检索结果-内蒙古大学图书馆

Deep Reinforcement Learning-Assisted Robust Cubature Kalman Filter for Power System Dynamic State Estimation With Multi-Rate Measurements

引用

IEEE Transactions on Automation Science and Engineering 2025年 22卷 14346-14357页

作者： Gu, Haoli Liu, Shichao Chen, Bo Wang, Rusheng Yu, Li Kaynak, Okyay Zhejiang University of Technology Department of Automation Hangzhou310023 China Zhejiang Key Laboratory of Intelligent Perception and Control for Complex Systems Hangzhou310023 China Ningbo University of Technology Ningbo315201 China Bogazici University Istanbul34342 Turkey

The coexistence of high-frequency phasor measurement units (PMUs) and conventional SCADA systems raises the challenge of heterogenous-source and multi-rate measurements which significantly degrades the performance of power system dynamic state estimation. In this work, a deep reinforcement learning (DRL) assisted robust cubature Kalman filtering (CKF) scheme is proposed to handle measurements from hybrid sources and with different time scales. In specific, a multi-rate measurement function reconstruction approach is designed with an independent discretization mechanism to lift the present limitation of requiring an integer multiple relationship of the sampling rates from multiple sources in most of existing works. Embedded with this discretization mechanism, a deep reinforcement learning assisted two-parameter linear exponential smoothing method is proposed to reconstruct the slow measurement model with online adjustable estimation parameters. A generalized correntropy loss criterion is also included in the robust CKF to counter the non-Gaussian noise and the noise distribution variation caused by the reconstruction. Comparisons results demonstrate that the proposed DRL-based robust CKF method can achieve better accuracy and robustness under various operating scenarios. © 2004-2012 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Privacy-preserving distributed estimation for interconnected dynamic systems

引用

Automatica 2025年 177卷

作者： Zhang, Yuchen Chen, Bo Wang, Jianzheng Yu, Li Department of Automation Zhejiang University of Technology Hangzhou310023 China Zhejiang Key Laboratory of Intelligent Perception and Control for Complex Systems Hangzhou310023 China

This paper investigates the problem of privacy protection in distributed estimation for interconnected dynamic systems. The exchange of information between subsystems during weighted sum aggregation poses significant privacy risks to distributed estimation. To address these concerns, we propose a noise contamination mechanism for private matrix–vector multiplication and private weighted sum aggregation. This mechanism decomposes the matrix into two column-rank-deficient matrices and injects noises derived from their null spaces to protect the confidentiality of the vector during the matrix–vector multiplication. Several conditions are established to ensure that the mechanism achieves complete confidentiality. Subsequently, we design a double-layer encryption scheme for private weighted sum aggregation with hidden weights, incorporating private matrix–vector multiplication and the Paillier cryptosystem. Furthermore, we develop privacy-preserving distributed estimators for interconnected dynamic systems using the proposed aggregation schemes. Our analysis demonstrates that both subsystems and their distributed estimators achieve effective privacy protection. Finally, an illustrative example is provided to validate the effectiveness of the proposed methods. © 2025 Elsevier Ltd

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Resilient Formation control Based on Watermarks for Networked Quadrotors under Deception Attacks

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Zhan, Weiwei Miao, Zhiqiang Zeng, Jianxin Chen, Yanjie Wu, Zheng-Guang He, Wei Wang, Yaonan Hunan University College of Electrical and Information Engineering Changsha410082 China Fuzhou University School of Mechanical Engineering and Automation Fuzhou350108 China National Engineering Research Center of Robot Visual Perception and Control Technology Changsha410082 China Zhejiang University Institute of Cyber-Systems and Control Hangzhou310027 China University of Science and Technology Beijing Key Laboratory of Intelligent Bionic Unmanned Systems Ministry of Education School of Intelligence Science and Technology Institute of Artificial Intelligence Beijing100083 China

This article addresses the problem of formation control of networked UAVs under deception attacks. A lightweight resilient formation control framework based on watermarks is proposed to achieve the desired formation configuration without extra monitoring attack status. Since deception attacks are covert, the shared information is watermarked before transmission to establish the protocol among networked UAVs. To facilitate the resilient formation controller design, a decoder is first developed to decipher the inverse transformation of deception attacks, where the watermark is the criterion for approximating the inverse transformation. The Gauss error function is introduced to eliminate some unrealistic input commands under deception attacks, obtaining the predefined input performance. Then, a resilient formation controller is developed to guarantee the global boundedness of all signals within the inner-loop and outerloop system, while the formation error converges to a small neighborhood of zero by solving the linear matrix inequality. Two challenging deception attack examples in simulations and experiments are conducted to verify the effectiveness and performance of the proposed resilient formation control framework. © 1967-2012 IEEE.

关键词： Inverse transforms

来源：评论

学校读者我要写书评

暂无评论

RGB-infrared fusion tracking algorithm based on Siamese network 2

RGB-infrared fusion tracking algorithm based on Siamese netw...

引用

2nd International Conference on Computer Vision, Image, and Deep Learning

作者： Li, Ruyou Cui, Wennan Wang, Zhiyong Zhang, Jingjing School of Automation China University of Geosciences Wuhan430074 China Key Laboratory of Intelligent Infrared Perception Chinese Academy of Sciences Hubei key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education

ISBN: (数字)9781510646827

ISBN: (纸本)9781510646810

The target tracking method based on RGB image is affected by many factors such as light and haze weather, so it is difficult to distinguish the tracking target from the background, and it is easy to lead to the drift or even loss of the tracking target. Target tracking based on infrared images is not affected by light, haze and other illumination factors, but the target's color, texture and other characteristic information will be missing. Therefore, in order to obtain the target's color, texture and other characteristic information in a poorly illuminated environment, while achieving accurate and fast tracking of the object, this paper proposes a RGB and infrared image fusion tracking method based on a deep convolutional network. Firstly, the fusion method of RGB and infrared images is studied;secondly, a target tracking network based on the Siamese network is established to extract the image convolution features of the target template and the current target;finally, the response map is calculated by the deep cross-correlation module. At last, the performance test of the target tracking algorithm is carried out on the VOT2019RGBT data set. Experimental results show that the algorithm can effectively solve the problem of target tracking when the target is partially occluded, the tracking scene has no suitable illumination or the light changes strongly, and it is of great significance to improve the accuracy of target tracking under complex backgrounds. © 2021 SPIE.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

A bi-level optimization approach for joint rack sequencing and storage assignment in robotic mobile fulfillment systems

引用

Science China(Information Sciences) 2023年第11期66卷 127-149页

作者： Xiang SHI Fang DENG Sai LU Yunfeng FAN Lin MA Jie CHEN Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing Institute of Technology Beijing Institute of Technology Chongqing Innovation Center Zhejiang Cainiao Supply Chain Management Co. Ltd. Shanghai Research Institute for Intelligent Autonomous Systems

This paper studies a novel rack scheduling problem with multiple types of multiple storage locations(RS-MTMS), which can decide the retrieval sequence of racks and assign each rack a storage location after visiting a picking station. A major challenge in RS-MTMS is that the storage assignment problem and the retrieval sequence decision are closely coupled. If the RS-MTMS is solved directly, the storage assignment scheme and the retrieval sequence of racks are generally generated separately, thus resulting in poor performance. To overcome this difficulty, we propose a bi-level optimization approach for jointly optimizing the storage assignment and retrieval sequence(Bi JSR). In Bi JSR, the storage assignment problem is solved by variable neighborhood search(VNS) in the upper-level optimization. Effective candidate modes are incorporated into VNS to improve solution quality and computational efficiency. The sequencing optimization is obtained in the lower-level according to the given storage location set. A transformation strategy with sufficient problem-specific knowledge is developed to identify the lower-level optimization as the traveling salesman problem and its variants. Then these identified problems are solved using the loop-based *** results show that the proposed Bi JSR is more effective and efficient than the representative algorithms in solving the RS-MTMS problem.

关键词： rack scheduling sequence decision storage assignment bi-level optimization robotic mobile fulfillment system

来源：评论

学校读者我要写书评

暂无评论

Optimal Rescue Path for Maritime Air Crash Based on Probability Density Distribution and Bayesian Formula

Optimal Rescue Path for Maritime Air Crash Based on Probabil...

引用

第37届中国控制会议

作者： Jing Wang Ping Yu Zhen-Tao Liu State Key Laboratory of Industrial Control Technology College of Control Science and EngineeringZhejiang University Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems

Optimal rescue path for maritime air crash based on probability density distribution and Bayesian formula is proposed,where probable crash area is determined through surface search at a high altitude,and then the minimum wreckage floating zone is obtained by probability density ***,we divide it into regular hexagons based on Honeycomb Model to identify the point search area that is endowed with priority by Bayesian ***,the optimal path is worked out by transferring optimization problem to be a Traveling Salesman Problem(TSP).In simulations,some spots are randomly chosen on a Google map in which we can find debris in ocean through surface search at high *** a point search route is obtained by using Annealing algorithm,which strips out 4%of time compared with current *** intelligent search and rescue framework based on reinforcement learning is *** future work,search and rescue work will be free from manpower and bad weather constraints.

关键词： Point search Hexagonal regions Priority Bayesian formula Traveling Salesman Problem Reinforcement Learning

来源：评论

学校读者我要写书评

暂无评论

An Improved Machine Learning Model for Pure Component Property Estimation

引用

Engineering 2024年第8期39卷 61-73页

作者： Xinyu Cao Ming Gong Anjan Tula Xi Chen Rafiqul Gani Venkat Venkatasubramanian State Key Laboratory of Industrial Control Technology College of Control Science and EngineeringZhejiang UniversityHangzhou 310027China Department of Physics Bard College at Simon’s RockGreat BarringtonMA 01230USA PSE for SPEED Company Charlottenlund DK-2920Denmark Sustainable Energy and Environment Thrust The Hong Kong University of Science and Technology(Guangzhou)Guangzhou 510000China Department of Applied Sustainability Széchenyi István UniversityGyör 9026Hungary Complex Resilient Intelligent Systems Laboratory Department of Chemical EngineeringColumbia UniversityNew YorkNJ 10027USA

Information on the physicochemical properties of chemical species is an important prerequisite when performing tasks such as process design and product ***,the lack of extensive data and high experimental costs hinder the development of prediction techniques for these ***,accuracy and predictive capabilities still limit the scope and applicability of most property estimation *** paper proposes a new Gaussian process-based modeling framework that aims to manage a discrete and high-dimensional input space related to molecular structure representation with the group-contribution approach.A warping function is used to map discrete input into a continuous domain in order to adjust the correlation between different *** selection techniques,including prior elicitation and prior predictive checking,are also applied during the building procedure to provide the model with more information from previous research *** framework is assessed using datasets of varying sizes for 20 pure component *** 18 out of the 20 pure component properties,the new models are found to give improved accuracy and predictive power in comparison with other published models,with and without machine learning.

关键词： Group contribution Gaussian process Warping function Prior predictive checking

来源：评论

学校读者我要写书评

暂无评论

Cooperative trajectory planning algorithm of USV-UAV with hull dynamic constraints

arXiv

引用

arXiv 2022年

作者： Huang, Tao Chen, Zhe Gao, Wang Xue, Zhenfeng Liu, Yong Institute of Cyber-Systems and Control Zhejiang University No.38 Zheda Road Hangzhou310027 China Research Center for Intelligent Perception and Control Huzhou Institute of Zhejiang University No.819 Xisaishan Road Huzhou313098 China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100191 China

Efficient trajectory generation in complex dynamic environments remains an open problem in the unmanned surface vehicle (USV). The perception of the USV is usually interfered with by the swing of the hull and the ambient weather, making it challenging to plan the optimal USV trajectories. In this paper, a cooperative trajectory planning algorithm for the coupled USV-UAV system is proposed to ensure that USV can execute a safe and smooth path in the process of autonomous advance in multi-obstacle maps. Specifically, the unmanned aerial vehicle (UAV) plays the role of a flight sensor, providing real-time global map and obstacle information with a lightweight semantic segmentation network and 3D projection transformation. And then, an initial obstacle avoidance trajectory is generated by a graph-based search method. Concerning the unique under-actuated kinematic characteristics of the USV, a numerical optimization method based on hull dynamic constraints is introduced to make the trajectory easier to be tracked for motion control. Finally, a motion control method based on NMPC with the lowest energy consumption constraint during execution is proposed. Experimental results verify the effectiveness of the whole system, and the generated trajectory is locally optimal for USV with considerable tracking accuracy. © 2022, CC BY.

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

Deep Domain Adaptation Regression for Force Calibration of Optical Tactile Sensors

Deep Domain Adaptation Regression for Force Calibration of O...

引用

IEEE/RSJ International Conference on intelligent Robots and systems (IROS)

作者： Zhuo Chen Ni Ou Jiaqi Jiang Shan Luo Department of Engineering Robot Perception Lab Centre for Robotics Research King’s College London London United Kingdom State Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing Institute of Technology Beijing China

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Optical tactile sensors provide robots with rich force information for robot grasping in unstructured environments. The fast and accurate calibration of three-dimensional contact forces holds significance for new sensors and existing tactile sensors which may have incurred damage or aging. However, the conventional neural-network-based force calibration method necessitates a large volume of force-labeled tactile images to minimize force prediction errors, with the need for accurate Force/Torque measurement tools as well as a time-consuming data collection process. To address this challenge, we propose a novel deep domain-adaptation force calibration method, designed to transfer the force prediction ability from a calibrated optical tactile sensor to uncalibrated ones with various combinations of domain gaps, including marker presence, illumination condition, and elastomer modulus. Experimental results show the effectiveness of the proposed unsupervised force calibration method, with lowest force prediction errors of 0.102N (3.4% in full force range) for normal force, and 0.095N (6.3%) and 0.062N (4.1%) for shear forces along the x-axis and y-axis, respectively. This study presents a promising, general force calibration methodology for optical tactile sensors.

关键词： Accuracy Force Tactile sensors Lighting Elastomers Data collection Optical imaging Adaptive optics Calibration Optical sensors

来源：评论

学校读者我要写书评

暂无评论

Near-Optimal Online Motion Planning of Connected and Automated Vehicles at a Signal-Free and Lane-Free Intersection

Near-Optimal Online Motion Planning of Connected and Automat...

引用

2018 IEEE intelligent Vehicles Symposium, IV 2018

作者： Li, Bai Zhang, Youmin Zhang, Yue Jia, Ning Ge, Yuming Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'An University of Technology Xi'an710048 China College of Control Science and Engineering Zhejiang University Hangzhou310027 China Department of Mechanical Industrial and Aerospace Engineering Concordia Institute of Aerospace Design and Innovation Concordia University Montreal Canada Division of Systems Engineering Center for Information and Systems Engineering Boston University BostonMA02215 United States Institute of Systems Engineering Tianjin University Tianjin300072 China China Academy of Information and Communications Technology Beijing100191 China

ISBN: (纸本)9781538644522

In this paper, we propose a cooperative motion planning method for a group of connected and automated vehicles (CAVs) crossing a lane-free intersection without using explicit traffic signaling. This multi-vehicle motion planning task is formulated as a centralized optimal control problem. However, the solution to this optimal control problem is numerically intractable due to the high dimensionality of the collision-avoidance constraints and the nonlinearity of the vehicle kinematics. A two-stage strategy is proposed for generating online solutions: at Stage 1, the CAVs are requested to reach a standard formation before entering the intersection;at Stage 2, the vehicles cross the intersection. As the motion planning sub-problem at Stage 2 begins with a standard configuration, the optimal solution to this standard sub-problem can be computed offline in advance and applied online directly. On the other hand, the formation reconfiguration sub-problem at Stage 1 is easy to solve online. Through dividing the entire dynamic process into two periods, the difficulties in the original optimal control problem are significantly reduced so that the real-time performance is achieved. © 2018 IEEE.

关键词： Motion planning

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：