检索结果-内蒙古大学图书馆

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

作者： Liu, Xin Zhang, Qiang Wang, QiWen Xue, GuoQing Xu, Bo School of Navigation of Shipping Shandong Jiaotong University Weihai264209 China Shandong Port Group Co. Ltd Qing Dao266000 China Qingdao Pilot Station 266000 China

ISBN: (纸本)9798350361674

This article proposes an adaptive neural network event triggered control scheme based on virtual parameter learning for ship automatic berthing control under false data injection (FDI) attack environment, which is simultaneously affected by external interference, uncertain dynamics, and input saturation. In the controller design process, neural network technology and adaptive virtual parameter learning methods are combined to perform online reconstruction compensation for actuator signal mutations, uncertain dynamics, and external disturbances caused by FDI attacks. In addition, event triggering mechanism is adopted to reduce communication load and channel occupancy rate. Finally, the stability of the control law was analyzed using Lyapunov theory, and the effectiveness of the scheme was verified through comparative simulation experiments. The simulation results showed that the control algorithm proposed in this paper has superior control performance and steady-state performance in FDI attack environments. In practical engineering applications, this scheme can provide theoretical support for the automatic berthing of intelligent ships. © 2024 ieee.

关键词： Sliding mode control

来源：评论

学校读者我要写书评

暂无评论

Model Predictive control for Offset-free Tracking: a new data-driven application for Secondary Voltage Regulation on Transmission Network

Model Predictive Control for Offset-free Tracking: a new dat...

引用

International conference on Smart Energy systems and Technologies (SEST) - Driving the Advances for Future Electrification

作者： Acerbi, Federica Piccagli, Davide Stefano Pozzi, Fabio Sciarpa, Luca Giannuzzi, Giorgio Maria Pisani, Cosimo Bruno, Gianluca CESI SpA Milan Italy Terna SpA Rome Italy

ISBN: (纸本)9798350386509;9798350386493

This paper investigates the evolution of Secondary Voltage Regulation (SVR) in response to the increasing penetration of enewable energy sources (RES) within power systems. Traditional SVR, historically reliant on fossil fuel-based plants, faces challenges stemming from their under-utilization and intermittent operation. As conventional power plants decline, emerging resources such as synchronous compensators and STATCOMS offer voltage control capabilities without compromising RES integration, prompting the need for a redesigned control system to effectively harness their capabilities and optimize voltage regulation performance in an increasingly dynamic network environment. In this evolving scenario, a review of SVR literature reveals a shift towards data-driven methodologies, leveraging real-world data for improved control strategies. To address these challenges, a new Secondary Voltage Regulator is proposed based on a data-driven Model Predictive control (MPC) approach, designed for offset-free tracking. The suggested approach, known for its proficiency in tracking, has been adjusted to provide an implementation suitable for the Italian transmission system. Field tests conducted on Sicilian transmission network validate the effectiveness of the MPC-based controller under real-world conditions, filling an important gap in understanding its performance and applicability in transmission systems.

关键词： data-driven Modeling Model Predictive control Reactive Power Management Secondary Voltage control

来源：评论

学校读者我要写书评

暂无评论

data-driven Stabilization of Input-Saturated systems

引用

ieee control systems LETTERS 2023年 7卷 1640-1645页

作者： Breschi, Valentina Zaccarian, Luca Formentin, Simone Eindhoven Univ Technol Dept Elect Engn NL-5600 MB Eindhoven Netherlands Univ Toulouse LAAS CNRS F-31000 Toulouse France Univ Trento Dip Ing Ind I-38122 Trento Italy Politecn Milan Dipartimento Elettron Informaz & Bioingn I-20133 Milan Italy

We provide a data-driven stabilization approach for input-saturated systems with formal Lyapunov guarantees. Through a generalized sector condition, we propose a convex design algorithm based on linear matrix inequalities for obtaining a regionally stabilizing data-driven static state-feedback gain. Regional, rather than global, properties allow us to address non-exponentially stable plants, thereby making our design broad in terms of applicability. Moreover, we discuss consistency issues and introduce practical tools to deal with measurement noise. Numerical simulations show the effectiveness of our approach and its sensitivity to the features of the dataset.

关键词： Noise measurement State feedback Stability analysis Predictive models Numerical stability Lyapunov methods Linear systems data-driven control input saturation

来源：评论

学校读者我要写书评

暂无评论

data Augmented Rule-based Expert System to control a Hybrid Storage System 22

Data Augmented Rule-based Expert System to Control a Hybrid ...

引用

ieee 22nd Mediterranean Electrotechnical conference (MELECON)

作者： Bessa, Ricardo J. Lobo, Francisco Fernandes, Francisco Silva, Bernardo INESC TEC Ctr Power & Energy Syst CPES Porto Portugal CPES Porto Portugal INESC TEC Dept Elect & Comp Engn Porto Portugal Univ Porto Fac Engn Porto Portugal

ISBN: (纸本)9798350387032;9798350387025

Hybrid storage systems that combine high energy density and high power density technologies can enhance the flexibility and stability of microgrids and local energy communities under high renewable energy shares. This work introduces a novel approach integrating rule-based (RB) methods with evolutionary strategies (ES)-based reinforcement learning. Unlike conventional RB methods, this approach involves encoding rules in a domain-specific language and leveraging ES to evolve the symbolic model via data-driven interactions between the control agent and the environment. The results of a case study with Liion and redox flow batteries show that the method effectively extracted rules that minimize the energy exchanged between the community and the grid.

关键词： Hybrid storage control symbolic evolutionary strategies reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Physics-Guided Multi-Agent Deep Reinforcement learning for Robust Active Voltage control in Electrical Distribution systems

引用

ieee TRANSACTIONS ON CIRCUITS AND systems I-REGULAR PAPERS 2024年第2期71卷 922-933页

作者： Chen, Pengcheng Liu, Shichao Wang, Xiaozhe Kamwa, Innocent Carleton Univ Dept Elect Ottawa ON K1S 5B6 Canada McGill Univ Dept Elect & Comp Engn Montreal PQ H3A 0G4 Canada Laval Univ Dept Elect & Comp Sci Engn Quebec City PQ G1V 0A6 Canada

Although several multi-agent deep reinforcement learning (MADRL) algorithms have been employed in power distribution networks configured with high penetration level of Photovoltaic (PV) generators for active voltage control (AVC), the impact of the voltage fluctuation of a single PV node on voltage violations of other PV nodes in the network is ignored. Consequently, it leads to the conservativeness of the existing MADRL based AVC algorithms. In this paper, a robust MADRL control algorithm is designed to minimize the nodal voltage violation and line loss with the exploration of coupling voltage fluctuations across all the controlled nodes by coordinating PV inverters, and a physics factor is utilized to guide (physics-guided) the training policy with the expectation of a better performance compared to existing purely data-driven methods. In the proposed physics-guided multi-agent adversarial twin delayed deep deterministic (PG-MA2TD3) policy gradient algorithm, a physics factor, global sensitivity of voltage (GSV), is properly embedded in the algorithm to measure the influence of the nodal voltage fluctuation on voltage violations on the other controlled nodes with PV inverters and this GSV is shared in the learning center to guide the centralized learning and decentralized execution process. The multi-agent adversarial learning (MAAL) embedded with the GSV to seek an adaptive descend gradient for reducing the Q-value function appropriately rather than always assuming the worst case. Therefore, this physics-guided method can reduce the conservation and provide significantly better reward. Finally, the proposed algorithm is compared with several other methods on ieee 33-bus, 141-bus and 322-bus with three-year data in Portuguese and the results indicate the proposed method can obtain the minimal voltage fluctuation and the best reward in the comparisons.

关键词： Distribution networks Voltage fluctuations active voltage control multi-agent deep reinforcement learning multi-agent adversarial learning static var compensators

来源：评论

学校读者我要写书评

暂无评论

An Unsupervised Approach to Wind Turbine Blade Icing Detection Based on Beta Variational Graph Attention Autoencoder

引用

ieee TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2024年 73卷 1页

作者： Wang, Lei He, Yigang Shao, Kaixuan Xing, Zhikai Zhou, Yazhong Wuhan Univ Sch Elect Engn & Automat State Key Lab Power Grid Environm Protect Wuhan 430072 Peoples R China

Supervised deep-learning methods are data driven and widely used for wind turbine blade icing detection (ID). data-driven methods generally require a complete dictionary of labeled sensor data. However, labeling sensor data increases engineering costs and can introduce costly errors such as incorrect data labels. In addition, the reported data-driven approaches ignore the contribution of structural properties of multivariate sensor data to failure patterns identification. To address these shortcomings, the current study proposes a beta variational graph attention autoencoder (beta-VGATAE) for blade ID. The beta-VGATAE model employs a beta variational autoencoder (beta-VAE) architecture to achieve unsupervised learning. A graph attention network is used as a spatial feature extractor within the beta-VAE architecture since it considers the spatial structure of the sensor data. Actual sensor data from supervisory control and data acquisition systems were used to validate the proposed model. Specifically, we verified the rationality of designing each component in the beta-VGATAE. Experimental results show that the highest levels of accuracy achieved were 90.9% and 93.4% for the respective scenarios involving two wind turbines;the beta-VGATAE detection model has high accuracy and excellent generalization ability.

关键词： Beta variational autoencoder (beta-VAE) graph attention network (GAT) icing detection (ID) unsupervised learning wind turbine

来源：评论

学校读者我要写书评

暂无评论

Model Analysis and Optimization Design Strategy for a Class of Heliostat Field systems 13

Model Analysis and Optimization Design Strategy for a Class ...

引用

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

作者： Fa, Yuchao Zhang, Chenxuan Song, Yunjin Zhang, Ruikun College of Information Science and Technology Qingdao University of Science and Technology Qingdao266061 China School of Mathematics and Physics Qingdao University of Science and Technology Qingdao266061 China College of Chemistry and Molecular Engineering Qingdao University of Science and Technology QingDao266045 China

ISBN: (纸本)9798350361674

It is a critical issue to accurately calculate and optimize the various performances of a heliostat field. This paper presents a model for calculating the cosine efficiency using vector computation. Subsequently, another model based on ray tracing is established to calculate both the shading and blocking efficiency and receiver interception efficiencies. Lastly, this paper has adopted a graph-theory algorithm to expedite the calculation process of the ray tracing model and has presented an optimization design strategy for a specific heliostat field, which has a radius limit of 350m and is located at a latitude of 39.4°. This have increased its average annual power generation by 31.66% and per square meter power lightly. © 2024 ieee.

关键词： Graph algorithms

来源：评论

学校读者我要写书评

暂无评论

data-driven Thermal Modeling for Electrically Excited Synchronous Motors - A Supervised Machine learning Approach

Data-driven Thermal Modeling for Electrically Excited Synchr...

引用

Transportation Electrification conference and Expo (ITEC)

作者： Tatari, Farzaneh Trapp, Davis Schneider, Jason Aligoudarzi, Mohsen Mirza Drive Syst Design Inc Control Syst Farmington Hills MI 48335 USA

ISBN: (纸本)9798350317671;9798350317664

This paper proposes a data-driven supervised machine learning (ML) for online thermal modeling of electrically excited synchronous motors (EESMs). EESMs are desired for EVs due to their high performance, efficiency, and durability at a relatively low cost. Therefore, obtaining precise EESM temperature estimations are significantly important, because online accurate temperature estimation can lead to EESM performance improvement and guaranteeing its safety and reliability. In this study, in addition to the default inputs' data, EESM losses data is leveraged to improve the performance of the proposed ML approach for thermal modeling. Exponentially weighted moving averages and standard deviations of the inputs are also incorporated in the learning process to consider the memory effect for modeling a dynamical thermal model. Using the experimental data of an EESM prototype, the performance of ordinary least squares (OLS) method is evaluated through a complete training, testing and cross-validation process. Finally, simulation results will provide the key performance metrics of OLS for EESM thermal modeling.

关键词： data-driven learning Electrically excited synchronous motors (EESMs) Machine learning (ML) Thermal modeling

来源：评论

学校读者我要写书评

暂无评论

Distributed control Problems of Second-Order Directed Signed Networks Based on Sampled data 13

Distributed Control Problems of Second-Order Directed Signed...

引用

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

作者： Lil, Jinchao Zhang, Yi Du, Mingjun Pang, Shaopeng Ji, Peng Shandong Province Jinan250353 China

ISBN: (纸本)9798350361674

In this study, the bipartite consensus problem of directed signed network based on sampled data is studied. A control protocol for second-order signed network is proposed, which is based on sampling data. By leveraging principles of the Laplacian matrix and graph theory, the protocol is derived, and the necessary and sufficient conditions for achieving bipartite consensus and state stability are identified. The research findings suggest that bipartite consensus can be reached in structurally balanced network topologies with the correct choice of sampling period and parameters, whereas state stability is achievable in structurally unbalanced configurations. In addition, simulation examples are used to verify the accuracy of the derived results. © 2024 ieee.

关键词： bipartite consensus Sampled data signed network structural balance

来源：评论

学校读者我要写书评

暂无评论

Optimal Tracking control for Constrained Two-Link Robot Based on Adaptive Dynamic Programming 13

Optimal Tracking Control for Constrained Two-Link Robot Base...

引用

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

作者： Liao, Xin Wang, Kang Li, Xiaoli Faculty of Information Technology Beijing University of Technology Beijing100124 China Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing100124 China

ISBN: (纸本)9798350361674

This paper introduces a novel state and input constrained optimal tracking control method to address limitations posed by only partially known robot system models and constrained physical variables, such as joint position, velocity, and torque during the control process. The method employs the slack function and nonquadratic function methods to effectively handle state error and input constraints, ensuring the overall stationarity and safety of the control process. Subsequently, the adaptive dynamic programming (ADP) algorithm is designed to formulate update laws for the approximating neural networks, enabling the derivation of optimal control solutions without relying on an internal dynamic model of the system. Finally, convergence and performance are validated through simulation experiments, confirming its efficacy in managing constraints and demonstrating its application perspectives in real-world scenarios. © 2024 ieee.

关键词： Robot programming

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：