检索结果-内蒙古大学图书馆

An Adaptive Physics-Informed Neural Network with Two-Stage Learning Strategy to Solve Partial Differential Equations

引用

Numerical Mathematics(Theory,Methods and Applications) 2023年第2期16卷 298-322页

作者： Shuyan Shi Ding Liu Ruirui Ji Yuchao Han School of Automation and Information Engineering Xi‘an University of TechnologyXi‘an 710048P.R.China National&Local Joint Engineering Research Center of Crystal Growth Equipment and System Integration Xi‘an 710048P.R.China Xi’an University of Technology Shannxi Key Laboratory of Complex System Control and Intelligent Information ProcessingXi‘an 710048P.R.China

Physics-Informed Neural Network(PINN)represents a new approach to solve Partial Differential Equations(PDEs).PINNs aim to solve PDEs by integrating governing equations and the initial/boundary conditions(I/BCs)into a loss ***,the imbalance of the loss function caused by parameter settings usually makes it difficult for PINNs to converge,*** they fall into local *** other words,the presence of balanced PDE loss,initial loss and boundary loss may be critical for the *** addition,existing PINNs are not able to reveal the hidden errors caused by non-convergent boundaries and conduction errors caused by the PDE near the ***,these problems have made PINN-based methods of limited use on practical *** this paper,we propose a novel physics-informed neural network,*** adaptive physics-informed neural network with a two-stage training *** algorithm adds spatio-temporal coefficient and PDE balance parameter to the loss function,and solve PDEs using a two-stage training process:pre-training and formal *** pre-training step ensures the convergence of boundary loss,whereas the formal training process completes the solution of PDE by balancing various loss *** order to verify the performance of our method,we consider the imbalanced heat conduction and Helmholtz equations often appearing in practical *** Klein-Gordon equation,which is widely used to compare performance,reveals that our method is able to reduce the hidden *** results confirm that our algorithm can effectively and accurately solve models with unbalanced loss function,hidden errors and conduction *** codes developed in this manuscript are publicy available at https://***/callmedrcom/ATPINN.

关键词： Physics informed neural networks partial differential equations two-stage learning scientific computing

来源：评论

学校读者我要写书评

暂无评论

Optimal controller Design for Non-Affine Nonlinear Power systems with Static Var Compensators for Hybrid UAVs

引用

Tsinghua Science and Technology 2022年第1期27卷 196-206页

作者： Yanchu Li Qingqing Ding Shufang Li Stanimir Valtchev Beijing Key Laboratory of Network System Architecture and Convergence Beijing Laboratory of Advanced Information Networkand School of Information&Communication EngineeringBeijing University of Posts and TelecommunicationsBeijing 100876China State Key Laboratory of Control and Simulation of Power System and Generation Equipments Tsinghua UniversityBeijing 100084China the Nova School of Science and Technology(FCT/UNL) Caparica 2829-516LisbonPortugal Technical University of Sofia(TUS) Sofia 2125Bulgaria

A generalized non-affine nonlinear power system model is presented for a single machine bus power system with a Static Var Compensator(SVC)or State Var system(SVS)for hybrid Unmanned Aerial Vehicles(UAVs).The model is constructed by differential algebraic equations on the MATLAB-Simulink platform with the programming technique of its *** the inverse system method and the Linear Quadratic Regulation(LQR),an optimized SVC controller is *** simulations under three fault conditions show that the proposed controller can effectively improve the power system transient performance.

关键词： Static Var Compensator(SVC) Unmanned Aerial Vehicles(UAV) power system non-affine nonlinear control inverse system method Linear Quadratic Regulation(LQR)

来源：评论

学校读者我要写书评

暂无评论

Cooperative formation tracking for heterogeneous multi-UAVs with faulty sensors of leader measurement 43

Cooperative formation tracking for heterogeneous multi-UAVs ...

引用

43rd Chinese control Conference, CCC 2024

作者： Lv, Yan Gong, Xiao Yang, Ruohan Fang, Jiayue Miao, Shuo Feng, Zhichao Yu, Yue Beijing Institute of Control and Electronic Technology Key Laboratory of Information System and Technology Beijing100038 China Northwestern Polytechnical University School of Electronics and Information Xi'an710072 China The Rocket Force University of Engineering Xi'an710025 China

ISBN: (纸本)9789887581581

This paper focuses on cooperative formation tracking problem of heterogeneous leader-following multi-UAVs with faulty sensors where the faulty sensors of the followers can only measure the partial output of the leader. First, the kinematic models of heterogeneous multi-UAVs based on the individual speed response time constants are established. Then, by utilizing the output regulation method, a formation controller based on a distributed observer is proposed based on partial outputs obtained by the faulty sensors of the followers. It should be noted that the proposed controller can achieve formation tracking of UAVs with faulty sensors to the leader UAV. Finally, a simulation example is performed to check out the validation of the proposed methods. © 2024 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Joint Optimization of Privacy Protection and Resource Allocation for Vehicular Edge Networks

Joint Optimization of Privacy Protection and Resource Alloca...

引用

2023 IEEE/CIC International Conference on Communications in China, ICCC 2023

作者： Gao, Tianqi Tao, Hongfeng Ni, Yuanzhi Shi, Jun Jiang, Fengcheng Jiangnan University School of Internet of Things Engineering Wuxi214122 China Ministry of Education Key Laboratory of System Control and Information Processing Shanghai200240 China

ISBN: (纸本)9798350345384

In the last decade, the service of vehicular networks has benefited from the rapid development of advanced communication and computing technologies including edge computing. For vehicular network operators, it is valuable to study how to realize the accurate allocation of edge computing resource on the premise of protecting users' privacy. In this paper, we design a histogram publishing algorithm based on differential privacy. The algorithm first classifies tasks according to the characteristics of computing requests, then interferes categorized tasks and designs a shuffling algorithm based on Blum Blum Shub (BBS). Finally, the frequency histogram of computing resource is obtained by post-processing of the Expectation-Maximum (EM) algorithm. The simulation results verify the accuracy and superiority of the proposed histogram publishing algorithm by comparing it with the existing methods. © 2023 IEEE.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Vehicle Platoon control Based on information Exchanges in Internet of Vehicles 5th

Vehicle Platoon Control Based on Information Exchanges in ...

引用

5th Chinese Conference on Swarm Intelligence and Cooperative control, CCSICC 2021

作者： Gao, Tianqi Tian, Yuanxu Tao, Hongfeng Ni, Yuanzhi School of Internet of Things Engineering Jiangnan University Wuxi214122 China Key Laboratory of System Control and Information Processing Ministry of Education Shanghai200240 China

ISBN: (纸本)9789811939976

Vehicle platooning is an emerging application in transportation system, boosting safe and efficient traffic environment. Based on the vehicular wireless communication technology, the driving states of the neighboring vehicles can be obtained for accurate vehicle control. In this work, the vehicle platoon system is modeled considering random characteristics of vehicular wireless communications. The consensus-based platoon control strategy and the autoregressive filtering algorithm are designed for efficient and effective control under topology of predecessor following (PF) and predecessor leading following (PLF), respectively. The platoon control model and algorithms are implemented by Simulink, where the results verify the effectiveness of the proposed solutions. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Time series analysis

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Learning for Low-Light Image Enhancement by Pseudo Low-Light Image 16

Semi-Supervised Learning for Low-Light Image Enhancement by ...

引用

16th International Congress on Image and Signal processing, BioMedical Engineering and Informatics, CISP-BMEI 2023

作者： Xie, Shuo Ma, Yingjie Xu, Wei Qiu, Song Sun, Yifei East China Normal University School of Communication and Electronic Engineering China Ministry of Education Key Laboratory of System Control and Information Processing Shanghai200240 China

ISBN: (纸本)9798350330755

Building paired datasets in low-light enhancement entails significant cost and time, making such datasets precious commodities. Many researchers focus on how to enable models to learn more information from limited datasets. A prevalent strategy involves employing semi-supervised learning techniques to enhance model performance through additional unpaired images. However, one of the main challenges faced is the scarcity of a vast number of unpaired images from the same domain as the original low-light images. Consequently, we introduce a semi-supervised image enhancement method using pseudo-low-light images. Initially, we generate pseudo low-light images with less noise compared with the source domain image by the Signal-to-Noise Ratio prior and diffusion models. We then employ the Mean-Teacher network and the feature constraints of the pseudo-low-light images to realize low-light image enhancement. Comprehensive experimental results validate the efficacy of our approach on real-world datasets. © 2023 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Weed detection based on improved Yolov5 8

Weed detection based on improved Yolov5

引用

8th International Conference on Intelligent Computing and Signal processing, ICSP 2023

作者： Yu, ZiZheng Nie, ZiJun Hu, Yong Qi Yan, HuangBin Lou, LiJun Yin, Zhijian Yang, Zhen Jiangxi Science and Technology Normal University School of Communications and Electronics Nanchang China Key Laboratory of System Control and Information Processing Ministry of Education Shanghai China

ISBN: (纸本)9798350302455

The scale of grain production affects human life and development. With the continuous expansion of cultivated land, the reproductive ability of weeds to mutiply gradually increases, which affects the growth of crops. If weeds are not treated properly managed, they can also allow spread indiscriminately in the field and reduce crop yields. The growth ability of weeds is stronger than that of crops, and there are many types of weeds with a wide of species diversity. To solve the problem that the existing weed detection methods cannot detect and classify weeds accurately and quickly, a deep learning method based on improved Yolov5 was designed for weed detection. By replacing the 3 × 3 convolution with multi-head self-attention (MHSA) in the Yolov5's backbone, the accuracy of weed detection is improved. The experimental results show that the improved Yolov5 weed detection algorithm achieves 51.4% accuracy. Compared with the original Yolov5 model, the calculation amount is 3 points less than the original, and total time required is slightly shorter, which improves the accuracy of weed classification and positioning. © 2023 IEEE.

关键词： Crops

来源：评论

学校读者我要写书评

暂无评论

Augmented Reality Enabled Telepresence Framework for Intuitive Robotic Teleoperation

Augmented Reality Enabled Telepresence Framework for Intuiti...

引用

2023 IEEE International Conference on Robotics and Biomimetics, ROBIO 2023

作者： Xu, Zheng Lin, Zecai Liu, Huanghua Ren, Qingsong Gao, Anzhu Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education Institute of Medical Robotics and Department of Automation Shanghai200240 China

ISBN: (纸本)9798350325706

In terms of telepresence for robotic teleoperation, the existing remote surgery provides the patient's side real-time videos to remote operators. Its effectiveness is limited due to the lack of depth information, occlusion, and restricted viewing angles. To address it, this paper develops a robotic telepresence framework integrating augmented reality (AR) and 3D reconstruction technology, providing a 3D virtual patient's side environment for remote operators. The real scene of the patient's side is reconstructed by a monocular camera with a manipulator before the operation, and the manipulator is teleoperated by the operator at the remote's side. The manipulator's pose is fused into the classic SVO+REMODE algorithm to improve the reconstructed accuracy. On the remote's side, an AR head-mounted display (HMD) is deployed to provide telepresence for operators under a similar environment, and the reconstructed scene of the patient's side is registered to the remote room, from which the operator can see the whole scene of the patient body and surrounding objects. An ArUco cube is used to evaluate the superimposed error between virtual and real displays, and the effectiveness is validated in an experimental platform for remote surgery. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mn-based MXene with high lithium-ion storage capacity

引用

Nano Research 2024年第5期17卷 4181-4191页

作者： Yanyan Wu Dongqing Liu Xiaonan Wang Usman Ghani Muhammad Asim Mushtaq Jinfeng Yang Huarui Sun Panagiotis Tsiakaras Xingke Cai School of Science and Ministry of Industry and Information Technology Key Laboratory of Micro-Nano Optoelectronic Information System Harbin Institute of Technology ShenzhenShenzhen 5180552 China Collaborative Innovation Center of Extreme Optics Shanxi UniversityTaiyuan 030006China Institute for Advanced Study Shenzhen UniversityShenzhen 518060China College of Mechatronics and Control Engineering Shenzhen UniversityShenzhen 518060China Laboratory of Alternative Energy Conversion Systems Department of Mechanical EngineeringSchool of EngineeringUniversity of ThessalyPedion Areos 38834Greece

3d-transition metal(Fe,Co,Ni,and Mn)-based MXene materials have been predicted to demonstrate exceptional electrochemical performance because of their good electrical conductivity and the presence of metallic atoms with multiple charge ***,until now,there have been no reports on MXenes based on Fe,Co,Ni,and Mn,due to the lack of 3d-metal-layered ***,we successfully synthesized the first 3d-transition metal-based MXenes,Mn_(2)CT_(x) by exfoliating a layered precursor derived from the anti-perovskite bulk *** as-prepared Mn_(2)CT_(x) MXene nanosheets were employed as anode materials in lithium-ion batteries,which exhibited stable storage capacity of 764.7 mAh·g^(-1) at 0.5 C,placing its storage capacities at an upper-middle level compared with other reported MXene materials as well as other Mn-based anode ***,this study opens a new avenue for MXene research by synthesizing 3d-transition metal-based MXenes for electrochemical applications.

关键词： Mn_(3)GaC Mn_(2)CT_(x) MXenes lithium-ion battery anode materials negative fading capacity

来源：评论

学校读者我要写书评

暂无评论

Dynamic Template Update Mechanism for Visual Object Tracking 8

Dynamic Template Update Mechanism for Visual Object Tracking

引用

8th International Conference on Intelligent Computing and Signal processing, ICSP 2023

作者： Hu, YongQi Cai, ZhongWang Nie, ZiJun Yu, ZiZheng Cao, Ying Yin, Zhijian Yang, Zhen Jiangxi Science and Technology Normal University School of Communications and Electronics Nanchang China Ministry of Education Key Laboratory of System Control and Information Processing Shanghai China

ISBN: (纸本)9798350302455

Given the requirements for robust target classification and accurate target state estimation in visual tracking, SiamFC++ proposes a set of practical guidelines for designing high-performance general-purpose trackers by considering the special nature of visual tracking problems. Inspired by dynamic modules, We propose an empirical method for integrating a dynamic module into the image input, which is concatenated with the template module after feature maps are extracted by the backbone network. Since the position and shape of the object can change significantly within a video sequence, the added dynamic module can better focus on the target region of the feature map to obtain better similarity maps. Extensive experiments and comparisons demonstrate that our simple and effective method achieves reliable results on the benchmarks of LaSOT, TrackingNet, and GOT-10K and provides a significant speed advantage in real-time. © 2023 IEEE.

关键词： Computer vision

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：