OPC UA PubSub as the communication standard for cyclic real-time data exchange. Our work investigates standby redundancy using OPC UA PubSub, analyzing a system with redundant controllers and devices in publisher-subscriber roles. The analysis reveals that failovers are not subscriber-transparent without synchronized publisher states. We discuss solutions and experimentally validate an internal stack state synchronization alternative.

关键词： Redundancy process control control systems Hardware Real-time systems Synchronization Standards Manufacturing automation Interoperability Communication standards

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：