检索结果-内蒙古大学图书馆

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Sun, Zexin Chen, Mingyu Baillieul, John Boston University Division of Systems Engineering United States Boston University Department of Electrical and Computer Engineering United States Boston University Division of Systems Engineering Departments of Mechanical Engineering Electrical and Computer Engineering BostonMA02215 United States

ISBN: (纸本)9798350316339

Nonlinear differential equations are encountered as models of fluid flow, spiking neurons, and many other systems of interest in the real world. Common features of these systems are that their behaviors are difficult to describe exactly and invariably unmodeled dynamics present challenges in making precise predictions. In this paper, we present a novel data-driven linear estimator based on Koopman operator theory to extract meaningful finite-dimensional representations of complex non-linear systems. The Koopman model is used together with deep reinforcement networks that learn the optimal stepwise actions to predict future states of nonlinear systems. Our estimator is also adaptive to a diffeomorphic transformation of the estimated nonlinear system, which enables it to compute optimal state estimates without re-learning. © 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

Permanent Magnet Temperature Estimation for PMSMs Using Virtual Position-offset Injection

引用

CES Transactions on electrical Machines and systems 2024年第1期8卷 51-60页

作者： Beichen Ding Yuting Lu Kaide Huang Guodong Feng Chunyan Lai IEEE the School of Intelligent Systems Engineering Sun Yat-sen UniversityShenzhen 518107China the Fosan University Foshan 528225China the Department of Electrical and Computer Engineering Concordia UniversityQCCanada

This paper proposes a virtual position-offset injection based permanent magnet temperature estimation approach for permanent magnet synchronous machines(PMSMs). The concept of virtual position-offset injection is mathematically transforming the machine model to a virtual frame with a position-offset. The virtual frame temperature estimation model is derived to calculate the permanent magnet temperature(PMT) directly from the measurements with computation efficiency. The estimation model involves a combined inductance term, which can simplify the establishment of saturation compensation model with less measurements. Moreover, resistance and inverter distorted terms are cancelled in the estimation model, which can improve the robustness to the winding temperature rise and inverter distortion. The proposed approach can achieve simplified computation in temperature estimation and reduced memory usage in saturation compensation. While existing model-based approaches could be affected by either the need of resistance and inverter information or complex saturation compensation. Experiments are conducted on the test machine to verify the proposed approach under various operating conditions.

关键词： PMSM Magnet temperature estimation Virtual position offset injection Inverter nonlinearity

来源：评论

学校读者我要写书评

暂无评论

Inverse kinematics solution for a six-degree-of-freedom upper limb rehabilitation robot using deep learning models

引用

Neural Computing and Applications 2025年 1-19页

作者： Shah, Muhammad Faizan Khan, Naveed Ahmad Jamwal, Prashant K. Chetty, Girija Goecke, Roland Hussain, Shahid School of Information Technology & Systems University of Canberra Canberra Australia Department of Electrical and Computer Engineering Nazarbayev University Astana Kazakhstan School of Systems and Computing University of New South Wales Canberra Australia

The inverse kinematics problem in serially manipulated upper limb rehabilitation robots implies the usage of the end-effector position to obtain the joint rotation angles. In contrast to the forward kinematics, there are no systematic approaches for solving the inverse kinematics problem. Furthermore, for some morphology of the upper limb rehabilitation robots, the inverse kinematics problem is particularly challenging to solve. Conventional methods to solve the inverse kinematics problem reported in the literature are computationally expensive. In the present work, we propose a deep learning-based model to acquire the joint angles for a given end-effector position. The proposed approach exhibits high efficacy in determining the joint angles for various target positions and can accurately predict the end-effector positions once trained, improving the ability of the upper limb rehabilitation robot to adapt to varying patient needs. Due to its improved capability and effectiveness to track positions, the proposed algorithm lays the foundation for the development of efficient controllers in future. © The Author(s) 2025.

关键词： Inverse kinematics

来源：评论

学校读者我要写书评

暂无评论

DASA: Delay-Adaptive Multi-Agent Stochastic Approximation 63

DASA: Delay-Adaptive Multi-Agent Stochastic Approximation

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Fabbro, Nicolo Dal Adibi, Arman Poor, H. Vincent Kulkarni, Sanjeev R. Mitra, Aritra Pappas, George J. University of Pennsylvania Electrical and Systems Engineering Department United States Princeton University Department of Electrical and Computer Engineering United States North Carolina State University Electrical and Computer Engineering Department United States

ISBN: (纸本)9798350316339

We consider a setting in which N agents aim to speedup a common Stochastic Approximation (SA) problem by acting in parallel and communicating with a central server. We assume that the up-link transmissions to the server are subject to asynchronous and potentially unbounded time-varying delays. To mitigate the effect of delays and stragglers while reaping the benefits of distributed computation, we propose DASA, a Delay-Adaptive algorithm for multi-agent Stochastic Approximation. We provide a finite-time analysis of DASA assuming that the agents' stochastic observation processes are independent Markov chains. Significantly advancing existing results, DASA is the first algorithm whose convergence rate depends only on the mixing time τm i x and on the average delay τa v g while jointly achieving an N-fold convergence speedup under Markovian sampling. Our work is relevant for various SA applications, including multi-agent and distributed temporal difference (TD) learning, Q-learning and stochastic optimization with correlated data. © 2024 IEEE.

关键词： Markov chains

来源：评论

学校读者我要写书评

暂无评论

Enhancing Renewable Energy Integration:A Gaussian-Bare-Bones Levy Cheetah Optimization Approach to Optimal Power Flow in electrical Networks

引用

computer Modeling in engineering & Sciences 2024年第8期140卷 1339-1370页

作者： Ali S.Alghamdi Mohamed A.Zohdy Saad Aldoihi Department of Electrical Engineering College of EngineeringMajmaah UniversityAl-Majmaah11952Saudi Arabia Electrical and Computer Engineering Department Oakland UniversityRochesterMI48309USA Institute of Earth and Space Science King Abdulaziz City for Science and Technology(KACST)Riyadh11442Saudi Arabia Computer Science and Systems Engineering Institute Polytechnique de ParisPalaiseau CedexFrance

In the contemporary era,the global expansion of electrical grids is propelled by various renewable energy sources(RESs).Efficient integration of stochastic RESs and optimal power flow(OPF)management are critical for network *** study introduces an innovative solution,the Gaussian Bare-Bones Levy Cheetah Optimizer(GBBLCO),addressing OPF challenges in power generation systems with stochastic *** primary objective is to minimize the total operating costs of RESs,considering four functions:overall operating costs,voltage deviation management,emissions reduction,voltage stability index(VSI)and power loss ***,a carbon tax is included in the objective function to reduce carbon *** scrutiny,using modified IEEE 30-bus and IEEE 118-bus systems,validates GBBLCO’s superior performance in achieving optimal *** results demonstrate GBBLCO’s efficacy in six optimization scenarios:total cost with valve point effects,total cost with emission and carbon tax,total cost with prohibited operating zones,active power loss optimization,voltage deviation optimization and enhancing voltage stability index(VSI).GBBLCO outperforms conventional techniques in each scenario,showcasing rapid convergence and superior solution ***,GBBLCO navigates complexities introduced by valve point effects,adapts to environmental constraints,optimizes costs while considering prohibited operating zones,minimizes active power losses,and optimizes voltage deviation by enhancing the voltage stability index(VSI)*** research significantly contributes to advancing OPF,emphasizing GBBLCO’s improved global search capabilities and ability to address challenges related to local *** emerges as a versatile and robust optimization tool for diverse challenges in power systems,offering a promising solution for the evolving needs of renewable energy-integrated power grids.

关键词： Renewable energy integration optimal power flow stochastic renewable energy sources gaussian-bare-bones levy cheetah optimizer electrical network optimization carbon tax optimization

来源：评论

学校读者我要写书评

暂无评论

A ROS-2 based Path Planning and Maze Solving of Autonomous Robots

A ROS-2 based Path Planning and Maze Solving of Autonomous R...

引用

2024 International Conference on Advances in Computing, Communication, electrical, and Smart systems, iCACCESS 2024

作者： Nuhel, Ahsan Kabir Hossain, Sazzad Hassan, Md.Tonim Haider, Iftekhar Saha, Ankur Taha, Adnan Sabith Ony, Asma-UI Husna Electrical and Electronics Engineering Bangladesh University of Hertfordshire Computer Networks and Systems Security United Kingdom Electrical and Electronics Engineering Bangladesh Computer Science and Engineering Bangladesh University of Information Technology and Sciences Computer Science and Engineering Bangladesh

ISBN: (纸本)9798350350289

The goal of this study is to build a self-driving robot that can effectively navigate mazes by utilizing sophisticated computer vision algorithms with ROS2. Fusion 360 is used to create the robot model, and ROS2 launch files are used to initialize the sensor and control nodes. Attaining optimal path planning and accurate localization are the main objectives. The combination of novel motion planning based on the orientation of the robot with graph search algorithms like DFS, A∗, and Dijkstra's leads to effective maze discovery and traversal. Thorough testing shows that the system can successfully navigate unfamiliar maze configurations, demonstrating the dependability of ROS2 and modern robotics techniques. By completing this study, a foundation for future advancements in perception and planning to manage more complex settings is laid. © 2024 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Latent Variable and Classification Performance Analysis of Bird-Drone Spectrograms with Elementary Autoencoder

IEEE Transactions on Radar Systems

引用

IEEE Transactions on Radar systems 2024年 3卷 115-123页

作者： White, Daniel Jahangir, Mohammed Mishra, Amit Kumar Baker, Chris J. Antoniou, Michail University Of Birmingham School Of Electrical Electronic And Systems Engineering United Kingdom Aberystwyth University Department Of Computer Science United Kingdom

Deep learning with convolutional neural networks has been widely utilised in radar research concerning automatic target recognition. Maximising numerical metrics to gauge the performance of such algorithms does not necessarily correspond to model robustness against untested targets, nor does it lead to improved model interpretability. Approaches designed to explain the mechanisms behind the operation of a classifier on radar data are proliferating, but bring with them a significant computational and analysis overhead. This work uses an elementary unsupervised convolutional autoencoder (CAE) to learn a compressed representation of a challenging dataset of urban bird and drone targets and subsequently if apparent quality of the representation via preservation of class labels leads to better classification performance after a separate supervised training stage. It is shown that a CAE that reduces the features output after each layer of the encoder gives rise to the best drone vs bird classifier. A clear connection between unsupervised evaluation via label preservation in the latent space and subsequent classification accuracy after supervised fine-tuning is shown, supporting further efforts to optimise radar data latent representations to enable optimal performance and model interpretability. © 2023 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Polarimetric Image Fusion Strategies for Improving Target Shape and Contrast in Remote Sensing Applications 21

Polarimetric Image Fusion Strategies for Improving Target Sh...

引用

Electro-Optical and Infrared systems: Technology and Applications XXI 2024

作者： Ratliff, Bradley M. Tyo, J. Scott Taylor, Michael Prikkel, Connor Dept. Electrical & Computer Engineering Dayton University DaytonOH United States Electrical & Computer Systems Engineering Dept. Monash University Melbourne Australia

ISBN: (纸本)9781510681088

Images from passive imaging polarimeters are often displayed in terms of their intensity (s0), degree of linear polarization (DoLP), and angle of polarization (AOP). The AOP and DoLP together generally provide information about shape and surface quality of imaged objects;however, the information conveyed in these images are often difficult to interpret, especially to an analyst unfamiliar with polarization phenomenology. Furthermore, it can be challenging to train machine learning approaches with direct polarimetric information due to the limited availability of application-specific data. Augmenting s0 images with polarimetric information in the form of contrast and shape enhancement thus allows for the data to remain in the domain of traditional EO-IR intensity imagery that is more familiar for both humans and trained networks. In this work we explore several strategies for effectively fusing polarimetric information into s0 imagery to improve target shape and contrast for both human and algorithmic consumption, with a particular focus on remote sensing and target detection applications. © 2024 SPIE.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

Broadband single-polarization single-mode low confinement loss hollow core anti-resonant fiber with semi-elliptical nested tube

引用

Optical and Quantum Electronics 2025年第4期57卷 1-12页

作者： Lin, Wen Fei, Yihong Wang, Ning Jia, Hongzhi Engineering Research Center of Optical Instruments and Systems Ministry of Education Shanghai Key Laboratory of Modern Optical Systems School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai200093 China

In this paper, a hollow-core anti-resonant optical fibre containing a semi-elliptical nested tube is proposed, which has the characteristics of single-polarization, large bandwidth, single-mode and low confinement loss. By optimizing the structural design, the polarization extinction ratio (PER) of the fiber reaches 21,0183 at a wavelength of 1.55 μm, and the y-polarized fundamental mode loss is only 0.00086 dB/m. By changing the material and thickness of the semi-ellipsoidal nested tube, a large bandwidth of 280 nm was achieved in the wavelength range of 1.51-1.78 μm, with loss limited to less than 0.001 dB/m within the bandwidth range. The PER and higher-order mode extinction ratio of 4870, 1487, respectively. The loss remains below 0.01 dB/m when the bending radius exceeds 4.5 cm. Therefore, it is expected that this optical fiber can be used in optical devices such as fiber optic sensors, fiber optic lasers and fiber optic gyroscopes. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Single mode fibers

来源：评论

学校读者我要写书评

暂无评论

Towards Green AI by Reducing Training Effort of Recurrent Neural Networks Using Hyper-Parameter Optimization with Dynamic Stopping Criteria 22

Towards Green AI by Reducing Training Effort of Recurrent Ne...

引用

22nd IEEE International Symposium on Intelligent systems and Informatics, SISY 2024

作者： Podgorelec, Vili Fister, Iztok Vrbancic, Grega University of Maribor Intelligent Systems Laboratory Faculty of Electrical Engineering and Computer Science Slovenia

ISBN: (纸本)9798350385601

Neural networks have become a leading model in modern machine learning, able to model even the most complex data. For them to be properly trained, however, a lot of computational resources are required. With the carbon footprint of ever-growing adoption of neural networks in mind, an approach to reduce the required training resources would be very welcome. We designed a new training effort reduction method based on the calculation of area under the normalized loss curve and assessed it on the electricity consumption forecasting problem with the recurrent neural networks. The results show that the proposed method was able to considerably reduce the amount of computational resources, while maintaining the predictive performance, and thus contributing towards the Green AI. © 2024 IEEE.

关键词： Green AI hyper-parameter optimization machine learning neural networks resource optimization

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：