检索结果-内蒙古大学图书馆

IEEE Conference on Decision and Control

作者： Jinjiang Li Tao Liu Tengfei Liu Department of Electrical and Electronic Engineering The University of Hong Kong (HKU) Hong Kong SAR HKU Shenzhen Institute of Research and Innovation Shenzhen China State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang China

This paper studies the data-driven finite-time control (FTC) problem of unknown discrete-time linear time-invariant (LTI) systems with unknown and bounded noise. The proposed FTC aims to guarantee that the state of such a system does not exceed a given bound over a finite time interval under bounded initial conditions. Data-dependent representations are built for the unknown system without and with noise from pre-collected input/state data, based on which a finite-time controller is designed. Sufficient conditions of finite-time stability/boundness of the closed-loop system without/with noise are derived. Compared with model-based FTC methods that strongly depend on some accurate system models, the proposed method is model-free and only relies on pre-collected data. Numerical simulations are performed to illustrate the effectiveness of the proposed scheme.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Novel Cooperative Particle Swarm Optimization with Interactive Learning Strategy 1

引用

8th International Conference on Life System Modeling and Simulation, LSMS 2024 and 8th International Conference on Intelligent Computing for Sustainable Energy and Environment, ICSEE 2024

作者： Wang, Qiliang Liu, Yiheng Xu, Hao Zhang, Pinggai Wu, Qinlin Wei, Lisheng Anhui Key Laboratory of Electric Drive and Control School of Electrical Engineering Anhui Polytechnic University Anhui Wuhu241000 China Industrial Process Control Optimization and Automation Engineering Research Center School of Electronic Engineering Chaohu University Anhui Chaohu238024 China School of Computer Science and Artificial Intelligence Chaohu University Anhui Chaohu238024 China

ISBN: (数字)9789819603138

ISBN: (纸本)9789819603121

Particle Swarm Optimization (PSO) is an optimization method grounded in swarm intelligence, designed to mimic the social behaviors of bird flocks during hunting. By sharing information about their positions, the entire swarm can explore and search diverse areas within a given space. This method features rapid convergence, minimal parameters, and straightforward implementation, making it a potent and efficient metaheuristic technique. Nevertheless, conventional PSO algorithms, despite their simplicity and efficiency, often become trapped in local optima when tackling complex multimodal problems, which limits their global search capability. To mitigate these limitations, a new Cooperative Particle Swarm Optimization algorithm with Interactive Learning (CPSOIL) is introduced. This approach incorporates an interactive learning strategy, allowing particles to learn from their neighbors by perceiving the surrounding particles during updates. Moreover, a mechanism has been added to modify the particle velocity update when the algorithm encounters local optima, thereby preserving population diversity, enhancing the likelihood of escaping local optima, and improving algorithm accuracy. Comparisons with other leading algorithms on the CEC2005 benchmark functions indicate that, in most cases, the enhanced algorithm outperforms its counterparts. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Adaptive Optimal Output Regulation of Discrete-Time Linear Systems: A Reinforcement Learning Approach

Adaptive Optimal Output Regulation of Discrete-Time Linear S...

引用

IEEE Conference on Decision and Control

作者： Sayan Chakraborty Weinan Gao Kyriakos G. Vamvoudakis Zhong-Ping Jiang CAN Lab New York University Brooklyn NY USA State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang China The Daniel Guggenheim School of Aerospace Engineering Georgia Institute of Technology GA USA

In this paper, we solve the optimal output regulation problem for discrete-time systems without precise knowledge of the system model. Drawing inspiration from reinforcement learning and adaptive dynamic programming, a data-driven solution is developed that enables asymptotic tracking and disturbance rejection. Notably, it is discovered that the proposed approach for discrete-time output regulation differs from the continuous-time approach in terms of the persistent excitation condition required for policy iteration to be unique and convergent. To address this issue, a new persistent excitation condition is introduced to ensure both uniqueness and convergence of the data-driven policy iteration. The efficacy of the proposed methodology is validated by an inverted pendulum on a cart example.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamic Prediction of Abnormal Condition for Multiple Fused Magnesium Melting processes Based on Video Continual Learning

TechRxiv

引用

TechRxiv 2022年

作者： Zhang, Zhe The College of Information Science and Engineering Northeastern University Shenyang110819 China The State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang110819 China

process industry is the pillar industry of national economy, particularly, the process of producing magnesia by fused magnesia furnace system is a typical category of process industry. Due to the complex smelting mechanism and changing production factors, abnormal working conditions often occur in fused magnesia furnace. The semi-molten condition is the most typical and harmful abnormal condition. In this paper, an adaptive pretraining-inference-dynamic training-validation semantic segmentation method based on industrial video is proposed for dynamic prediction of semi-molten condition of multiple fused magnesium furnaces. The experimental results show that compared with the prediction model without adaptive learning, the prediction performance of the adaptive learning model in this paper for multiple fused magnesium melting processes is significantly improved. © 2022, CC BY-NC-SA.

关键词： Magnesia

来源：评论

学校读者我要写书评

暂无评论

Operando monitoring of gelation kinetics of polyacrylamide hydrogel using in-fiber dual-MZI

引用

Fundamental Research 2024年

作者： Zhao, Yong Li, Like Han, Bo Zhang, Hongrui Zhang, Ya-nan College of Information Science and Engineering Northeastern University Shenyang 110819 China Hebei Key Laboratory of Micro-Nano Precision Optical Sensing and Measurement Technology Northeastern University at Qinhuangdao Qinhuangdao 066004 China State Key Laboratory of Synthetical Automation for Process Industries Shenyang 110819 China

Operando monitoring of gelation kinetics and exploring the gelation law are crucial for optimizing the performance of hydrogels. In this paper, we propose a novel superposition sensing structure based on an integrated dual-Mach–Zehnder interferometer (MZI), which can simultaneously sense temperature and refractive index (RI), with an RI sensitivity of −10,173 nm/RIU and a temperature sensitivity of 8.14 nm/ °C. For the first time, its application for the operando monitoring of gelation kinetics of polyacrylamide hydrogel (PAH) is demonstrated. By establishing the kinetic curves of temperature and RI information in the gelation process, it is confirmed that the gelation process can be divided into three stages: initial lag, rapid gelation, and final saturation. In addition, two gelation laws are verified through experiments: (1) As the concentration of monomers and crosslinkers increases, RI changes, and the amount of heat released gradually increases. (2) As the concentration of catalysts increases, the gelation time decreases significantly. This superposition sensing technique based on dual-MZI can be further applied to monitor other complex dynamic biochemical processes, thereby providing insights into the laws and mechanisms of reaction processes. © 2024

关键词： Dual-Mach–Zehnder interferometer Dynamic process monitoring Gelation Optical fiber sensor Polyacrylamide hydrogel

来源：评论

学校读者我要写书评

暂无评论

Corrections to “Intelligent Traffic Data Transmission and Sharing Based on Optimal Gradient Adaptive Optimization Algorithm”

引用

IEEE Transactions on Intelligent Transportation Systems 2024年第3期25卷 3202-3204页

作者： Xing Li Haotian Zhang Yajing Shen Lina Hao Wanfeng Shang School of Electrical Engineering and Intelligentization Dongguan University of Technology Dongguan China State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang China College of Computer Science and Technology Jilin University Changchun China Department of Biomedical Engineering City University of Hong Kong Hong Kong China School of Mechanical and Engineering Northeastern University Shenyang China Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China

In [1] , inaccuracies in several critical equations along with their accompanying descriptions appear in the article. Furthermore, some references are missing, and certain analyses of experiments are flawed.

关键词： Adaptive systems Data communication Optimization Intelligent transportation systems

来源：评论

学校读者我要写书评

暂无评论

Resilient Distributed Localization for Mobile Sensor Networks Under Malicious Attacks

SSRN

引用

SSRN 2024年

作者： Lv, Yuan-Wei Yang, Guang-Hong Dimirovski, Georgi Marko College of Information Science and Engineering Northeastern University Liaoning Shenyang110819 China State Key Laboratory of Synthetical Automation of Process Industries Northeastern University Liaoning Shenyang110819 China Doctoral School FEIT Ss. Cyril and Methodius University at Skopje Skopje1000 Macedonia

This paper studies the distributed localization problem for mobile sensor networks in the presence of malicious attacks, which manipulate relative measurements to mislead the localization process. Based on the cubature Kalman filter, a distributed attack-resilient cooperative localization algorithm is proposed, which enables each sensor to estimate its state by utilizing only local relative measurements and neighboring messages. Specifically, an innovation-based saturation mechanism, which assigns small coefficient for unreasonably large innovation, is designed to confine the impact of the attacks. In this way, all measurements that associates with a sensor are handled separately to obtain local estimates, which are then fused together based on the covariance intersection method. Compared with the existing extended Kalman filter based positioning approaches, the employed cubature integral rules avoid evaluating the Jacobian matrix and can improve the performance of nonlinear state estimation. Moreover, the consistency of all sensors' estimates is maintained, and the boundedness of the error covariance matrices is guaranteed. Finally, two examples are provided to verify the feasibility of the proposed algorithm. © 2024, The Authors. All rights reserved.

关键词： Sensor networks

来源：评论

学校读者我要写书评

暂无评论

Passivity-Based Online Reinforcement Learning for Real Time Model-Free Overhead Crane System Control

Passivity-Based Online Reinforcement Learning for Real Time ...

引用

Chinese Control and Decision Conference, CCDC

作者： Haoran Zhang Chunhui Zhao Jinliang Ding State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Hangzhou China State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang China

ISBN: (纸本)9781665478977

In this paper, a novel model-free online Reinforcement Learning (RL) control method is proposed for the real-time overhead crane control problem. The crane control problem is first formulated as an optimal regulation problem with a user-specified objective function. Two neural-networks, namely Actor-Critic networks, are employed to approximate the objective function and the optimal control policy respectively. Then, an improved network updating rule with an additional passivity-based stabilization term is developed to remove the requirement of the initial stabilizing control policy. Unlike other crane control approaches, the proposed online RL algorithm does not rely on prior knowledge of the overhead crane mathematical model. Finally, simulation studies are carried out to demonstrate the effectiveness of the proposed method in the presence of system parameter variations when compared to LQR control.

关键词： Adaptation models Cranes System dynamics Reinforcement learning Linear programming Mathematical models Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Resilient Learning-Based Control Under Denial-of-Service Attacks

arXiv

引用

arXiv 2024年

作者： Chakraborty, Sayan Gao, Weinan Vamvoudakis, Kyriakos G. Jiang, Zhong-Ping The CAN Lab New York University BrooklynNY11201 United States The State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang110819 China The Daniel Guggenheim School of Aerospace Engineering Georgia Institute of Technology GA30332-0150 United States

In this paper, we have proposed a resilient reinforcement learning method for discrete-time linear systems with unknown parameters, under denial-of-service (DoS) attacks. The proposed method is based on policy iteration that learns the optimal controller from input-state data amidst DoS attacks. We achieve an upper bound for the DoS duration to ensure closed-loop stability. The resilience of the closed-loop system, when subjected to DoS attacks with the learned controller and an internal model, has been thoroughly examined. The effectiveness of the proposed methodology is demonstrated on an inverted pendulum on a cart. © 2024, CC BY-NC-ND.

关键词： Inverted pendulum

来源：评论

学校读者我要写书评

暂无评论

Neural Network-Based Dimensionality Reduction for Large-Scale Binary Optimization With Millions of Variables

引用

IEEE Transactions on Evolutionary Computation 2024年 1-1页

作者： Tian, Ye Wang, Luchen Yang, Shangshang Ding, Jinliang Jin, Yaochu Zhang, Xingyi School of Computer Science and Technology Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui University Hefei China Institutes of Physical Science and Information Technology Anhui University Hefei China School of Artificial Intelligence Anhui University Hefei China State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang China School of Engineering Westlake University Hangzhou China

Binary optimization assumes a pervasive significance in the context of practical applications, such as knapsack problems, maximum cut problems, and critical node detection problems. Existing techniques including mathematical programming, heuristics, evolutionary computation, and neural networks have been employed to tackle binary optimization problems (BOPs), however, they grapple with the challenge of optimizing a large number of binary variables. In this paper, we propose a dimensionality reduction method to assist evolutionary algorithms in solving large-scale BOPs, which is achieved based on neural networks. The proposed method converts the optimization of a large number of binary variables into the optimization of a small number of network weights, resulting in a significant reduction in search space dimensionality. Crucially, the proposed method obviates the necessity for a training process, which eliminates the requirement for a priori knowledge and enhances the search efficiency. On six types of single-and multi-objective BOPs with up to 10 000 000 variables, the proposed method demonstrates superiority over top-tier evolutionary algorithms and neural network-based methods. IEEE

关键词： Neural networks

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：