检索结果-内蒙古大学图书馆

4th IEEE International Conference on Information Technology, Big Data and Artificial Intelligence, ICIBA 2024

作者： Chen, Xiaoyu Du, Shuxin Qiu, Yi Huzhou University School of Engineering Zhejiang China Huzhou Key Laboratory of Intelligent Sensing and Optimal Control for Industrial Systems Zhejiang China

ISBN: (纸本)9798350363586

Currently, large models perform extremely well in natural language processing (NLP). Pre-trained large-scale language models (such as GPT-4, BERT, T5, etc.) have achieved significant performance improvements in a variety of NLP tasks. However, applying these models to specific domains still faces significant challenges, such as lack of domain-specific knowledge and insufficient adaptation to domain-specific structured data. In this article, we take the e-commerce field as an example, clean and convert various collected e-commerce structured data into specific formats, and conduct continuous pre-training of the TAPAS model. During the pre-training process, parameters are gradually adjusted through backpropagation to minimize the loss function to improve the accuracy of the model. By comparing various indicators with other models. Experimental results show that the TAPAS model after continuous pre-training shows better performance in processing structured data tasks in the e-commerce field, significantly improving its accuracy in tasks such as question answering and information extraction in this field. © 2024 IEEE.

关键词： Data accuracy

来源：评论

学校读者我要写书评

暂无评论

Output-Feedback RMPC for Polytopic Uncertain Systems under Multiple Fading Measurements 6

Output-Feedback RMPC for Polytopic Uncertain Systems under M...

引用

6th International Conference on Internet of Things, Automation and Artificial Intelligence, IoTAAI 2024

作者： Li, Huangju Yu, Yanye Wang, Jianhua Zhou, Min Zuo, Jiawei Huzhou University School of Engineering Huzhou China Huzhou Key Laboratory of Intelligent Sensing and Optimal Control of Industrial Systems Huzhou China

ISBN: (纸本)9798350386974

This paper addresses output-feedback robust model predictive control (RMPC) for systems with polytopic uncertainties and fading measurements. The phenomenon of fading measurements, which better describes practical engineering, and the attenuation coefficients of which are described by a set of random variables with known statistical properties. It aims to design a series of controllers within the RMPC framework to ensure the asymptotic stability of the closed-loop system. Then, sufficient conditions are provided to guarantee the feasibility of the RMPC strategy and the stability of the established closed-loop system. Finally, the effectiveness of the proposed MPC strategy is demonstrated through a network-based DC motor exemplification. © 2024 IEEE.

关键词： Predictive control systems

来源：评论

学校读者我要写书评

暂无评论

Robust model predictive control based on FlexRay communication protocol 6

Robust model predictive control based on FlexRay communicati...

引用

6th International Conference on Internet of Things, Automation and Artificial Intelligence, IoTAAI 2024

作者： Zhou, Min Yu, Yanye Wang, Jianhua Zuo, Jiawei Li, Huangju Huzhou University School of Engineering Huzhou China HuZhou Key Laboratory of Intelligent Sensing and Optimal Control of Industrial Systems Huzhou China

ISBN: (纸本)9798350386974

This study investigates robust model predictive control (RMPC) problem for a class of polytopic uncertain systems under the FlexRay protocol (FRP). The FRP, which is governed by both the time-triggered (Round-Robin protocol, RRP) and event-triggered (try-once-discard protocol, TODP) rules, is embedded into the shared communication network to orchestrate the transmission rule of the signals with different attributes, thereby further enhancing the transmission flexibility. The objective of this paper is to design a output feedback controller within the RMPC framework, providing sufffcient conditions for the recursive feasibility of the RMPC strategy and the asymptotical stability of the closed-loop system in terms of the token-dependent Lyapunov-like approach. Furthermore, an effective controller under the RMPC framework is derived by solving an online constrained optimization problem. Finally, the effectiveness of the model predictive control strategy is veriffed through numerical simulations. © 2024 IEEE.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

Fault Tolerant control Based on GA-DRE for a Manipulator with Actuator Fault 43

Fault Tolerant Control Based on GA-DRE for a Manipulator wit...

引用

43rd Chinese control Conference, CCC 2024

作者： Qiu, Jiongzhi Fang, Yiming Zhao, Donliang Liu, Le Shao, Nuan Yanshan University Key Lab of Industrial Computer Control Engineering of Hebei Province Qinhuangdao066004 China Hebei University of Environmental Engineering Department of Environmental Engineering Qinhuangdao China

ISBN: (纸本)9789887581581

To solve the trajectory tracking control problem of a rigid manipulator system in the case of unexpected actuator failure, considering the uncertainty of system parameters and bounded disturbance, an adaptive fault-tolerant tracking control strategy is proposed in this paper. Firstly, an adaptive strategy is designed to estimate and compensate the effects of actuator failure and system uncertainty, and the dynamic regression matrix is extended and mixed to improve the accuracy of parameter estimation without persistency of excitation (PE), which will enhance the trajectory tracking performance. Then, in the framework of sliding mode fault-tolerant control, combined with standard Gradient Adaptive and Dynamic Regressor Extension (GA-DRE) parameter estimation technology, a composite adaptive fault-tolerant controller is designed. Finally, theoretical analysis and numerical simulation results show that the proposed method can perform accurate parameter estimation in a finite time under the premise of matching the new conditions based on DRE additional terms, and the trajectory tracking errors of the expected positions and velocities of each joint of the manipulator can asymptotically converge to zero. © 2024 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Sliding mode control

来源：评论

学校读者我要写书评

暂无评论

Resilient Robust Model Predictive control under Adaptive Event-Triggered Mechanism 6

Resilient Robust Model Predictive Control under Adaptive Eve...

引用

6th International Conference on Internet of Things, Automation and Artificial Intelligence, IoTAAI 2024

作者： Yu, Yanye Li, Huangju Wang, Jianhua Zhou, Min Zuo, Jiawei Huzhou University School of Engineering Huzhou China Huzhou Key Laboratory of Intelligent Sensing and Optimal Control of Industrial Systems Huzhou China

ISBN: (纸本)9798350386974

The problem of resilient robust model predictive control (RMPC) with hard constraints based on an adaptive event-triggered mechanism for a class of polytopic uncertain systems is investigated in this article. To reduce the burden of network communication, a novel adaptive event-triggering mechanism is introduced between the sensor and the controller (S/C) network. The objective of this paper is to design a resilient RMPC controller while considering the system performance degradation caused by the adaptive event-triggered mechanism, aiming to maintain high system performance while conserving communication resources. Moreover, by solving an online optimization problem, sufficient conditions are obtained to ensure that all states of the system are in the time-varying terminal constraint set. To conclusively validate the efficacy of the proposed resilient RMPC algorithm under the adaptive event-triggered mechanism, we adopt a specific distillation parameter example for illustration. © 2024 IEEE.

关键词： Predictive control systems

来源：评论

学校读者我要写书评

暂无评论

Variational Reconstruction and Simulation Experiments of Sea Surface Wind Field for Ocean Data Buoy

引用

Journal of Ocean University of China 2024年第3期23卷 577-582页

作者： LI Yunzhou HUANG Sixun YAN Shen SUN Xuejin QI Suiping WANG Zhongqiu TANG Xiaoyu College of Meteorology and Oceanography National University of Defense TechnologyChangsha 410073China Institute of Oceanographic Instrumentation Qilu University of Technology(Shandong Academy of Sciences)Qingdao 266061China State Key Laboratory of Industrial Control Technology College of Control Science and EngineeringZhejiang UniversityHangzhou 310027China Laoshan Laboratory Qingdao 266237China

The sea surface wind field is an important physical parameter in oceanography and *** the continuous refinement of numerical weather prediction,air-sea interface materials,energy exchange,and other studies,three-dimensional(3D)wind field distribution at local locations on the sea surface must be measured *** current in-situ observation of sea surface wind parameters is mainly achieved through the installation of wind sensors on ocean data ***,the results obtained from this single-point measurement method cannot reflect wind field distribution in a vertical direction above the sea ***,the present paper proposes a theoretical framework for the optimal inversion of the 3D wind field structure variation in the area where the buoy is *** variation analysis method is first used to reconstruct the wind field distribution at different heights of the buoy,after which theoretical analysis verification and numerical simulation experiments are *** results indicate that the use of variational methods to reconstruct 3D wind fields is significantly effective in eliminating disturbance errors in observations,which also verifies the correctness of the theoretical analysis of this *** findings of this article can provide a reference for the layout optimization design of wind measuring instruments in buoy observation systems and also provide theoretical guidance for the design of new observation buoys in the future.

关键词： moored buoy three-dimensional wind field distribution variational analysis wind field reconstruction

来源：评论

学校读者我要写书评

暂无评论

Deterministic Event-Based Physical Watermarks Against Replay Attacks in Cyber-Physical Systems

IEEE Transactions on Industrial Cyber-Physical Systems

引用

IEEE Transactions on industrial Cyber-Physical Systems 2025年 3卷 61-69页

作者： Zhao, Xudong Xing, Wei Zhang, Junfeng Wang, Xinyu Zong, Guangdeng Zhao, Ning Hainan University School of Information and Communication Engineering Haikou570288 China Dalian University of Technology Key Laboratory of Intelligent Control and Optimization for Industrial Equipment Ministry of Education Dalian116622 China Tiangong University School of Control Science and Engineering Tianjin300387 China Bohai University College of Control Science and Engineering Jinzhou121013 China

Cyber-physical systems (CPSs) are of great importance in various applications and have garnered significant attention. Ensuring their security is a crucial concern, while this paper focuses on the security of CPSs against replay attacks during the transmission of sensor measurements over a wireless network. It is widely recognized that incorporating physical watermark signals is an effective approach to mitigate replay attacks. However, traditional physical watermarks are time-based and result in a notable degradation in the performance of Linear Quadratic Gaussian systems. With this in mind, a novel event-based physical watermarking technique is devised to address the performance degradation and detect replay attacks. The approach involves a deterministic physical watermark schedule that utilizes the innovation sequence to determine whether to incorporate physical watermarks or not. We provide evidence that the probability of successfully embedding physical watermarks increases when the system is targeted by malicious attacks. Additionally, we demonstrate that the deterministic event-based watermarking approach is more effective than the traditional time-based watermarking method. Finally, simulation examples are included to validate and illustrate the theoretical results. © 2023 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

Real-Time Intrusion Detection Based on Decision Fusion in industrial control Systems

IEEE Transactions on Industrial Cyber-Physical Systems

引用

IEEE Transactions on industrial Cyber-Physical Systems 2024年 2卷 143-153页

作者： Xue, Yawen Pan, Jie Geng, Yangyang Yang, Zeyu Liu, Mengxiang Deng, Ruilong Information Engineering University Zhengzhou450001 China Singapore University of Technology and Design ITrust 487372 Singapore The University of Sheffield Department of Automatic Control and Systems Engineering SheffieldS10 2TN United Kingdom Zhejiang University State Key Laboratory of Industrial Control Technology The College of Control Science and Engineering Hangzhou310027 China Huzhou Institute of Industrial Control Technology Huzhou313000 China

industrial control systems (ICSs) are becoming increasingly interconnected as the rapid convergence of information technology (IT) and operation technology (OT) networks, and meanwhile massive attack surfaces have been exposed. However, traditional intrusion detection systems (IDSs) are difficult to be directly deployed in ICSs due to the hard real-time requirement and rare patching chance. Besides, the design of effective and practical IDSs is hampered by the lack of benchmarking ICS cybersecurity datasets. To bridge the gaps, this paper makes the first attempt by open-sourcing the developed ICS cybersecurity datasets and proposing a decision fusion based real-time IDS. Firstly, we design a customized cybersecurity dataset in a full-hardware and high-fidelity platform, including 7 types of cyber threats tailored for ICSs. The collected dataset includes network traffic, sensor readings, actuator status, and system parameters, providing the state-of-the-art benchmark dataset for ICSs consisting of cross-layer characteristics. Furthermore, we design an online decision fusion-based IDS by strategically integrating 4 widely-used machine learning models. The proposed IDS is deployed on a real-time running ethanol distillation, surpassing the performance of single detection models in terms of precision and F1-score, which substantially enhances intrusion detection accuracy and cybersecurity of ICS. © 2023 IEEE.

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

Broadcast Gossip Algorithm for Nash Equilibrium Seeking of Nonaggregative Games

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第5期5卷 2444-2452页

作者： Wang, Dong Wu, Feiyue Xu, Xiaopeng Wen, Changyun Lian, Jie Zhou, Jun Dalian University of Technology Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education School of Control Science and Engineering Dalian116024 China Nanyang Technological University School of Electrical and Electronic Engineering 639798 Singapore Xuzhou Heavy Machinery Company Ltd. Xuzhou221600 China

In this article, we focus on seeking the Nash equilibrium (NE) of nonaggregative games over a directed communication network. An asynchronous broadcast-based gossip algorithm is proposed, where each player broadcasts its own decision and estimates of other players' decisions to its out-neighbors. Then, the neighboring players update its respective decisions using its independent stepsize and estimates of other players' decisions by weighting its own and the received decision estimates from $(0,\,1)$. The almost surely convergence of the proposed algorithm with the diminishing stepsizes is presented by using a lemma and the property of the Kronecker product. Furthermore, the expected error bound between the NE and decisions for the proposed algorithm with constant stepsizes is presented with the increasing active probability of each player. Finally, two numerical examples are provided to illustrate the effectiveness of the proposed algorithm and the convergence rate comparison. © 2020 IEEE.

关键词： Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

Reinforcement learning-based cost-sensitive classifier for imbalanced fault classification

引用

Science China(Information Sciences) 2023年第11期66卷 113-126页

作者： Xinmin ZHANG Saite FAN Zhihuan SONG State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University

Fault classification plays a crucial role in the industrial process monitoring domain. In the datasets collected from real-life industrial processes, the data distribution is usually imbalanced. The datasets contain a large amount of normal data(majority) and only a small amount of faulty data(minority); this phenomenon is also known as the imbalanced fault classification problem. To solve the imbalanced fault classification problem, a novel reinforcement learning(RL)-based cost-sensitive classifier(RLCC) based on policy gradient is proposed in this paper. In RLCC, a novel cost-sensitive learning strategy based on policy gradient and the actor-critic of RL is developed. The novel cost-sensitive learning strategy can adaptively learn the cost matrix and dynamically yield the sample weights. In addition, RLCC uses a newly designed reward to train the sample weight learner and classifier using an alternating iterative approach. The alternating iterative approach makes RLCC highly flexible and effective in solving the imbalanced fault classification *** effectiveness and practicability of the proposed RLCC method are verified through its application in a real-world dataset and an industrial process benchmark.

关键词： imbalanced fault classification fault diagnosis industrial process monitoring deep reinforcement learning cost-sensitive learning policy gradient sample weights

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：