检索结果-内蒙古大学图书馆

Concurrent learning-Based Adaptive control of Underactuated Robotic systems With Guaranteed Transient Performance for Both Actuated and Unactuated Motions

引用

ieee TRANSACTIONS ON NEURAL NETWORKS AND learning systems 2024年第12期35卷 18133-18144页

作者： Yang, Tong Sun, Ning Liu, Zhuoqing Fang, Yongchun Nankai Univ Coll Artificial Intelligence IRAIS Tianjin 300350 Peoples R China Nankai Univ Inst Intelligence Technol & Robot Syst Shenzhen Res Inst Shenzhen 518083 Peoples R China

With the wide applications of underactuated robotic systems, more complex tasks and higher safety demands are put forward. However, it is still an open issue to utilize "fewer" control inputs to satisfy control accuracy and transient performance with theoretical and practical guarantee, especially for unactuated variables. To this end, for underactuated robotic systems, this article designs an adaptive tracking controller to realize exponential convergence results, rather than only asymptotic stability or boundedness;meanwhile, unactuated states exponentially converge to a small enough bound, which is adjustable by control gains. The maximum motion ranges and convergence speed of all variables both exhibit satisfactory performance with higher safety and efficiency. Here, a data-driven concurrent learning (CL) method is proposed to compensate for unknown dynamics/disturbances and improve the estimate accuracy of parameters/weights, without the need for persistency of excitation or linear parametrization (LP) conditions. Then, a disturbance judgment mechanism is utilized to eliminate the detrimental impacts of external disturbances. As far as we know, for general underactuated systems with uncertainties/disturbances, it is the first time to theoretically and practically ensure transient performance and exponential convergence speed for unactuated states, and simultaneously obtain the exponential tracking result of actuated motions. Both theoretical analysis and hardware experiment results illustrate the effectiveness of the designed controller.

关键词： Lyapunov methods mechatronics motion control robotics underactuated systems

来源：评论

学校读者我要写书评

暂无评论

Adaptive Frequency control to Overcome Packet Dropouts and Uncertainties in Hybrid Power systems

引用

ieee ACCESS 2025年 13卷 44196-44213页

作者： Loka, Renuka Parimi, Alivelu M. Rao Gampa, Srinivasa Manoj Kumar, Nallapaneni Univ St Thomas Ctr Microgrid Res St Paul MN 55105 USA Birla Inst Technol & Sci Pilani BITS Pilani Dept Elect Engn Hyderabad Campus Hyderabad 500078 India Seshadri Rao Gudlavalleru Engn Coll Dept Elect & Elect Engn Gudlavalleru 521356 Andhra Pradesh India City Univ Hong Kong Sch Energy & Environm Kowloon Hong Kong Peoples R China Hariterde Int Council Circular Econ Res Ctr Res & Innovat Sci Technol Engn Arts & Math STE Palakkad 678631 Kerala India

The increasing integration of renewable energy into hybrid power systems (HPS) introduces significant uncertainties, posing challenges to frequency control. Additionally, packet dropouts in measurement and control signals further complicate frequency regulation under these uncertain conditions. Existing frequency regulation techniques often neglect real-world data on load and source uncertainties, packet dropouts in measurement data, and lack comprehensive control. This paper presents a novel adaptive control architecture designed to maintain network frequency stability in the presence of packet dropouts and system uncertainties. The proposed methodology consists of offline uncertainty characterization and online adaptive control. A deep learning model predicts load uncertainties, while supervised machine learning models characterize renewable fluctuations, informing model-based control. data-driven predictive control (DDPC) strategy has been implemented to compensate for packet dropouts. The DDPC features a triggering mechanism that activates adaptive control, combining uncertainty prediction with auxiliary control for dynamic frequency regulation. The proposed approach is validated through time-domain simulations on an isolated HPS with integrated renewable and distributed energy resources (DERs). Despite significant uncertainties and packet dropouts, the DDPC framework successfully limits frequency deviations to within 100 mHz. Furthermore, hardware-in-the-loop (HIL) simulations confirm the practical feasibility and robustness of the methodology. Integrating offline uncertainty characterization with online adaptive control offers an effective solution for robust frequency control in renewable integrated HPS.

关键词： Uncertainty Frequency control Load modeling Adaptive control Frequency measurement Renewable energy sources Loss measurement Adaptation models Measurement uncertainty Predictive models deep learning distributed energy resources frequency regulation hardware-in-the-loop simulation uncertainty

来源：评论

学校读者我要写书评

暂无评论

Enhancing Autonomous Driving: A Scalable Multi-Layered DRL Approach for Decision and control 13

Enhancing Autonomous Driving: A Scalable Multi-Layered DRL A...

引用

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

作者： Wu, Liangguang Zhou, Kailong Fei, Ting Yao, Maojia Han, Hao Li, Honglin Dongfeng Motor Corporation Research and Development Institute Wuhan432000 China School of Automotive Engineering Wuhan University of Technology Wuhan430070 China

ISBN: (纸本)9798350361674

Autonomous driving technology is rapidly progressing, promising significant societal benefits. This paper presents an advanced DRL-based framework for end-to-end autonomous vehicle decision-making and control. Our technical proposal is articulated through a scalable, multi-layered architecture that integrates sensory data aggregation, trajectory prediction, and dynamic control layers. The framework is distinctive for its Actor-Critic approach, where the Critic network evaluates potential trajectories and the Actor network implements the control commands, ensuring safety and compliance with traffic norms. The adaptability and robustness of our system are validated in extensive simulations and real-world trials, demonstrating its efficacy across various sensory system configurations. This research contributes to the autonomous driving domain by providing a versatile and reliable framework for intelligent vehicle navigation. The methodologies and systems presented in this paper have undergone rigorous validation through simulation experiments and practical real-vehicle tests, confirming the viability and effectiveness of our advanced DRL-based framework for autonomous vehicle decision-making and control. © 2024 ieee.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Tail-Sitter UAV Attitude Disturbance Rejection control with Compensating Function Observer Based Additive State Decomposition controller 13

Tail-Sitter UAV Attitude Disturbance Rejection Control with ...

引用

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

作者： Qin, Yulong Qi, Guoyuan Li, Kuo School of Control Science and Engineering Tiangong University Tianjin300387 China

ISBN: (纸本)9798350361674

This paper, a control method for suppressing attitude disturbance of a tail-sitter UAV is proposed. Due to the special structure of the UAV and the change of pitch angle during the transition, nonlinear terms and unwanted disturbance are introduced, which bring additional challenges to the controller design. The nonlinear and disturbance terms are placed in the primary system according to the principle of additive decomposition controller (ASD), then the matching and non-matching disturbance in the primary system are estimated using compensating function observer (CFO), and then The controllers of the primary and secondary systems can be obtained from the pole configurations, and the original system controllers are obtained by summing up these two controllers. Simulation results demonstrate that this control method has superior tracking effect in the face of large matching and non-matching disturbances compared with the traditional PID control algorithm. © 2024 ieee.

关键词： Disturbance rejection

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection Method for Complex systems Based on a Domain-Adaptive Causal Decoupling Model

引用

ieee TRANSACTIONS ON INDUSTRIAL INFORMATICS 2025年第3期21卷 2748-2757页

作者： Wang, Chong Liu, Jie Tsinghua Univ Dept Automat Beijing 100084 Peoples R China Beihang Univ Sch Reliabil & Syst Engn Beijing 100083 Peoples R China

Anomaly detection is vital for industrial system safety. The digitized industrial system has led to the widespread application of data-driven methods on anomaly detection modelling. Nevertheless, the time-variant operation conditions that change continuously the data distribution pose a significant risk of rendering models ineffective. To address this issue, a domain-adaptive causal decoupling model is designed in this article, considering the influence of operation conditions on system causality. And, an efficient anomaly detection method for complex systems is proposed, leveraging the domain-adaptive causal decoupling model. Specifically, a directed graph-based encoder is designed to capture the influence of the system operation modes and conditions on the causal structure and causal strength. Then, a causal decoupling model is proposed to learn domain-adaptive degradation status representations, which are essential for anomaly detection modeling. The effectiveness of the proposed method is verified via the real monitoring data of a high-speed train brake control system.

关键词： Monitoring Anomaly detection Degradation systems operation Complex systems Adaptation models Cause effect analysis Adaptive systems data models Informatics causal discovery causality complex systems decoupling causal representation learning domain adaptation

来源：评论

学校读者我要写书评

暂无评论

data-driven Multi-Objective Optimization of Power Consumption and Quality for Finishing Rolling Process 13

Data-Driven Multi-Objective Optimization of Power Consumptio...

引用

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

作者： Chen, Xiaolu Yang, Ying College of Engineering Peking University State Key Laboratory for Turbulence & Complex Systems Department of Mechanics and Engineering Science Beijing100871 China

ISBN: (纸本)9798350361674

This paper investigates the operational optimization in the context of the steel hot rolling production and finishing facilities. Optimizing the operational variables of the finishing rolling process can improve the rolling quality and reduce the unit power consumption. However, there are too many operational variables in the process and their interactions are strongly coupled, making it difficult to develop an effective model for in-depth study. Therefore, this paper adopts a data-driven approach, using neural network algorithms to construct the data prediction models between performance and set values respectively. Multi-objective optimization of the set values is performed by combining the actual mechanism and equipment constraints. In the obtained Pareto optimal solutions, the conflicting choices are further balanced among multiple objectives to obtain the most suitable operating parameters. Experimentally verified using production line production data, the method proposed in this paper significantly improves the performance indexes. © 2024 ieee.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

data-driven Dynamics Modeling of Miniature Robotic Blimps Using Neural ODEs With Parameter Auto-Tuning

引用

ieee ROBOTICS AND AUTOMATION LETTERS 2024年第12期9卷 10986-10993页

作者： Zhu, Yongjian Cheng, Hao Zhang, Feitian Peking Univ Coll Engn Dept Adv Mfg & Robot State Key Lab Turbulence & Complex Syst Beijing 100871 Peoples R China Peking Univ Coll Engn Dept Adv Mfg & Robot Robot & Control Lab Beijing 100871 Peoples R China

Miniature robotic blimps, as one type of lighter-than-air aerial vehicles, have attracted increasing attention in the science and engineering community for their enhanced safety, extended endurance, and quieter operation compared to quadrotors. Accurately modeling the dynamics of these robotic blimps poses a significant challenge due to the complex aerodynamics stemming from their large lifting bodies. Traditional first-principle models have difficulty obtaining accurate aerodynamic parameters and often overlook high-order nonlinearities, thus coming to their limit in modeling the motion dynamics of miniature robotic blimps. To tackle this challenge, this letter proposes the Auto-tuning Blimp-oriented Neural Ordinary Differential Equation method (ABNODE), a data-driven approach that integrates first-principle and neural network modeling. Spiraling motion experiments of robotic blimps are conducted, comparing the ABNODE with first-principle and other data-driven benchmark models, the results of which demonstrate the effectiveness of the proposed method.

关键词： Aerodynamics Robots Mathematical models Neural networks Accuracy Vehicle dynamics Nonlinear dynamical systems Vectors Quadrotors Force Dynamics calibration and identification machine learning for robot control

来源：评论

学校读者我要写书评

暂无评论

FLCSDet: Federated learning-driven Cross-Spatial Vessel Detection for Maritime Surveillance With Privacy Preservation

引用

ieee TRANSACTIONS ON INTELLIGENT TRANSPORTATION systems 2025年第1期26卷 1177-1192页

作者： Huang, Yanhong Liu, Wen Lin, Yijing Kang, Jiawen Zhu, Fenghua Wang, Fei-Yue Wuhan Univ Technol Hubei Key Lab Inland Shipping Technol Sch Nav Wuhan 430063 Peoples R China State Key Lab Maritime Technol & Safety Wuhan 430063 Peoples R China Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China Guangdong Univ Technol Sch Automat Guangzhou 510006 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Multimodal Artificial Intelligence S Beijing 100190 Peoples R China

Maritime surveillance plays a vital role in reducing maritime accidents and improving maritime safety. To enhance situational awareness for maritime movements, deep learning-based visual object detection has become an important part of maritime surveillance. However, the detection results are highly dependent on the training datasets collected from different departments (i.e., clients). If the sub-datasets from departments are sensitive and private in cross-department maritime surveillance, it will be intractable to directly combine these sub-datasets to train the learning-based object detection method. To solve this issue, we propose a federated learning-driven cross-spatial vessel detection model, called FLCSDet, for maritime surveillance with privacy preservation. In particular, an efficient multi-scale attention module is integrated into our FLCSDet to achieve local cross-spatial feature learning. To improve the federated-learning aggregation method, we propose an optimized algorithm based on the proportion of valid data on departments to adaptively select the allocating weights and preserve the specific characteristics of client data. In addition, we employ transfer learning to further improve the robustness and convergence of our FLCSDet under different experimental scenarios. Compared with several representative federated learning-based detection methods, our FLCSDet could achieve superior detection performance in terms of both quantitative and qualitative results. Moreover, comprehensive experiments conducted on real datasets from both inland waterways and open seas demonstrate the robustness and generalization of our method in intelligent transportation systems. The source code is available at https://***/huangyanh/FLCSDet.

关键词： Surveillance data privacy data models Visualization Training Adaptation models Safety Accuracy Traffic control Federated learning Maritime surveillance vessel detection federated learning privacy preservation

来源：评论

学校读者我要写书评

暂无评论

Quantitative Trading Model Building and Stock Investment Decision Making from a data-driven Perspective 13

Quantitative Trading Model Building and Stock Investment Dec...

引用

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

作者： Wang, Guoliang Guo, Guangxing Liaoning Petrochemical University Liaoning Fushun113001 China

ISBN: (纸本)9798350361674

This paper explores the problem of quantitative trading based on stock data from a data-driven perspective and develops a new model that relies deeply on buy, sell and hold behaviour to quantify and optimise investment returns. Considering the structural characteristics of the given model, traditional optimisation methods cannot meet the requirements. Therefore, we derive the optimal trading factors for the past time period based on historical stock price data and modify them so that they can be used to guide actual trading in the future. Although there are some differences between the modified trading factor and the ideal optimal trading factor, the results of the study show that the modified trading factor has utility in safeguarding investment returns, while the ideal optimal trading factor at future moments is not available. Meanwhile, we propose a data-driven investment strategy to further improve investment returns. Finally, the practical feasibility and generality of the proposed model and methodology are verified by detailed trading of actual stock price data. © 2024 ieee.

关键词： Computer Simulations data driven data Visualization Investment Decisions Quantitative Trading

来源：评论

学校读者我要写书评

暂无评论

Detection of Faults and Attacks in Power Monitoring System via Semi-Supervised learning with Pseudo Label Refinery 36

Detection of Faults and Attacks in Power Monitoring System v...

引用

36th Chinese control and Decision conference (CCDC)

作者： Chen, Wei Zhang, Wei Li, Yuanzhi Miao, Kaiyao Zhang, Meng State Grid Anhui Elect Power Dispatch & Control Ctr Hefei Peoples R China State Grid Anhui Elect Power Elect Power Res Inst Hefei Peoples R China Xi An Jiao Tong Univ Sch Cyber Sci & Engn Xian Peoples R China

ISBN: (纸本)9798350387780;9798350387797

With the expansion of power grids and incorporation of new energy sources, fault and attack detection in power monitoring systems has become increasingly vital for maintaining grid stability and safety. A significant challenge for data-driven detection methods is the scarcity of labeled measurement data, which critically hampers their detection performance. This paper proposes a novel data-driven framework, SuPer, for detecting faults and attacks in power monitoring systems. SuPer employs a novel combination of self-adaptive thresholding-based pseudolabeling and prototype-based data purification strategies, which have superior detection performance under conditions of scarcity labeled data. SuPer generates reliable pseudo-labels for massive unlabeled measurements and selects the high-confidence ones to participate in the training process, which enhances the machine learning model's ability to identify anomalies accurately. Extensive experiments are conducted in a power system framework to demonstrate SuPer's effectiveness, particularly highlighting its improved performance in scenarios with limited labeled data.

关键词： faults cyber-attacks power monitoring systems semi-supervised learning pseudo-labeling

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：