检索结果-内蒙古大学图书馆

Aerodynamic Effects Compensation on Multi-Rotor UAVs Based on a Neural Network Control Allocation Approach

IEEE/CAA Journal of Automatica Sinica 2022年第2期9卷 295-312页

作者： Sarah P.Madruga Augusto H.B.M.Tavares Saulo O.D.Luiz Tiago P.do Nascimento Antonio Marcus N.Lima Graduate Program of Electrical Engineering Universidade Federal de Campina GrandeCampina Grande-PBBrazil Department of Electrical Engineering Universidade Federal de Campina GrandeCampina Grande-PBBrazil IEEE Department of Computer Systems Universidade Federal da ParaibaJoao Pessoa-PBBrazil

This paper shows that the aerodynamic effects can be compensated in a quadrotor system by means of a control allocation approach using neural ***,the system performance can be improved by replacing the classic allocation matrix,without using the aerodynamic inflow equations *** network training is performed offline,which requires low computational *** target system is a Parrot MAMBO drone whose flight control is composed of PD-PID controllers followed by the proposed neural network control allocation *** a quadrotor is particularly susceptible to the aerodynamics effects of interest to this work,because of its small *** compared the mechanical torques commanded by the flight controller,i.e.,the control input,to those actually generated by the actuators and established at the *** was observed that the proposed neural network was able to closely match them,while the classic allocation matrix could not achieve *** allocation error was also determined in both ***,the closed-loop performance also improved with the use of the proposed neural network control allocation,as well as the quality of the thrust and torque signals,in which we perceived a much less noisy behavior.

关键词： Aerodynamics effects control allocation minidrone multi-rotor UAV neural networks

来源：评论

学校读者我要写书评

暂无评论

AI-Enabled Smart Hybrid Energy Optimization Management System for Green Hydrogen-Based Islanded Microgrids 6

AI-Enabled Smart Hybrid Energy Optimization Management Syste...

引用

6th IEEE Novel Intelligent and Leading Emerging Sciences Conference, NILES 2024

作者： Mohamed, Noor El-Deen M. El Zoghby, Helmy M. Abdelhakam, Mostafa M. Elmesalawy, Mahmoud M. Helwan University Faculty of Engineering Computer and Systems Engineering Department Cairo Egypt Helwan University Department of Electrical Power and Machines Engineering Cairo Egypt Helwan University Faculty of Engineering Electronics and Communications Engineering Department Cairo Egypt

ISBN: (纸本)9798350378511

Renewable hybrid energy systems are crucial for ensuring energy sustainability. This work presents an advanced control and management system for green hydrogen production, leveraging artificial intelligence (AI) and Internet of Things (IoT) technologies. The system optimizes renewable energy utilization, improves hydrogen production efficiency, and ensures a reliable energy supply to meet varying demands. AI algorithms are used, including Random Forest, Artificial Neural Networks (ANN) and Long Short-Term Memory (LSTM) networks to forecast photovoltaic (PV) energy production and load consumption. These models are integrated into a centralized control system that dynamically adjusts energy distribution between immediate consumption and hydrogen production. Using data from the Rye microgrid, the system's effectiveness is demonstrated in enhancing decision-making for energy management in small-scale islanded operations. © 2024 IEEE.

关键词： Clean energy

来源：评论

学校读者我要写书评

暂无评论

Evolutionary Optimization Methods for High-Dimensional Expensive Problems:A Survey

引用

IEEE/CAA Journal of Automatica Sinica 2024年第5期11卷 1092-1105页

作者： MengChu Zhou Meiji Cui Dian Xu Shuwei Zhu Ziyan Zhao Abdullah Abusorrah Department of Electrical and Computer Engineering New Jersey Institute of TechnologyNewarkNJ 07102 USA School of Information and Electronic Engineering Zhejiang Gongshang UniversityHangzhou 310018China School of Intelligent Manufacturing Nanjing University of Science and TechnologyNanjing 210094China Institute of Systems Engineering Macao University of Science and TechnologyMacao 999078China School of Artificial Intelligence and Computer Jiangnan UniversityWuxi 214122China School of Information Science and Engineering Northeastern UniversityShenyang 110819China Center of Research Excellence in Renewable Energy and Power Systems Department of Electrical and Computer EngineeringFaculty of EngineeringKing Abdulaziz UniversityJeddah 21589Saudi Arabia K.A.CARE Energy Research and Innovation Center King Abdulaziz UniversityJeddah 21589Saudi Arabia

Evolutionary computation is a rapidly evolving field and the related algorithms have been successfully used to solve various real-world optimization *** past decade has also witnessed their fast progress to solve a class of challenging optimization problems called high-dimensional expensive problems(HEPs).The evaluation of their objective fitness requires expensive resource due to their use of time-consuming physical experiments or computer ***,it is hard to traverse the huge search space within reasonable resource as problem dimension *** evolutionary algorithms(EAs)tend to fail to solve HEPs competently because they need to conduct many such expensive evaluations before achieving satisfactory *** reduce such evaluations,many novel surrogate-assisted algorithms emerge to cope with HEPs in recent *** there lacks a thorough review of the state of the art in this specific and important *** paper provides a comprehensive survey of these evolutionary algorithms for *** start with a brief introduction to the research status and the basic concepts of ***,we present surrogate-assisted evolutionary algorithms for HEPs from four main *** also give comparative results of some representative algorithms and application ***,we indicate open challenges and several promising directions to advance the progress in evolutionary optimization algorithms for HEPs.

关键词： computer optimization evolutionary

来源：评论

学校读者我要写书评

暂无评论

Next Generation Memristor Reservoir Computing 3

Next Generation Memristor Reservoir Computing

引用

3rd IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural engineering, MetroXRAINE 2024

作者： Nikiruy, K. Ivanov, T. Ziegler, M. Rossetti, D. Corinto, F. Ascoli, A. Tetzlaff, R. Demirkol, A.S. Schmitt, N. Micro-and Nanoelectronic Systems Tu Ilmenau Department of Electrical Engineering and Information Technology Ilmenau Germany Turin Italy Institute of Circuits and Systems Tu Dresden Faculty of Electrical and Computer Engineering Dresden Germany

ISBN: (纸本)9798350378009

The nonlinear transformation used in reservoir computing can be effectively replaced by nonlinear vector autoregression (NVAR) for data prediction. In such a method, also known as next generation reservoir computing (NGRC), the input signal consists of a linear part, including several previous data points, and their nonlinear combinations. Here we show that the application of this method to a network with memristive weights (memristors) can be used to predict signals, depending on the nature of the nonlinear functions and the number of memristors. The network allows an accurate prediction of chaotic time series of Mackey-Glass and Duffing oscillators. © 2024 IEEE.

关键词： Memristors

来源：评论

学校读者我要写书评

暂无评论

Transformer Protection Strategy During Solar Storm: Threat Analysis and Implementing Countermeasures 10

Transformer Protection Strategy During Solar Storm: Threat A...

引用

10th IEEE International Conference on Power systems, ICPS 2023

作者： Ahmed, Meraj Qadir, Aktab Qadir, Akdas Khan, Shakil Haque, Mehedi Haque, S.M Anowarul Mymensingh Engineering College Department of Electrical and Electronic Engineering Mymensingh2200 Bangladesh Universiti Kebangsaan Malaysia Electronic and Systems Engineering Faculty of Engineering and Built Environment Department of Electrical Malaysia

ISBN: (纸本)9798350318739

Geomagnetic fluctuations have the potential to generate geomagnetically induced currents (GICs) within power transformers, which can result in equipment breakdown and power interruptions. The current investigation involves developing and experimenting with an RLC device to prevent geomagnetically induced currents (GICs) within the neutral part of a transformer. The device is designed to be compatible with the frequency range of geomagnetically induced currents (GICs) and the impedance characteristics of the transformer neutral. The outcomes indicate that the RLC apparatus effectively restricted geomagnetically induced currents (GICs) from accessing the transformer, safeguarding it against potential harm. The mentioned apparatus holds significant potential as a crucial constituent of a comprehensive GIC safeguarding mechanism for power transformers, thus offering consistent power transmission to end-users. MATLAB-SIMULINK simulates how the RLC device blocks GIC from entering the power transformer. © 2023 IEEE.

关键词： Power transformers

来源：评论

学校读者我要写书评

暂无评论

Weed Detection Based on Fine-Tuned YOLOv5 16

Weed Detection Based on Fine-Tuned YOLOv5

引用

16th International Conference on Information Technology and electrical engineering, ICITEE 2024

作者： Agustian, Indra Wibirama, Sunu Ardiyanto, Igi Anggraini, Ika Novia Noviansyah, Pariyanto Universitas Gadjah Mada Department of Electrical and Information Engineering Yogyakarta Indonesia Universitas Bengkulu Study Program of Electrical Engineering Bengkulu Indonesia Universitas Gadjah Mada Department of Electrical and Information Engineering Yogyakarta55281 Indonesia Universitas Gadjah Mada Department of Electrical and Information Engineerig Yogyakarta Indonesia

ISBN: (纸本)9798350375817

Conventional weed control often ignores weed locations, potentially causing land damage. AI-based weed detection offers a modern solution. Unfortunately, little attention has been paid to how an augmentation technique improves performance of AI-based weed detection. To address this research gap, we proposed a weed detection model based on fine-tuned YOLOv5 to detect weeds in corn fields aged 1 to 3 weeks. YOLOv5 offers computational benefits, includes auto-augmentation capabilities, and presents a more organized visualization of the outcomes from the training data. The primary dataset used in this study comprised 3,437 images with a total of 18,267 annotated objects, including corn plants and weeds. We observed the effect of mosaic augmentation on the dataset images based on auto-augmentation in YOLOv5. We found that mosaic augmentation with a 0.75 probability outperformed 0.5 and 1.0. The best mAP performance was at the level @0.5 with score of 0.776 for all classes. Meanwhile, the mAP@0.5:0.95 was 0.573 for all classes, indicating that the model's performance requires further improvement. Our study is promising as a guidance for future development of AI-based weed detection. © 2024 IEEE.

关键词： weed deep learning Weed detection weed-yolo yolov5

来源：评论

学校读者我要写书评

暂无评论

Non‐linearly conductive ZnO microvaristors/epoxy resin composite prepared by wet winding with polyester fibre cloth

引用

High Voltage 2022年第1期7卷 32-40页

作者： Zhikang Yuan Jun Hu Zhiwen Huang Gang Sun Ya Sun Jinliang He Department of Electrical Engineering State Key Laboratory of Power SystemsTsinghua UniversityBeijingChina

ZnO microvaristors/epoxy resin composite has drawn great attention from academia and industry for its adjustable non‐linear conductivity,high mechanical strength,and good ageing ***,the sedimentation of ZnO microvaristors in epoxy resin during preparation is the key problem,which limits its application in *** this study,a novel method of wet winding with polyester fibre cloth is proposed to prepare the ZnO microvaristors/epoxy resin *** anti‐settling effect of ZnO micro-varistors in the composite is verified by scanning electron microscopy(SEM)and thermal gravimetric analysis(TGA).The microstructure shows that ZnO microvaristors distribute uniformly in the composite,and the content difference of ZnO microvaristors at the top and bottom part is only 0.4%.The composite shows typical non‐linear conductivity,and the threshold electric field and the non‐linear coefficient decrease with the content of ZnO microvaristors,while the conductivity in the insulating state shows an increasing *** verify the field grading effect of the composite with non‐linear conductivity(CNC),a finite element model of a needle‐plate electrode,simulating the condition of a conductive tip in a solid insulated system,is set *** can adaptively grade the electric field,which reduces the surface electric field of the needle tip by 86.6%and the highest electric field in the system by 82.1%.This wet winding method solidifies the industrial application of CNC in high‐voltage power equipment.

关键词： composite resin winding

来源：评论

学校读者我要写书评

暂无评论

Comprehensive technical analysis of post-combustion carbon capture and storage based on monoethanolamine absorption for petrochemical industry in Indonesia

引用

Clean Energy 2024年第6期8卷 16-36页

作者： Muh Asyrofi Rahma Muthia Mohammad Akita Indianto Energy Systems Engineering Graduate Program Department of Interdisciplinary EngineeringFaculty of EngineeringUniversitas IndonesiaKampus Baru UI DepokDepokWest Java 16424Indonesia Department of Chemical Engineering Faculty of EngineeringUniversitas IndonesiaKampus Baru UI DepokDepokWest Java 16424Indonesia Sustainable Energy Systems and Policy Research Cluster Universitas IndonesiaKampus Baru UI DepokDepokWest Java 16424Indonesia Tropical Renewable Energy Center Faculty of EngineeringUniversitas IndonesiaKampus Baru UI DepokDepokWest Java 16424Indonesia

The implementation of carbon capture and storage in the petrochemical industry is one of the means of *** research focuses on a comprehensive technical analysis of the deployment of post-combustion carbon capture and storage based on monoethanolamine absorption in the petrochemical *** olefin complex petrochemical industry in Tuban,Indonesia,is the basis for the analysis,which includes a steam cracker,polyethylene,polypropylene,and raw pyrolysis gasoline hydrotreating units,with capacities of 1000,940,600,and 570 kilotons/year,*** total energy consumption is about 16024.53 GJ/h,and the CO_(2) emissions are about 1.6 megatons/*** on these plant systems,comprehensive technical analyses of the implementation of carbon capture and storage in that industry were performed using Aspen HYSYS®simulation *** analysis was carried out to determine the total CO_(2) captured,energy intensity,monoethanolamine consumption,and net CO_(2) captured in various scenarios based on the number of absorber column stages,absorption pressure,and desorption *** CO_(2) storage site is about 100 km away and is transported by an onshore pipeline with a supercritical phase of CO_(2).The optimal net CO_(2) capture value is achieved by setting up a 50-stage absorber column with a pressure of 1 barg and a temperature of 110℃ at the top of the desorber column,resulting in a CO_(2) capture yield of 86.4%and an energy intensity of 12.6 GJ/ton CO_(2).Under these conditions,the net CO_(2) captured in the scenario based on gas power plants’electricity is 0.225 megatons/year,while in the scenario based on gas power plants incorporating 30%biomass electricity,it is 0.544 megatons/*** increased use of renewable energy in carbon capture and storage facilities,more net CO_(2) is *** study can be applied to various cases of post-combustion carbon capture and storage implementation in the industrial sector,especially in the

关键词： carbon capture and storage petrochemical olefin monoethanolamine absorption pipeline injection energy intensity net captured CO_(2)

来源：评论

学校读者我要写书评

暂无评论

Efficiency Enhancement and Cost Reduction through Speed Optimization of Two-regime Generator Set with Three-stage Synchronous Alternator

引用

Chinese Journal of electrical engineering 2025年第1期11卷 194-205页

作者： Hassen Smail Mostafa Kamel Smail Abdelhak Goudjil Electrical Engineering Department University of Batna 2Batna 05078Algeria Aerospace Systems Department Institut Polytechnique des Sciences Avancées(IPSA)Ivry-sur-Seine 94200France Group of Electrical Engineering Paris(GeePs) UMR CNRS 8507Centrale SupélecUniversité Paris-SaclaySorbonne UniversityGif sur Yvette 91192France

Variable-speed generators(VSG)offer numerous benefits over fixed-speed *** advantages include significant fuel savings,reduced noise emissions,and extended engine ***,VSGs have a major drawback:their high manufacturing cost owing to the expensive permanent-magnet generators(PMGs)commonly used in these generators,as well as the large size of the power electronics section,which has the same power rating as the generator *** to reduce the initial investment cost by introducing a two-regime generator(TRG)is *** first mode operates at a constant speed for loads exceeding 50%,without the need for a *** second mode operates at variable speeds for loads below 50%using a converter that reduces its power by 50%,thus decreasing the investment ***,the cost can be further reduced by replacing the PMG with a brushless synchronous *** controller employed in thisstudy is a two-loop proportional-integral-derivative controllerthat exhibits favorable dynamics and compensates for dead times and parameter *** have shown a significant reduction in cost compared to VSGwhile retaining the advantages of the latter.

关键词： Variable-speed generators permanent-magnet generator two-regime generator PID controller

来源：评论

学校读者我要写书评

暂无评论

Simultaneous imposition of initial and boundary conditions via decoupled physics-informed neural networks for solving initialboundary value problems

引用

Applied Mathematics and Mechanics(English Edition) 2025年第4期46卷 763-780页

作者： K.A.LUONG M.A.WAHAB J.H.LEE Deep Learning Architecture Research Center Sejong UniversitySeoul05006Republic of Korea Soete Laboratory Department of Electrical EnergyMetalsMechanical Constructionsand SystemsFaculty of Engineering and ArchitectureGhent UniversityGent9000Belgium College of Engineering Yuan Ze UniversityTaoyuan32026TaiwanChina

Enforcing initial and boundary conditions(I/BCs)poses challenges in physics-informed neural networks(PINNs).Several PINN studies have gained significant achievements in developing techniques for imposing BCs in static problems;however,the simultaneous enforcement of I/BCs in dynamic problems remains *** overcome this limitation,a novel approach called decoupled physics-informed neural network(d PINN)is proposed in this *** d PINN operates based on the core idea of converting a partial differential equation(PDE)to a system of ordinary differential equations(ODEs)via the space-time decoupled *** this end,the latent solution is expressed in the form of a linear combination of approximation functions and coefficients,where approximation functions are admissible and coefficients are unknowns of time that must be ***,the system of ODEs is obtained by implementing the weighted-residual form of the original PDE over the spatial domain.A multi-network structure is used to parameterize the set of coefficient functions,and the loss function of d PINN is established based on minimizing the residuals of the gained *** this scheme,the decoupled formulation leads to the independent handling of I/***,the BCs are automatically satisfied based on suitable selections of admissible ***,the original ICs are replaced by the Galerkin form of the ICs concerning unknown coefficients,and the neural network(NN)outputs are modified to satisfy the gained *** benchmark problems involving different types of PDEs and I/BCs are used to demonstrate the superior performance of d PINN compared with regular PINN in terms of solution accuracy and computational cost.

关键词： decoupled physics-informed neural network(dPINN) decoupled formulation Galerkin method initial-boundary value problem(IBVP) machine learning

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：