检索结果-内蒙古大学图书馆

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

作者： Zhao, Yuxin Zhu, Ke Song, Xueming Zhang, Jianming Zhejiang Univ Coll Control Sci & Technol Hangzhou 310000 Peoples R China Zhejiang Univ Robot Inst Yuyao 314500 Peoples R China

ISBN: (纸本)9798350321050

In order to improve the transportation efficiency of hospital AGV logistics system, we have studied the task scheduling of AGVs. We mathematically describe the multi-vehicle scheduling problem in hospital AGV logistics system, propose a task scheduling method based on multi-agent reinforcement learning, and demonstrate that this scheduling strategy outperforms the traditional heuristic scheduling strategy in terms of both solution results and computational efficiency.

关键词： AGVs Task scheduling Reinforcement learning Hospital logistic transportation

来源：评论

学校读者我要写书评

暂无评论

controlling Aluminum Strip Thickness by Clustered Reinforcement learning With Real-World dataset

引用

ieee TRANSACTIONS ON INDUSTRIAL INFORMATICS 2024年第8期20卷 9928-9938页

作者： Xiao, Ziqi He, Zhili Liang, Huanghuang Hu, Chuang Cheng, Dazhao Wuhan Univ Sch Comp Sci Wuhan 430072 Peoples R China Chinalco Adv Mfg Co Ltd Chongqing 400039 Peoples R China

Consistent thickness in aluminum strips stands as a pivotal indicator of aluminum sheet product quality. Conventional automatic gauge control systems are complex, multivariable, and strongly coupled. However, the rolling process faces uncertainties, preventing the establishment of precise mathematical models. To tackle this, we propose an aluminum strip cold rolling thickness control method grounded in offline reinforcement learning. To facilitate the learning of better control policies, we construct a dataset of aluminum strip cold rolling process control data derived from real-world historical records and expertise for offline policy training, which is named dataset for aluminum strip cold rolling and comprises 8 373 540 Markov decision process tuples. We employ a clustered approach to handle time-varying production conditions. A constrained filtering scheme is introduced to eliminate problematic data after a data-driven ensemble rolling model is established. Evaluation and case study demonstrate that our method effectively reduces aluminum strip thickness deviations without requiring prior knowledge, thus improving control performance.

关键词： Strips Aluminum Production Process control Costs Optimization Thickness control Aluminum strip cold rolling clustered approach data-driven deep reinforcement learning (DRL) real-world dataset thickness control

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

Optimization Scheme of Fuzzy control System based on Reinforcement learning Compensation 13

Optimization Scheme of Fuzzy Control System based on Reinfor...

引用

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

作者： He, Saichao Liu, Jia'nan Hong, Wenjing Shi, Jia Institute of Artificial Intelligence Xiamen University Fujian Xiamen361005 China College of Chemistry and Chemical Engineering Xiamen University Fujian Xiamen361005 China

ISBN: (纸本)9798350361674

Fuzzy control technology has been extensively studied and widely used in reality due to its ability to transform human control experience, described in vague terms, into automatic control law. However, when dealing with complex systems that require valuable control experience, fuzzy control technology may not necessarily guarantee optimal control performance. Therefore, developing an advanced optimization scheme of fuzzy control systems is essential. In this paper, a model-free optimization scheme is developed for the fuzzy control system based on reinforcement learning algorithm, which is named Reinforcement learning Assisted Fuzzy control (RLAFC). The main feature of this scheme is that it can automatically obtain an effective compensation policy for the fuzzy controller by employing a data-driven reinforcement learning algorithm. Compared to the standalone reinforcement learning algorithm, the proposed method can achieve a synergistic combination of experiential and data-driven learning approaches, which brings about better control performance as well as improved safety assurance during the learning process. Finally, the simulation results of a car-following control task demonstrate the effectiveness of the proposed method. We believe that RLAFC is an effective solution for the control problems of complex systems by the combination of human control knowledge and artificial intelligence technology. © 2024 ieee.

关键词： Fuzzy control

来源：评论

学校读者我要写书评

暂无评论

Robust Iterative learning control for Robot Manipulators with Input Deadzone 12

Robust Iterative Learning Control for Robot Manipulators wit...

引用

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

作者： Ji, Shuangjie Yan, Qiuzhen Chen, Qiang Lin, Mingjun Zhejiang Univ Water Resources & Elect Power Coll Informat Engn Hangzhou 310018 Zhejiang Peoples R China Zhejiang Univ Technol Coll Informat Engn Hangzhou 310023 Zhejiang Peoples R China

ISBN: (纸本)9798350321050

This work studies trajectory tracking problem for robot manipulators with actuator deadzone under arbitrary initial states. A robust iterative learning control scheme is developed according to Lyapunov theory. First, the rectification reference trajectory is constructed for handling initial position of robotic ILC systems. Then, based on system parameterization technique, a robust adaptive iterative learning control law is derived to dealing with the deadzone nonlinearity and uncertainties. The convergence performance of the system and the boundedness of the closed-loop signal are proved by theoretical analysis. At the end, a numerical simulation is carried out to demonstrate the effectiveness of the proposed robust learning control scheme.

关键词： Adaptive iterative learning control nonparametric systems input deadzone inverse model

来源：评论

学校读者我要写书评

暂无评论

data-driven Linear Quadratic Regulator using LightGBM for Quadcopter control

Data-Driven Linear Quadratic Regulator using LightGBM for Qu...

引用

ieee International conference on Automatic control and Intelligent systems (I2CACIS)

作者： Al Ghifari, Ahmad Musthafa Mahayana, Dimitri Harsoyo, Agung Inst Teknol Bandung Sch Elect Engn & Informat Bandung Indonesia

ISBN: (纸本)9798350372113;9798350372106

A quadcopter is an unmanned aerial vehicle that requires a control system to stabilize it during flight. In this paper, a data-driven control algorithm, Light Gradient Boost Machine (LightGBM) is proposed to improve the quadcopter control system. The input and output data we use for the LightGBM algorithm are obtained from a closed-loop quadcopter system with a linear quadratic regulator (LQR) controller. With the expectation that the LightGBM control algorithm can replace the LQR controller on the quadcopter. Simulations have been carried out in this study, and the results of the simulations show that the proposed algorithm has similar response results as LQR control, so that the proposed algorithm can be used as a control system in the quadcopter system.

关键词： Quadcopter control system machine learning Linear Quadratic Regulator (LQR) LightGBM

来源：评论

学校读者我要写书评

暂无评论

Collaborative learning Tracking for Networked systems with Fading Communication 12

Collaborative Learning Tracking for Networked Systems with F...

引用

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

作者： Zhang, Zeyi Jiang, Hao Zeng, Kun Shen, Dong Renmin Univ China Sch Math Beijing 100872 Peoples R China Beijing Univ Chem Technol Coll Informat Sci & Technol Beijing 100029 Peoples R China

ISBN: (纸本)9798350321050

Using a networked structure, many subsystems can communicate and collaborate to accomplish a global objective. With collaborative learning control, the system enables high-precision tracking of repetitive tasks. However, the transmitted signal generally suffers damage in the network. The fading problem is one of the concerns being addressed. To this end, this article investigates collaborative learning control systems in fading channels. We propose a control algorithm equipped with decreasing learning gain. Then, we prove that the reference trajectory can be accurately realized in mean square sense. Finally, we provide numerical simulations to verify our method.

关键词： Collaborative learning control fading channels multiplicative randomness

来源：评论

学校读者我要写书评

暂无评论

Prescribed-Time Robust Repetitive learning control for PMSM Servo systems

引用

ieee TRANSACTIONS ON INDUSTRIAL ELECTRONICS 2024年第11期71卷 14753-14763页

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

This article proposes a prescribed-time robust repetitive learning control scheme for uncertain permanent magnet synchronous motor (PMSM) servo systems. An error-tracking approach is developed through constructing a desired error trajectory, such that the exact settling time of the error convergence can be achieved without using any switching mechanism in controller design. In order to achieve high-precision steady-state tracking accuracy, a fully saturated repetitive learning law is developed to reduce the residual periodic steady-state error and drive the tracking error to converge into a sufficiently small region around the origin, such that the rapid transient response and high-precision steady-state tracking accuracy of the PMSM servo system can be both guaranteed simultaneously. Comparative experiments are provided to verify the effectiveness of the proposed method.

关键词： Trajectory Servomotors Convergence control systems Switches Steady-state Nonlinear systems Error-tracking approach prescribed time convergence servo systems repetitive learning control

来源：评论

学校读者我要写书评

暂无评论

Dynamic observer-based controllers for fractional-order linear systems with positive real uncertainty 12

Dynamic observer-based controllers for fractional-order line...

引用

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

作者： Li, He Liu, Shuo Shenyang Aerosp Univ Sch Automat Shenyang 110136 Peoples R China

ISBN: (纸本)9798350321050

This paper investigates the topic about robust dynamic observer-based controller design for fractional-order systems (0 < alpha < 1) with positive real uncertainty. By constructing the linear variation of variables, even when the system and the input matrix are uncertain simultaneously, the conditions of designed the observer and controller gain can be obtained by solving a set of linear matrix inequalities (LMIs). Compared with Luenberger observer, the dynamic observer-based controller is another method without using equality constraints under LMI conditions.

关键词： Positive real uncertainty Dynamic observer Fractional-order systems(FOS)

来源：评论

学校读者我要写书评

暂无评论

Adaptive Tracking and Synchronization control of Dual-motor Driving Servo System 12

Adaptive Tracking and Synchronization Control of Dual-motor ...

引用

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

作者： Dang, Jiali Ding, Jiacheng Zhang, Nan Wang, Shtibo Qingdao Univ Coll Automat Qingdao 266071 Peoples R China

ISBN: (纸本)9798350321050

This paper proposes an adaptive tracking and synchronization control scheme for dual-motor driving servo system with nonlinear dead-zone. To achieve the tracking performance, the neural network is used to approximate the unknown dynamics, and the approximation is incorporated into the control design to compensate the unknown dynamics. Then, adaptive dynamic surface controller is designed to improve the tracking performance. Moreover, a robust controller is presented based on the mean deviation coupling strategy to guarantee the synchronous operation of dual motors. Simulation results illustrate the performance of the proposed control strategy.

关键词： Adaptive dynamics surface mean deviation coupling neural network robust 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：