检索结果-内蒙古大学图书馆

Deep Reinforcement learning-Based Active Network Management and Emergency Load-Shedding control for Power systems

ieee TRANSACTIONS ON SMART GRID 2024年第2期15卷 1423-1437页

作者： Zhang, Haotian Sun, Xinfeng Lee, Myoung Hoon Moon, Jun Hanyang Univ Dept Elect Engn Seoul 04763 South Korea Incheon Natl Univ Dept Elect Engn Incheon 22012 South Korea

This paper presents two novel deep reinforcement learning (DRL) approaches aimed at solving complex power system control problems in a data-driven sense to maintain the stability of power systems. Specifically, we propose, respectively, SACPER (Soft Actor-Critic (SAC) with Prioritized Experience Replay (PER)) and Constrained Variational Policy Optimization (CVPO) DRL algorithms to address the sequential decision-making problem of active network management (ANM) in distributed power systems and optimizing emergency load shedding (ELS) control problems. First, we propose SACPER for the ANM problem, which prioritizes the training of samples with large errors and poor policy performance. Evaluation of SACPER in terms of stability improvement and convergence speed shows that the ANM problem is optimized and energy loss and operational constraint violations are minimized. Next, we introduce CVPO for the ELS control problem, which is formulated as the Safe Reinforcement learning (SRL) framework to address safety constraint prioritization issues in power systems. We consider additional voltage variables in the network as strong constraints for SRL to achieve fast voltage recovery and minimize unnecessary energy loss, while ensuring good training performance and efficiency. To demonstrate the performances of SACPER, we apply it to ANM6-Easy environment. The CVPO algorithm is applied to ieee 39-Bus and ieee 300-Bus systems. The simulation results of SACPER and CVPO are validated through extensive comparisons with other state-of-the-art DRL approaches.

关键词： Power system stability Safety Voltage control Inference algorithms Training Power systems Task analysis Deep reinforcement learning active network management emergency control safe reinforcement learning load shedding

来源：评论

学校读者我要写书评

暂无评论

Improved D-Type Iterative learning control for Hyperbolic Time-Delay Distributed Parameter systems under Sensor/Actuator Networks 13

Improved D-Type Iterative Learning Control for Hyperbolic Ti...

引用

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

作者： Zhang, Jianxiang Gong, Weitai Institute of Intelligent Systems and Control Guangxi University of Science and Technology Liuzhou545000 China School of Automation Guangxi University of Science and Technology China

ISBN: (纸本)9798350361674

This paper investigates the problem of iterative learning control in sensor/actuator networks for hyperbolic distributed parameter systems with time delays. For systems with known delays, this study firstly proposes an improved D-type iterative learning algorithm and proves the convergence of the iterative learning control strategy for nonlinear systems with control delays based on the principle of contraction mapping. Furthermore, by examining a nonlinear hyperbolic distributed parameter system with state delays, this paper verifies the convergence of the proposed algorithm through detailed mathematical derivations. To empirically validate the effectiveness and feasibility of the proposed algorithm, the paper finally demonstrates the performance of the iterative learning control strategy based on the proposed convergence conditions through numerical simulations. The results of the numerical simulations strongly support the applicability of the designed iterative learning algorithm in controlling hyperbolic distributed parameter systems with time delays. © 2024 ieee.

关键词： Delay control systems

来源：评论

学校读者我要写书评

暂无评论

Anti-sway control for Bulk Terminal Gantry Cranes Based on MFAC 12

Anti-sway Control for Bulk Terminal Gantry Cranes Based on M...

引用

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

作者： Liu, Wangwang Yao, Wenlong Chi, Ronghu Mu, Chenglin Qingdao Univ Sci & Technol Coll Automat & Elect Engn Qingdao 266100 Peoples R China

ISBN: (纸本)9798350321050

To address the problem of lifting weight sway generated by underactuated gantry cranes during operation, considering the load diversity of the portal machine and other disturbance effects, this paper proposes a control method that does not rely on an exact model. Firstly, a simple kinematic model of the gantry cranes is established and dynamically analyzed, then a compact form dynamic linearization is performed to obtain the data model, a pseudo-partial derivative estimation law is computed online, a model-free adaptive control based gantry cranes anti-sway controller is designed, and finally a simulation analysis is performed. The simulation results show that the load swing angle amplitude is effectively suppressed and quickly dissipated, while it has strong robustness to external unknown disturbances. Compared with the PID control simulation analysis, this control algorithm has more effective anti-sway control effect and can reach the stable state faster.

关键词： Gantry cranes Model-free adaptive control Underactuated system Anti-sway Disturbance

来源：评论

学校读者我要写书评

暂无评论

Consensus Tracking data-driven control of Multi-Agent systems based on Matrix S-Lemma under Noisy data 13

Consensus Tracking Data-Driven Control of Multi-Agent System...

引用

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

作者： Tan, Shuli Zhang, Xiufeng Yang, Chunxi Kunming University of Science and Technology Faculty of Mechanical and Electrical Engineering Kunming China Yunnan Key Laboratory of Intelligent Control and Application Yunnan Kunming650504 China

ISBN: (纸本)9798350361674

In this paper, the problem of consensus tracking for multi-agent systems in the presence of noise inter-ference is investigated. Unlike the traditional model-based approach, this paper assumes that the dynamics of all agents are unknown and only a portion of the input-state data is available. The offline data contaminated with noise interference is utilized. By introducing the matrix S-lemma, a necessary and sufficient conditions for directly designing consensus tracking controllers from bounded noisy input-state data is given. This method can be applied to large datasets and effectively addresses computational challenges associated with extensive data. Simulation result illustrates the effectiveness of the theoretical analysis. © 2024 ieee.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Fault-Tolerant Intermediate Estimator-Based Output Feedback control for a Class of Interconnected systems with Nonlinear Coupling Interconnections 12

Fault-Tolerant Intermediate Estimator-Based Output Feedback ...

引用

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

作者： Ma, Zhijuan Yu, Tingting Wang, Xin Heilongjiang Univ Harbin 150080 Peoples R China

ISBN: (纸本)9798350321050

This article proposes an output feedback fault-tolerant control (FTC) method to compensate for connection interruption faults and actuator faults present in interconnected systems. An intermediate estimator based fault reconstruction method and a decentralized FTC scheme are designed, using Kirchhoff matrix tree lemma to eliminate coupling effects between subsystems in interconnected systems. In addition, by combining the intermediate estimation algorithm and Lyapunov function method, it is proven that the global error system is uniformly ultimately bounded (UUB). This article also discusses the occurrence of connection failures and proves that our proposed method is still effective as long as at least one cycle can include all nodes. In comparison to previous results, the proposed decentralized FTC approach deals with interconnected dynamical systems that have unknown nonlinear interconnections and unreliable connections. Finally and most importantly, the rationality of the proposed FTC method has been verified using a networked chemical reactor recovery servo system.

关键词： Interconnected systems Fault-tolerant control Unreliable Interconnections Intermediate Observer

来源：评论

学校读者我要写书评

暂无评论

Robust data-driven Attitude control for Satellite Using Koopman Operator Theory 13

Robust Data-Driven Attitude Control for Satellite Using Koop...

引用

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

作者： Chen, Aijun Bu, Shichao Cui, Lei Zhang, Wenhan Li, Jitao Wang, Zhenhua Shanghai Institute of Satellite Engineering Shanghai201109 China Aerospace System Engineering Shanghai Shanghai201109 China Harbin Engineering University Harbin150001 China Harbin Institute of Technology Harbin150001 China

ISBN: (纸本)9798350361674

This paper studies the synthesis of robust control for a satellite attitude control system without pre-knowledge of model dynamics. First, by exploring the time-series data of satellite angular velocity, a lifted discrete-time linear system is constructed using Koopman operator theory and extended dynamic mode decomposition. This system provides an explanation for a finite measurement history. Second, an H∞ controller is designed to attenuate the effect of external disturbances and approximation errors during the stabilization process. The proposed methodology is able to guarantee the robustness performance. Finally, numerical simulations are performed to validate the effectiveness of the proposed method. © 2024 ieee.

关键词： Robust control

来源：评论

学校读者我要写书评

暂无评论

Model Predictive control of Permanent Magnet Synchronous Motor Based on Recursive Least Square Parameter Identification 12

Model Predictive Control of Permanent Magnet Synchronous Mot...

引用

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

作者： Yang, Dandan Yang, Bin Pang, Zhonghua Zheng, Changbing North China Univ Technol Key Lab Fieldbus Technol & Automat Beijing Beijing 100144 Peoples R China Beijing KingTrol Data Technol Co Ltd Beijing 100160 Peoples R China Henan Univ Urban Construct Sch Elect & Control Engn Pingdingshan 467000 Peoples R China

ISBN: (纸本)9798350321050

Model predictive control (MPC) has simple control structure and can achieve dynamic optimization control under constraint conditions. Due to the predictive control based on the system model, MPC has a high requirement for the accuracy of model parameters. This paper proposes a recursive least squares method based on the mathematical model of the motor for online parameter identification of permanent magnet synchronous motor (PMSM), which addresses the issue of sudden parameter changes that affect control effectiveness during operation. Through online identification, it is possible to effectively track changes in motor parameters and obtain real-time and accurate motor models. In addition, the updated motor model can serve as a predictive model for MPC. Thus, MPC can achieve more dynamic accurate prediction. Finally, the simulation is carried out to verify the effectiveness of the method that is proposed in this paper.

关键词： Permanent magnet synchronous motor model predictive control parameter identification recursive least square

来源：评论

学校读者我要写书评

暂无评论

Intelligent Structure control System Based on FPGA 12

Intelligent Structure Control System Based on FPGA

引用

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

作者： Qiu Ruikang Li Shengquan Cui Ronghua Zhang Lujin Li Juan Yangzhou Univ Coll Elect Energy & Power Engn Yangzhou 225127 Peoples R China

ISBN: (纸本)9798350321050

A linear active disturbance rejection control (LADRC) strategy is proposed to suppress the structural vibration caused by external excitations and internal uncertainties in intelligent structures under complex working conditions via an Anlu EG4S20B256 chip. First, the electromechanical coupling model of the whole vibration control system is obtained based on the dynamic equations of the all-clamped plate structure and the electromagnetic equations of the inertial actuator. Second, based on the system model, a third-order extended state observer (ESO) is designed to estimate the internal modelling errors and external excitation perturbations of the system in real time. In addition, the influence of internal and external disturbances on the control effect in the experiment is offset by a feedforward compensation. Finally, a vibration control platform based on the Anlu FPGA chip is built to verify the control effect of the proposed vibration active control strategy through physical real-time simulation.

关键词： All-clamped plate Active vibration control Linear active disturbance rejection control Field-programmable gate arrays

来源：评论

学校读者我要写书评

暂无评论

The Power of Input: Benchmarking Zero-Shot Sim-to-Real Transfer of Reinforcement learning control Policies for Quadrotor control

The Power of Input: Benchmarking Zero-Shot Sim-to-Real Trans...

引用

2024 International conference on Intelligent Robots and systems

作者： Dionigi, Alberto Costante, Gabriele Loianno, Giuseppe NYU Tandon Sch Engn Brooklyn NY 11201 USA Univ Perugia Dept Engn I-06125 Perugia Italy

ISBN: (纸本)9798350377712;9798350377705

In the last decade, data-driven approaches have become popular choices for quadrotor control, thanks to their ability to facilitate the adaptation to unknown or uncertain flight conditions. Among the different data-driven paradigms, Deep Reinforcement learning (DRL) is currently one of the most explored. However, the design of DRL agents for Micro Aerial Vehicles (MAVs) remains an open challenge. While some works have studied the output configuration of these agents (i.e., what kind of control to compute), there is no general consensus on the type of input data these approaches should employ. Multiple works simply provide the DRL agent with full state information, without questioning if this might be redundant and unnecessarily complicate the learning process, or pose superfluous constraints on the availability of such information in real platforms. In this work, we provide an in-depth benchmark analysis of different configurations of the observation space. We optimize multiple DRL agents in simulated environments with different input choices and study their robustness and their sim-to-real transfer capabilities with zero-shot adaptation. We believe that the outcomes and discussions presented in this work supported by extensive experimental results could be an important milestone in guiding future research on the development of DRL agents for aerial robot tasks.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Disturbance Rejection Based Adaptive Fast Terminal Sliding Mode control for Ship Course control 12

Disturbance Rejection Based Adaptive Fast Terminal Sliding M...

引用

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

作者： Qin Huayang Zheng Chen Tan Panlong Sun Mingwei Chen Zengqiang Sun Qinglin Nankai Univ Coll Artificial Intelligence Tianjin 300350 Peoples R China Beijing Inst Astronaut Syst Engn Beijing 100076 Peoples R China

ISBN: (纸本)9798350321050

As the main means of transportation in global trade, ships have received great attention in industry and academia. Aiming at the automatic control of the ship in the ocean, an adaptive fast terminal sliding mode control (FTSMC) method is proposed and regulates the ship course effectively. In particular, considering the nonlinear dynamics of the ship and unexpected external disturbances, the linear extended state observer (LESO) is employed to estimate and compensate for the total disturbance in ship course control. Specifically, an adaptive control gain is elaborately designed to eliminate the tracking error caused by the estimation error of the total disturbance, which ensures the asymptotic convergence of the closed-loop system. Based on the designed sliding manifold, the proposed method can achieve the control objective without singularity. Furthermore, the closed-loop stability are proved by rigorous Lyapunov-based analysis. In addition, the simulations with comparative results are provided to validate the effectiveness and robustness of the proposed method.

关键词： Adaptive control Fast terminal sliding mode control (FTSMC) Linear extended state observer (LESO) Ship course control

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：