检索结果-内蒙古大学图书馆

learning Provably Stable Local Volt/Var controllers for Efficient Network Operation

ieee TRANSACTIONS ON POWER systems 2024年第1期39卷 2066-2079页

作者： Yuan, Zhenyi Cavraro, Guido Singh, Manish K. Cortes, Jorge Univ Calif San Diego Dept Mech & Aerosp Engn La Jolla CA 92093 USA Power Syst Engn Ctr Natl Renewable Energy Lab Golden CO 80401 USA Univ Minnesota Dept Elect & Comp Engn Minneapolis MN 55455 USA

This paper develops a data-driven framework to synthesize local Volt/Var control strategies for distributed energy resources (DERs) in power distribution grids (DGs). Aiming to improve DG operational efficiency, as quantified by a generic optimal reactive power flow (ORPF) problem, we propose a two-stage approach. The first stage involves learning the manifold of optimal operating points determined by an ORPF instance. To synthesize local Volt/Var controllers, the learning task is partitioned into learning local surrogates (one per DER) of the optimal manifold with voltage input and reactive power output. Since these surrogates characterize efficient DG operating points, in the second stage, we develop local control schemes that steer the DG to these operating points. We identify the conditions on the surrogates and control parameters to ensure that the locally acting controllers collectively converge, in a global asymptotic sense, to a DG operating point agreeing with the local surrogates. We use neural networks to model the surrogates and enforce the identified conditions in the training phase. AC power flow simulations on the ieee 37-bus network empirically bolster the theoretical stability guarantees obtained under linearized power flow assumptions. The tests further highlight the optimality improvement compared to prevalent benchmark methods.

关键词： Distributed energy resources global stability local control Volt/Var control

来源：评论

学校读者我要写书评

暂无评论

SARSA (λ) Reinforcement learning Based Path Planning of Unmanned Aerial Vehicles 13

SARSA (λ) Reinforcement Learning Based Path Planning of Unm...

引用

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

作者： Dong, Huaizhi Zhao, Dong Huang, Darong Yan, Kun Ren, Wenjing School of Artificial Intelligence Anhui University Hefei230601 China School of Electronic Information Engineering Xi'an Thchnological University Xi'an710021 China School of Electrical Engineering and Automation Hefei University of Technology Hefei230009 China

ISBN: (纸本)9798350361674

This paper studies the path planning problem of space Unmanned aerial vehicle model based on SARSA (λ) Reinforcement learning method in complex environment. First, we utilize three-dimensional mathematical modeling to describe the positions of drone at each moment and motion trajectories, to facilitate subsequent analysis of state and action spaces. Then, by introducing the concept of eligibility traces into the traditional SARSA reinforcement learning algorithm, we optimize the path planning problem of drones in a three-dimensional environment. Finally, through simulation, it is demonstrated that this method not only accelerates the learning process but also smoothly updates states, thereby enhancing the exploration efficiency of drone path planning in space compared to traditional path planning algorithms. © 2024 ieee.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Distributed control of Multiple Electric Springs based on Droop and Consensus control in Microgrid 13

Distributed Control of Multiple Electric Springs based on Dr...

引用

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

作者： Wang, Hao Xu, Dezhi Yang, Weilin Huang, Wentao Pan, Tinglong School of Internet of Things Engineering Jiangnan University Wuxi214122 China School of Electrical Engineering Southeast University Nanjing210096 China

ISBN: (纸本)9798350361674

Aiming to address frequency fluctuation and output power imbalances in renewable energy grid connections, this paper proposes a strategy for distributed multilevel control of Electric Springs (ESs) to stabilize bus node voltage and equalize output power. Primary control utilizes the backstepping method to stabilize critical load voltages. Secondary control employs a collaborative approach of droop and consensus adaptive virtual impedance to facilitate ES control with or without communication. Under normal circumstances, consensus control enhances output power control accuracy. In the absence of communication, droop control independently obtains node voltage for backstepping reference voltage correction. Simulation verification demon-strates the proposed method's fast dynamic response, high control accuracy, and robustness. © 2024 ieee.

关键词： Microgrids

来源：评论

学校读者我要写书评

暂无评论

An updated look on the convergence and consistency of data-driven dynamical models 63

An updated look on the convergence and consistency of data-d...

引用

63rd ieee conference on Decision and control, CDC 2024

作者： Lovland, Kristian Grimstad, Bjarne Imsland, Lars Struen Norwegian University of Science and Technology Trondheim Norway Solution Seeker As Oslo Norway

ISBN: (纸本)9798350316339

Deep sequence models are receiving significant interest in current machine learning research. By representing probability distributions that are fit to data using maximum likelihood estimation, such models can model data on general observation spaces (both continuous and discrete-valued). Furthermore, they can be applied to a wide range of modelling problems, including modelling of dynamical systems which are subject to control. The problem of learning data-driven models of systems subject to control is well studied in the field of system identification. In particular, there exist theoretical convergence and consistency results which can be used to analyze model behaviour and guide model development. However, these results typically concern models which provide point predictions of continuous-valued variables. Motivated by this, we derive convergence and consistency results for a class of nonlinear probabilistic models defined on a general observation space. The results rely on stability and regularity assumptions, and can be used to derive consistency conditions and bias expressions for nonlinear probabilistic models of systems under control. We illustrate the results on examples from linear system identification and Markov chains on finite state spaces. © 2024 ieee.

关键词： Markov chains

来源：评论

学校读者我要写书评

暂无评论

An Enhanced GC-RANSAC Approach for Subway Indoor Ground Segmentation 13

An Enhanced GC-RANSAC Approach for Subway Indoor Ground Segm...

引用

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

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

ISBN: (纸本)9798350361674

Addressing the challenges of traditional LiDAR ground segmentation algorithms in processing complex subway scenes captured, an improved GC-RANSAC ground segmentation algorithm is proposed. This method initially uses the RANSAC algorithm to extract several planes. Then, it calculates the slope threshold for each plane to preserve non-ground areas. Finally, the min-cut algorithm is utilized to complete the ground segmentation. Based on the quadruped robots experimental platform, empirical data from subway scenarios are collected and tested. The processing results show the proposed algorithm demonstrates excellent performance compared with other selected methods. The False Negative Rates are 0.56%, 0.84%, and 1.67% for elevators, subway station corridors, and subway station halls respectively, which meets the effectiveness requirements for quadruped robots. © 2024 ieee.

关键词： Subway stations

来源：评论

学校读者我要写书评

暂无评论

Gaze-driven Adaptive learning System With ChatGPT-Generated Summaries

引用

ieee ACCESS 2024年 12卷 173714-173733页

作者： Santhosh, Jayasankar Dengel, Andreas Ishimaru, Shoya German Res Ctr Artificial Intelligence DFKI SDS Dept D-67663 Kaiserslautern Germany RPTU Kaiserslautern Landau Dept Comp Sci D-67663 Kaiserslautern Germany Osaka Metropolitan Univ Dept Comp Sci Naka Ku Sakai Osaka 5998531 Japan

Enhancing student engagement and comprehension is crucial for effective learning. However, tracking and improving these dynamic states in real-time remains a significant challenge. This study addresses this gap by integrating real-time engagement prediction from gaze data with an adaptive learning system that utilizes ChatGPT-generated summaries to enhance student engagement and learning outcomes. Our experiment with twenty two (N=22) university students demonstrates the effectiveness of gaze data in predicting real-time engagement levels and the impact of adaptive interventions on student engagement, objective and subjective comprehension, and cognitive load. To predict the self-reported engagement and comprehension levels, two deep neural network models, InceptionTime and Transformers were employed. The Transformers model achieved better outcomes, with an average accuracy of 68.15% in predicting engagement levels across a 5-fold StratifiedGroupKFold cross-validation. The results revealed that the experimental group, which received the AI-driven interventions, exhibited significantly better learning outcomes, higher engagement, and better objective comprehension results compared to the control group. Additionally, we observed strong correlations between gaze metrics, engagement levels, and learning outcomes, suggesting that real-time adaptive interventions can dynamically enhance the educational experience. This study advances the field of educational technology by demonstrating the benefits of integrating gaze tracking and AI in learning environments, laying the foundation for dynamic learning interfaces that adapt to individual engagement levels, potentially improving both comprehension and involvement.

关键词： Real-time systems Adaptive learning Adaptation models Gaze tracking Monitoring Electronic learning Correlation User interfaces Predictive models Transformers E-learning ChatGPT API eye-tracking real-time engagement personalized interventions comprehension enhancement

来源：评论

学校读者我要写书评

暂无评论

Deep Neural Networks With Koopman Operators for Modeling and control of Autonomous Vehicles

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES

引用

ieee TRANSACTIONS ON INTELLIGENT VEHICLES 2023年第1期8卷 135-146页

作者： Xiao, Yongqian Zhang, Xinglong Xu, Xin Liu, Xueqing Liu, Jiahang Natl Univ Def Technol Coll Intelligence Sci & Technol Changsha 410073 Peoples R China

Autonomous driving technologies have received notable attention in the past decades. In autonomous driving systems, identifying a precise dynamical model for motion control is nontrivial due to the strong nonlinearity and uncertainty in vehicle dynamics. Recent efforts have resorted to machine learning techniques for building vehicle dynamical models, but the generalization ability and interpretability of existing methods still need to be improved. In this paper, we propose a pure data-driven vehicle modeling approach based on deep neural networks with an interpretable Koopman operator. The main advantage of using the Koopman operator is to represent the nonlinear dynamics in a linear lifted feature space. In the proposed approach, a deep learning-based extended dynamic mode decomposition algorithm is presented to learn a finite-dimensional approximation of the Koopman operator. A multi-step prediction loss function is used in the training process, enabling a long-term prediction capability. Furthermore, a data-driven model predictive controller with the learned Koopman model is designed for velocity profile tracking control of autonomous vehicles. Simulation results in a high-fidelity CarSim environment show that our approach outperforms previously developed traditional and advanced modeling methods. Velocity profile tracking tests of the autonomous vehicle are also performed in the CarSim environment. The results show that our approach has better tracking accuracy and higher computational efficiency than the model predictive control algorithms using a nonlinear model and a linear time-varying model.

关键词： Vehicle dynamics Predictive models Computational modeling Neural networks Autonomous vehicles Nonlinear dynamical systems Deep learning Koopman operator deep learning extended dynamic mode decomposition (EDMD) data-driven modeling model predictive control (MPC)

来源：评论

学校读者我要写书评

暂无评论

Enhanced Real-Time ATM-Based MPC for Electric Vehicles With CyberPhysical Security Aspect

引用

ieee TRANSACTIONS ON TRANSPORTATION ELECTRIFICATION 2025年第1期11卷 4698-4716页

作者： Arsalan, Ali Papari, Behnaz Timilsina, Laxman Muriithi, Grace Moghassemi, Ali Rahman, S. M. Imrat Buraimoh, Elutunji Ozkan, Gokhan Edrington, Christopher S. Clemson Univ Secure Energy & Automat Lab SEAL Clemson SC 29634 USA Clemson Univ Real Time COntrol & Optimizat Lab RT COOL Clemson SC 29634 USA

Inverter-based electric drive systems (EDSs) in electric vehicles (EVs) are susceptible to various common cyber and physical anomalies (CPAs), such as cyberattacks (CAs) and open-circuit faults (OCFs) in power switches. Most existing data-driven diagnostic schemes for motor drives solely rely on residual and three-phase output current signals and are prone to misclassification due to overlapping data features associated with these anomalies. Moreover, these methods concentrate on detecting either CAs or OCFs independently, lacking a unified approach that can be universally applied to both types of anomalies. Therefore, in this work, a physics-informed machine learning (PIML) approach is proposed, which can effectively distinguish between CAs and OCFs in EDS. In this regard, the unique features associated with stator current, resulting from various CPAs, are used to estimate the stator voltage characteristics through a synchronous motor mathematical model. The proposed voltage-based features characterizing better correlation via distinctive EDS transients in response to these anomalies are further used as the system's prior information by a machine learning (ML) classifier. Moreover, active thermal management (ATM)-based model predictive control (MPC) is utilized in the control layer due to its benefits in device-level thermal cycling and power quality. In addition, various variations in electrical, mechanical, and thermal characteristics due to CPAs in EDS have also been analyzed. The presented approach is evaluated for the US06 standard drive cycle in real time via controller-hardware-in-the-loop (CHIL) experiment for various case study scenarios, resulting in a classification accuracy of 98.92%.

关键词： control systems Stators Motor drives Transportation Electrification Circuit faults Torque Rotors Mathematical models Active thermal management (ATM)-based model predictive control (MPC) cyberattacks (CAs) electric drive system (EDS) physical fault detection physics-informed machine learning (PIML) physics-informed machine learning (PIML)

来源：评论

学校读者我要写书评

暂无评论

Application of Additive-State-Decomposition-Based Model-Compensation controller in Compound Vertical Takeoff and Landing Unmanned Aircraft 13

Application of Additive-State-Decomposition-Based Model-Comp...

引用

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

作者： Zhang, Xinran Qi, Guoyuan School of Control Science and Engineering Tiangong University Tianjin300387 China

ISBN: (纸本)9798350361674

The compound vertical take-off and landing (VTOL) unmanned aerial vehicle (UAV) is a complex nonlinear system characterized by strong coupling, high complexity, and sensitivity to external disturbances and model uncertainties. For a VTOL UAV, there are two main control modes: multi-rotor mode and fixed-wing mode. The completeness and accuracy of the control model should be considered;therefore, an observer is used to observe the model's uncertainty and external disturbances. Based on the idea of additive state decomposition (ASD), the high-order differentiator (HOD) and compensation function observer (CFO) are combined to design an ASD-based model compensation controller (ASD-MCC), which achieves tracking control for the primary system and stability control for the secondary system. The stability and convergence of the closed-loop system are proven. Using the complete model of the compound VTOL UAV, numerical simulations are conducted in MATLAB's Simulink platform to compare the proposed control algorithm with traditional PID control and model compensation control (MCC), verifying the superiority and effectiveness of the proposed algorithm. © 2024 ieee.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Design and Application of Integrated Condition Monitoring and Diagnostic Architecture for Airborne systems 13

Design and Application of Integrated Condition Monitoring an...

引用

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

作者： Li, Chen Huang, Jinjin Pei, Jie Air Force Engineering University Aviation Maintenance Nco School Xinyang464000 China

ISBN: (纸本)9798350361674

According to the requirements of high security, high reliability and easy maintenance of the airborne system, the comprehensive condition monitoring and diagnosis architecture based on the 'health management domain' is proposed to solve the problem of comprehensive integration of the state monitoring and diagnosis of the airborne system under multi-platform and multi-scenario conditions. This architecture proposes the comprehensive state monitoring method of general modules, functional threads and bus network according to the high integration design characteristics of the airborne system, so as to improve the online health perception capability of the onboard system without increasing hardware. It designs the health assessment and diagnosis model, proposes the multi-model integration algorithm framework of data fusion, and solves the application problem of multi-platform diagnostic model integration in the airborne system. Additionally, it also develops the graphical health management display and control interface and object-oriented health management database, and improves the interface friendliness and functional scalability of the health management system. This provides a reference for the development of the condition monitoring and diagnosis subsystem of the airborne system. © 2024 ieee.

关键词： Electronic health record

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：