检索结果-内蒙古大学图书馆

Fixed-time stabilization of discontinuous spatiotemporal neural networks with time-varying coefficients via aperiodically switching control

引用

Science China(Information Sciences) 2023年第5期66卷 182-195页

作者： Xiaofang HU Leimin WANG Chuan-Ke ZHANG Xiongbo WAN Yong HE School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education

This paper focuses on the challenge of fixed-time control for spatiotemporal neural networks(SNNs) with discontinuous activations and time-varying coefficients. A novel fixed-time convergence lemma is proposed, which facilitates the handling of time-varying coefficients of SNNs and relaxes the restriction on the non-positive definiteness of the derivative of the Lyapunov function. Besides, a more flexible and economical aperiodically switching control technique is presented to stabilize SNNs within a fixed time,efectively reducing the amount of information transmission and control costs. Under the newly established fixed-time convergence lemma and aperiodically switching controller, many more general algebraic conditions are deduced to ensure the fixed-time stabilization of SNNs. Numerical examples are provided to manifest the validity of the results.

关键词： spatiotemporal neural networks discontinuous activations time-varying coefficients fixed-time stabilization aperiodically switching control

来源：评论

学校读者我要写书评

暂无评论

Deep reinforcement learning for optimal denial-of-service attacks scheduling

引用

Science China(Information Sciences) 2022年第6期65卷 98-106页

作者： Fangyuan HOU Jian SUN Qiuling YANG Zhonghua PANG State Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing Institute of Technology Key Laboratory of Fieldbus Technology and Automation of Beijing North China University of Technology

We consider an optimal denial-of-service(DoS) attack scheduling problem of N independent linear time-invariant processes, where sensors have limited computational capability. Sensors transmit measurements to the remote estimator via a communication channel that is exposed to DoS attackers. However,due to limited energy, an attacker can only attack a subset of sensors at each time step. To maximally degrade the estimation performance, a DoS attacker needs to determine which sensors to attack at each time step. In this context, a deep reinforcement learning(DRL) algorithm, which combines Q-learning with a deep neural network, is introduced to solve the Markov decision process(MDP). The DoS attack scheduling optimization problem is formulated as an MDP that is solved by the DRL algorithm. A numerical example is provided to illustrate the efficiency of the optimal DoS attack scheduling scheme using the DRL algorithm.

关键词： optimal denial-of-service attack scheduling optimization limited energy deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Structure-Sensitive Graph Dictionary Embedding for Graph Classification

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第6期5卷 2962-2972页

作者： Liu, Guangbu Zhang, Tong Wang, Xudong Zhao, Wenting Zhou, Chuanwei Cui, Zhen Nanjing University of Science and Technology Key Laboratory of Intelligent Perception and Systems for High-Dimensional School of Computer Science and Engineering Nanjing210094 China

Graph structure expression plays a vital role in distinguishing various graphs. In this work, we propose a structure-sensitive graph dictionary embedding (SS-GDE) framework to transform input graphs into the embedding space of a graph dictionary for the graph classification task. Instead of a plain use of a base graph dictionary, we propose the variational graph dictionary adaptation (VGDA) to generate a personalized dictionary (named adapted graph dictionary) for catering to each input graph. In particular, for the adaptation, the Bernoulli sampling is introduced to adjust substructures of base graph keys according to each input, which increases the expression capacity of the base dictionary tremendously. To make cross-graph measurement sensitive as well as stable, multisensitivity Wasserstein encoding is proposed to produce the embeddings by designing multiscale attention on optimal transport. To optimize the framework, we introduce mutual information as the objective, which further deduces variational inference of the adapted graph dictionary. We perform our SS-GDE on multiple datasets of graph classification, and the experimental results demonstrate the effectiveness and superiority over the state-of-the-art methods. © 2020 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Data-driven rational design of single-atom materials for hydrogen evolution and sensing

引用

Nano Research 2024年第4期17卷 3352-3358页

作者： Lei Zhou Pengfei Tian Bowei Zhang Fu-Zhen Xuan Shanghai Key Laboratory of Intelligent Sensing and Detection Technology East China University of Science and TechnologyShanghai 200237China School of Mechanical and Power Engineering East China University of Science and TechnologyShanghai 200237China Key Laboratory of Pressure Systems and Safety of Ministry of Education East China University of Science and TechnologyShanghai 200237China

Herein we proposed a data-driven high-throughput principle to screen high-performance single-atom materials for hydrogen evolution reaction(HER)and hydrogen sensing by combing the theoretical computations and a topology-based multi-scale convolution kernel machine learning *** the rational training by 25 groups of data and prediction of all 168 groups of single-atom materials for HER and sensing,respectively,a high prediction accuracy(>0.931 R^(2) score)was achieved by our *** show that the promising HER catalysts include Pt atoms in C_(4) and Sc atoms in C_(1)N_(3) coordination ***,Y atoms in C_(4) coordination environment and Cd atoms in C_(2)N_(2)-ortho coordination environment were predicted with great potential as hydrogen sensing *** method provides a way to accelerate the discovery of innovative materials by avoiding the time-consuming empirical principles in experiments.

关键词： machine learning single-atom materials sensing hydrogen evolution

来源：评论

学校读者我要写书评

暂无评论

Accurate atomic scanning transmission electron microscopy analysis enabled by deep learning

引用

Nano Research 2024年第4期17卷 2971-2980页

作者： Tianshu Chu Lei Zhou Bowei Zhang Fu-Zhen Xuan Shanghai Key Laboratory of Intelligent Sensing and Detection Technology East China University of Science and TechnologyShanghai 200237China School of Mechanical and Power Engineering East China University of Science and TechnologyShanghai 200237China Key Laboratory of Pressure Systems and Safety of Ministry of Education East China University of Science and TechnologyShanghai 200237China

Currently,the machine learning(ML)-based scanning transmission electron microscopy(STEM)analysis is limited in the simulative stage,its application in experimental STEM is needed but ***,we built up a universal model to analyze the vacancy defects and single atoms accurately and rapidly in experimental STEM images using a full convolution *** our model,the unavoidable interference factors of noise,aberration,and carbon contamination were fully considered during the training,which were difficult to be considered in the *** toward the simultaneous identification of various vacancy types and low-contrast single atoms in the low-quality STEM images,our model showed rapid process speed(45 images per second)and high accuracy(>95%).This work represents an improvement in experimental STEM image analysis by ML.

关键词： deep learning low-dimensional materials atomic defects single atoms

来源：评论

学校读者我要写书评

暂无评论

Multi-objective configuration optimization method based on antlion algorithm for customer-oriented modular process

引用

Journal of intelligent and Fuzzy systems 2024年第3-4期47卷 265-277页

作者： Zhang, Qianqian Fan, Bo Sun, Lifan Information Engineering College Henan University of Science and Technology Luoyang China Henan Key Laboratory of Robot and Intelligent Systems Henan University of Science and Technology Luoyang China

Process parameter configuration needs to respond quickly in the customized manufacturing environment. A multi-objective optimization method based on antlion algorithm for product process configuration design is proposed. The weight mapping mechanism of customer demands is established to clarify the relationship between customer demands and manufacturing process, which also simplifies the process attribute analysis of customized products. The parameters to be optimized in the customization process are analyzed: product performance, process cost and production time. Based on the objective function including these parameters, a multi-objective optimization model of modular process reconstruction is established. The proposed model and algorithm can optimize these parameters in parallel and realize the rapid configuration of product modular process. In the application case of this paper, the proposed method is suitable for the whole process modular configuration of copper plate and strip. The feasibility and effectiveness of the model and algorithm in the proposed configuration scheme are verified. © 2024-IOS Press. All rights reserved.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Attitude Tracking Control for Rigid Spacecraft with Arbitrary Convergence Time

引用

Journal of systems Science & Complexity 2024年第6期37卷 2579-2594页

作者： XU Yu-Tian WU Ai-Guo Guangdong Provincial Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics Harbin Institute of Technology(Shenzhen)Shenzhen 518055China Key University Laboratory of Mechanism&Machine Theory and Intelligent Unmanned Systems of Guangdong Harbin Institute of Technology(Shenzhen)Shenzhen 518055China Department of Automation Harbin Institute of Technology(Shenzhen)Shenzhen 518055China HIT Wuhu Robot Technology Research Institute Wuhu 241060China

In this paper,attitude tracking control with arbitrary convergence time for rigid spacecraft is ***,a novel time-varying sliding function is proposed to achieve free-will arbitrary time convergence when the system states reside on the sliding *** such a sliding function,an attitude tracking controller is designed to guarantee that the states of the closed-loop system converge to the sliding surface within a predetermined time in the presence of external *** free-will arbitrary time convergences of the closed-loop system and sliding function are illustrated by numerical simulations.

关键词： Attitude tracking free-will arbitrary time stability rigid spacecraft sliding mode control

来源：评论

学校读者我要写书评

暂无评论

Robustness and Push Recovery of Humanoid Robots Using Predictive and Whole-Body Control

Robustness and Push Recovery of Humanoid Robots Using Predic...

引用

2024 IEEE International Conference on Unmanned systems, ICUS 2024

作者： Zhang, Shaojie Ni, Fenglei Li, Xueai Li, Xu Ji, Yi Shao, Xiangyu State Key Laboratory of Robotics and Systems Harbin Institute of Technology Harbin China Key Laboratory of Autonomous Intelligent Unmanned Systems Harbin Institute of Technology Harbin China

ISBN: (纸本)9798350384185

Robustness walking and recovery ability in uneven terrains and unexpected collisions are crucial for the practical application of humanoid ***, existing methods struggle to effectively balance stability, motion safety and walking *** paper proposes a hybrid control strategy combing Nonlinear Model Predictive Control (NMPC) and Whole-Body Control (WBC) to improve the robot's walking stability and reaction safety in collisions *** NMPC generates long-term and macroscopic movements, with capture point theory being utilized for foot placements determination under external *** this foundation, the WBC regulates the robot refinedly in real-time based on task priorities and *** verify the effectiveness of the proposed method, involving uneven terrain walking and external impacts rejection. © 2024 IEEE.

关键词： Anthropomorphic robots

来源：评论

学校读者我要写书评

暂无评论

Versatile Jumping of Humanoid Robots via Curriculum-Assisted Reinforcement Learning

Versatile Jumping of Humanoid Robots via Curriculum-Assisted...

引用

2024 China Automation Congress, CAC 2024

作者： Tan, Ruiyu Li, Xueai Ni, Fenglei Zhou, Dong Ji, Yi Shao, Xiangyu Key Laboratory of Autonomous Intelligent Unmanned Systems Harbin Institute of Technology Harbin China State Key Laboratory of Robotics and Systems Harbin Institute of Technology Harbin China

ISBN: (纸本)9798350368604

Versatile jumping is crucial for agile and adaptive behavior of humanoid robots in complex environments. However, humanoid robots have to manage impact forces while maintaining balance and stability throughout the take-off, flight, and landing phases, which imposes significant challenges for motion planning and controller design. This paper proposes a curriculum-assisted reinforcement learning framework for the humanoid robot to achieve various jumping tasks. The curriculum learning divides the jump training process into multi-stages and design different episodes in each stage to guarantee the training feasibility and generalize learned skills. Simulations on a 28 DOFs humanoid robot verify the excellent diverse jumping capability of the proposed policy. This exploration of different tasks also proves the policy’s robustness, allowing the robot quickly recover from perturbations using a variety of learned maneuvers. © 2024 IEEE.

关键词： Anthropomorphic robots

来源：评论

学校读者我要写书评

暂无评论

Distributed multiple model filtering for markov jump systems with communication delays

引用

Journal of the Franklin Institute 2023年第4期360卷 3407-3435页

作者： Li, Hui Yan, Liping Xia, Yuanqing Zhang, Jinhui the Key Laboratory of Intelligent Control Decision of Complex Systems School of Automation Beijing Institute of Technology Beijing100081 China

In this paper, we study a distributed state estimation problem for Markov jump systems (MJS) over sensor networks, in which each sensor node connects with each other through wireless networks with communication delays. We assume that each sensor node maintains a buffer to store delayed data transmitted from neighbor nodes. A distributed multiple model filter is designed by using the interacting multiple model methods (IMM) and a recursive delays compensation method. In order to ensure the stability, two stability conditions are derived for boundedness of estimation errors and boundedness of error covariance. Finally, the effectiveness of the proposed methods is illustrated by simulations and experiments of maneuvering target tracking. © 2022 The Franklin Institute

关键词： Sensor nodes

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：