检索结果-内蒙古大学图书馆

Performance evaluation of the particle swarm optimization algorithm to unambiguously estimate plasma parameters from incoherent scatter radar signals

引用

EARTH PLANETS AND SPACE 2020年第1期72卷 1-25页

作者： Martinez-Ledesma, Miguel Jaramillo Montoya, Francisco Univ Santiago Chile Phys Dept Av Ecuador 3493 Santiago Chile Univ Concepcion CePIA Dept Astron Av Esteban Iturra S-NCasilla 160-C Concepcion Chile Univ Chile Dept Elect Engn Av Tupper 2007 Santiago Chile

Simultaneously estimating plasma parameters of the ionosphere presents a problem for the incoherent scatter radar (ISR) technique at altitudes between similar to 130 and similar to 300 km. Different mixtures of ion concentrations and temperatures generate almost identical backscattered signals, hindering the discrimination between plasma parameters. This temperature-ion composition ambiguity problem is commonly solved either by using models of ionospheric parameters or by the addition of parameters determined from the plasma line of the radar. Some studies demonstrated that it is also possible to unambiguously estimate ISR signals with very low signal fluctuation using the most frequently used non-linear least squares (NLLS) fitting algorithm. In a previous study, the unambiguous estimation performance of the particle swarm optimization (PSO) algorithm was evaluated, outperforming the standard NLLS algorithm fitting signals with very small fluctuations. Nevertheless, this study considered a confined search range of plasma parameters assuming a priori knowledge of the behavior of the ion composition and signals with very large SNR obtained at the Arecibo Observatory, which are not commonly feasible at other ISR facilities worldwide. In the present study, we conduct Monte Carlo simulations of PSO fittings to evaluate the performance of this algorithm at different signal fluctuation levels. We also determine the effect of adding different combinations of parameters known from the plasma line, different search ranges, and internal configurations of PSO parameters. Results suggest that similar performances are obtained by PSO and NLLS algorithms, but PSO has much larger computational requirements. The PSO algorithm obtains much lower convergences when no a priori information is provided. The a priori knowledge of N-e and Te/Ti\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{

关键词： Temperature-ion composition ambiguity Ionospheric plasma parameters Incoherent scatter radar Monte Carlo simulation optimization algorithms Particle swarm optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Towards optimization Approaches in Smart Grid A Review 2

Towards Optimization Approaches in Smart Grid A Review

引用

2nd International Conference on Computing, Mathematics and Engineering Technologies (iCoMET)

作者： Malik, Sabeeh Ahmad Gondal, Taimoor Muzaffar Ahmad, Sadiq Adil, Muhammad Qureshi, Rizwan Natl Univ Sci & Technol Dept Elect Engn Islamabad Pakistan Super Coll Lahore Dept Elect Engn Lahore Pakistan COMSATS Univ Islamabad Dept Elect Engn Islamabad Pakistan City Univ Hong Kong Dept Elect Engn Kowloon Hong Kong Peoples R China

ISBN: (纸本)9781538695098

Smart grid is the advancement of conventional grid with the help of computational intelligence and networking abilities of various communication networks to develop sustainable, robust, efcient and resilient power grid. It is considered to be the next future grid, using bidirectional stream of electricity through communication module that provides an environment to change the behavior of consumer to prosumer, who can independently generate and manage import/export electrical energy in the local community. Smart grid provides adaptive, procient, self-healing and secure power system which allows the various stakeholders to exchange power through grid. For effective operation of smart grid, it is necessary to have secure interoperable and efcient communication network among the electronic gadgets used in smart grid as well as in consumers premises. Efcient communication and optimization schemes is required for the data exchange among the communication modules to optimize the power system. Our contribution includes the comparative analysis on various optimization techniques that can be used in smart grid for energy management. To address the challenges for the successful deployment of smart grid, we have enlisted major hurdles that could hamper the smart grid operation and control. We believe that this research article will be a useful to early stage researchers working in the energy optimization of smart grid.

关键词： Smart grid optimization algorithms Energy Management

来源：评论

学校读者我要写书评

暂无评论

optimization of P& PI controller parameters for variable speed drive systems using a flower pollination algorithm

引用

HELIYON 2020年第8期6卷 e04648页

作者： Nadweh, Safwan Khaddam, Ola Hayek, Ghassan Atieh, Bassam Alhelou, Hassan Haes Tishreen Univ Power Elect Engn Latakia Syria Manara Univ Mechatron Engn Latakia Syria

In this study, a novel flower pollination algorithm (FPA) has been suggested for optimal tuning of P and PI controllers included in a variable speed drive VSD system control circuit. In addition to the manual tuning of controllers' parameters, several optimization algorithms like GA, PSO, GWO have been used for controllers optimal tuning in different studies. In this study, the errors caused by grid side current harmonic distortion in the VSD system have been used depending on SPWM technique to generate switching signals for a four-quadrant chopper circuit that acts like a filter and compensates the harmonic content in the grid current and smooth ripples in both DC-link current and voltage. The studied drive system and control circuit have been modeled using Matlab/Simulink, then it was linked with the proposed algorithm and tested under different operation conditions. A hardware laboratory model has been built and tested in order to confirm the validity of this study. Comparing the proposed algorithm with other optimization algorithms shows that the suggested algorithm outperforms other algorithms in improving the time response of the VSD system, reducing total harmonic distortion THD of grid current, and reducing ripple factor PF.

关键词： Electrical engineering Energy Industrial engineering Computer-aided engineering Variable speed drive systems (VSDS) Four quadrant chopper Power quality Flower pollination algorithm (FPA) optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

A DESIGN FOR FOULING ORIENTED optimization OF AN HPT NOZZLE

A DESIGN FOR FOULING ORIENTED OPTIMIZATION OF AN HPT NOZZLE

引用

ASME Turbo Expo: Turbomachinery Technical Conference and Exposition

作者： Friso, R. Casari, N. Suman, A. Pinelli, M. Montomoli, Francesco Univ Ferrara Via Saragat 1 I-44122 Ferrara Italy Imperial Coll London UQLab Dept Aeronaut London SW7 2AZ England

ISBN: (纸本)9780791858585

Fouling and erosion are two problems that severely affect gas turbines. The shape of the blade, its roughness, and its structural stability can vary as a consequence of these phenomena. The outcomes of this occurrence can span from the efficiency reduction to the engine shut down according to the nature of the material ingested, to the concentration of contaminants in the air, the cleanliness of fuel and to the particular design of the machine. In this work, an axial turbine airfoil is modified according to the requirement of less sensibility to the phenomena above mentioned, utilizing an automatic optimization algorithm. An artificial neural network surrogate approach is used for searching the optimal shape, minimizing the computational cost of the entire process. The optimum design of the blade is therefore achieved, in order to reduce the effects of deposition on the performance. The methodology here proposed is fully general and it is applied to an HPT nozzle in the present analysis.

关键词： Nozzles optimization Design Blades Shapes Airfoils optimization algorithms Erosion Gas turbines Performance Turbines Artificial neural networks Machinery Fuels Engines Surface roughness Structural stability

来源：评论

学校读者我要写书评

暂无评论

Derivative-Free optimization of Neural Networks using Local Search 10

Derivative-Free Optimization of Neural Networks using Local ...

引用

IEEE 10th Annual Ubiquitous Computing, Electronics and Mobile Communication Conference (UEMCON)

作者： Aly, Ahmed Guadagni, Gianluca Dugan, Joanne B. Univ Virginia Comp Engn Program Charlottesville VA 22903 USA Univ Virginia Appl Math Program Charlottesville VA USA

ISBN: (纸本)9781728138855

Deep Neural Networks have received a great deal of attention in the past few years. Applications of Deep Learning broached areas of different domains such as Reinforcement Learning and Computer Vision. Despite their popularity and success, training neural networks can be a challenging process. This paper presents a study on derivative-free, single-candidate optimization of neural networks using Local Search (LS). LS is an algorithm where constrained noise is iteratively applied to subsets of the search space. It is coupled with a Score Decay mechanism to enhance performance. LS is a subsidiary of the Random Search family. Experiments were conducted using a setup that is both suitable for an introduction of the algorithm and representative of modern deep learning tasks, based on the FashionMNIST dataset. Training of a 5-Million parameter CNN was done in several scenarios, including Stochastic Gradient Descent (SGD) coupled with Backpropagation (BP) for comparison. Results reveal that although LS was not competitive in terms of convergence speed, it was actually able to converge to a lower loss than SGD. In addition, LS trained the CNN using Accuracy rather than Loss as a learning signal, though to a lower performance. In conclusion, LS presents a viable alternative in cases where SGD fails or is not suitable. The simplicity of LS can make it attractive to non-experts who would want to try neural nets for the first-time or on novel, non-differentiable tasks.

关键词： Deep Neural Networks optimization algorithms Machine Learning Deep Learning Fashion MNIST Convolutional Neural Networks Non-differentiable Tasks

来源：评论

学校读者我要写书评

暂无评论

ADJOINT-BASED MULTIDISCIPLINARY, MULTIPOINT optimization OF A RADIAL TURBINE CONSIDERING AERODYNAMIC AND STRUCTURAL PERFORMANCES

ADJOINT-BASED MULTIDISCIPLINARY, MULTIPOINT OPTIMIZATION OF ...

引用

ASME Turbo Expo: Turbomachinery Technical Conference and Exposition

作者： Mueller, Lasse Verstraete, Tom Schwalbach, Marc von Karman Inst Fluid Dynam Turbomachinery & Prop Dept B-1640 Rhode St Genese Belgium

ISBN: (纸本)9780791858585

This paper presents a multidisciplinary adjoint-based design optimization of a turbocharger radial turbine for automotive applications. The aim is to improve the total-to-static efficiency of the turbine while keeping mechanical stresses below a predefined limit. The search for the optimal design is accomplished using an efficient Sequential Quadratic Programming algorithm considering additional aerodynamic and manufacturing constraints. The aerodynamic performance of the wheel is evaluated by a Reynolds-Averaged Navier-Stokes solver, whereas the maximum stresses in the material are predicted by a Finite Element Analysis tool. The design gradients required by the optimizer are computed with the adjoint approach which provides sensitivity information largely independent of the number of design variables. The results presented in this paper show the clear need to take into account mechanical stresses during optimization, as they are the most restrictive design limitation. However, the gradient-based optimization algorithm is able to effectively keep the stress levels below the critical value while significantly improving the turbine efficiency in a few design cycles.

关键词： optimization Turbines Design Stress Turbochargers algorithms Automotive industry Cycles optimization algorithms Quadratic programming Wheels Finite element analysis Manufacturing

来源：评论

学校读者我要写书评

暂无评论

Surrogate model based optimization of constrained mixed variable problems: application to the design of a launch vehicle thrust frame

Surrogate model based optimization of constrained mixed vari...

引用

AIAA Science and Technology (SciTech) Forum and Exposition

作者： Pelamatti, Julien Brevault, Loic Balesdent, Mathieu Talbi, El-Ghazali Guerin, Yannick Univ Paris Saclay Univ Lille Direct Lanceurs CNESONERA DTIS Gif Sur Yvette France Univ Paris Saclay ONERA DTIS F-91123 Palaiseau France Univ Lille Polytech Lille CNRS CRIStAL Inria Lille Nord Europe F-59650 Villeneuve Dascq France CNES Direct Lanceurs F-75612 Paris France

ISBN: (数字)9781624105784

ISBN: (纸本)9781624105784

Within the framework of complex systems design, such as launch vehicles, numerical optimization is an essential tool as it allows to reduce the design process time and costs. The inclusion of discrete variables in the design optimization process allows to extend the applicability of numerical optimization methods to a broader number of systems and sub-systems. In this paper, a recently proposed adaptation of the Efficient Global optimization method for constrained mixed-variable problems is applied to the design optimization of a launch vehicle thrust frame, which depends on both continuous sizing parameters and discrete variables characterizing the number of structural reinforcements. The Efficient Global optimization adaptation that is considered is based on a redefinition of the Gaussian Process kernel as a product between a standard continuous kernel and a second kernel representing the covariance between the discrete variable values. From the results obtained on an analytical test-case as well as on the launch vehicle thrust frame design optimization, it is shown that the use of the mixed variable Efficient Global optimization algorithm allows to converge towards the neighborhoods of the problems optima with fewer function evaluations when compared to reference optimization algorithms.

关键词： discrete transforms launch vehicle Optimal design optimization algorithms optimization Procedure thrust Function evaluation redefinition Frame Global optimization optimization methods Complex systems Covariance

来源：评论

学校读者我要写书评

暂无评论

Beyond "To Act or Not to Act": Fast Lagrangian Approaches to General Multi-Action Restless Bandits 21

Beyond "To Act or Not to Act": Fast Lagrangian Approaches to...

引用

International Conference on Autonomous Agents and Multiagent Systems

作者： Jackson A. Killian Andrew Perrault Milind Tambe Harvard University

ISBN: (纸本)9781713832621

This paper presents new algorithms and theoretical results for solutions to Multi-action Multi-armed Restless Bandits, an important but insufficiently studied generalization of traditional Multi-armed Restless Bandits (MARBs). Though MARBs are popular for modeling many problems, they are restricted to binary actions, i.e., "to act or not to act". This renders them unable to capture critical complexities faced by planners in real domains, such as a system manager balancing maintenance, repair, and job scheduling, or a health worker deciding among treatments for a given patient. Limited previous work on Multi-action MARBs has only been specialized to sub-problems. Here we derive multiple algorithms for use on general Multi-action MARBs using Lagrangian relaxation techniques, leading to the following contributions: (i) We develop BLam, a bound optimization algorithm which leverages problem convexity to quickly and provably converge to the well-performing Lagrange policy; (ii) We develop SampleLam, a fast sampling technique for estimating the Lagrange policy, and derive a concentration bound to investigate its convergence properties; (iii) We derive best and worst case computational complexities for our algorithms as well as our main competitor; (iv) We provide experimental results comparing our algorithms to baselines on simulated distributions, including one motivated by a real-world community health intervention task. Our approach achieves significant, up to ten-fold speedups over more general methods without sacrificing performance and is widely applicable across general Multi-action MARBs. Code is available at https://***/killian-34/MAMARB-Lagrange-Policies.

关键词： Multi-action restless bandits Lagrangian relaxation Bound optimization Markov decision process Markov chain Psychomotor Agitation algorithms manager Not Lagrangian BASELINE optimization algorithms Lagrange

来源：评论

学校读者我要写书评

暂无评论

Review of transmission planning and scaling of renewable energy in energy communities

引用

Renewable and Sustainable Energy Reviews 2025年 222卷

作者： Kivanc Basaran Máté János Lőrincz Mohammad Hosein Alaei Renata Rodrigues Lautert Pierluigi Siano Mohsen Kia Göksu Görel Manisa Celal Bayar University Department of Electrical Engineering Manisa Turkey University of Reading School of the Built Environment UK Power System Studies Department Behrad Consulting Engineers Isfahan Iran Otto von Guericke University Institute of Electric Power Systems Magdeburg Germany Federal University of Santa Maria Center for Excellence in Energy and Power Systems Santa Maria Brazil University of Salerno Department of Management & Innovation Systems Via Giovanni Paolo II 132 Fisciano SA 84084 Italy Department of Electrical and Electronic Engineering Science University of Johannesburg Johannesburg 2006 South Africa School of Electrical & Electronic Engineering University College Dublin Dublin Ireland

This study explores renewable energy scaling in energy communities and transmission expansion planning (TEP). The increasing share of renewables creates challenges in transmitting wind and solar power from remote areas to cities. These challenges necessitate the modernization of conventional transmission systems. Energy communities, which focus on decentralized production and consumption, have the potential to mitigate these challenges by optimizing local energy flows. The primary objective of this study is to identify optimal strategies for the integration of renewable energy in energy communities and to assess the expansion of transmission infrastructure required to support this integration. A systematic literature review was conducted, encompassing articles published between 2009 and 2024 in this study. The review was based on searches across leading academic databases, including SCOPUS, ELSEVIER Science Direct, SpringerLink, and Google Scholar. A total of 1509 studies were initially identified, of which 266 articles were selected for detailed analysis. The findings indicate that energy communities play a pivotal role in facilitating the integration of renewable energy and enhancing grid resilience. However, the results also highlight that the efficiency of this integration can be significantly improved through advanced planning methodologies and supportive regulatory frameworks. While energy communities reduce the need for long-distance transmission through local generation, the expansion of transmission infrastructure remains essential during periods of high demand or low local generation. These results provide valuable insights into the development of future energy infrastructure policies and underscore the need for a more flexible and decentralized approach to transmission network expansion.

关键词： Energy community optimization algorithms Renewable energy scaling Scaling of renewable energy Smart grids Transmission expansion

来源：评论

学校读者我要写书评

暂无评论

From traditional to deep learning methods for skin lesion segmentation: A literature review

Scientific African

引用

Scientific African 2025年 29卷

作者： Abdelkrim Hammimou Hassan Ezzahori Abdelghani Boudaoud Mounaim Aqil Engineering and Applied Physics Team Superior School of Technology Sultan Moulay Slimane University Beni Mellal Morocco

Due to their similarity, skin lesions are challenging for early and precise diagnosis, and segmenting them manually is a laborious and time-consuming task. Therefore, several methods, including traditional and artificial intelligence methods, have been proposed for segmenting the skin lesions automatically. The majority of recent reviews, however, have overlooked the traditional methods and instead only briefly discussed their advantages and disadvantages. Consequently, this review aims to provide a thorough overview of this field and offer insights about the role and performance of the traditional methods in the era of artificial intelligence. We collected 128 peer-reviewed and high-quality publications using inclusion and exclusion criteria. These publications have been selected from four well-known databases, IEEE Xplore, ScienceDirect, Springer, and MDPI, and classified systematically into three categories: traditional, artificial intelligence, and hybrid methods. The main contributions of this paper are: (1) Exploring the most used traditional methods and performance enhancement techniques. (2) Providing the State of the art of the convolutional neural network and deep learning methods. (3) Highlighting the role of traditional methods in hybrid frameworks. (4) Providing an extensive performance analysis and discussing the computational cost and real-world applicability challenges associated with segmentation methods. The results highlight the superiority of deep learning methods over traditional methods, while also recognizing the relevance of traditional methods like Active contours and clustering as trusted tools for skin lesion segmentation. These methods benefit from improvements such as ensembling techniques and optimization algorithms. Additionally, 9% of reviewed papers were motivated by the combination of benefits from traditional methods and deep learning methods to develop more robust models. In conclusion, significant challenges remain in developing

关键词： Skin lesion segmentation Automatic segmentation Traditional methods Convolutional neural network Deep Learning Ensembling methods optimization algorithms Hybrid frameworks ABCDE Asymmetry, Border, Color, Diameter, and Evolution method AC Active contour ACC Accuracy ACO Ant colony optimization algorithm AI Artificial intelligence AK Actinic keratosis BCC Basal cell carcinoma BUZOA Buzzards optimization algorithm CAD Computer aided diagnosis CNN Convolutional neural network COVIDOA Coronavirus optimization algorithm CPU Central Processing Unit CST Color space transformation DC Dice coefficient DF Dermatofibroma FCM Fuzzy c-means FLOP Floating-point operation FN False negative FP False positive FPS Frames per second FRCN Full-resolution convolution network GA Genetic algorithm GAN Generative adversarial networks GPU Graphical processing unit IoU Intersection over union IPO interior-point optimization JI Jaccard index KM K-means MAC Multiply-accumulate operation Mel Melanoma Nev Nevus PM Performance metric PSO Particle swarm optimization ROI Region of interest SCC Squamous cell carcinoma SENS Sensitivity SFS Stochastic fractal search SGO Social group optimization SIFT Scale-invariant feature transform SK Seborrheic keratosis SLC Skin lesion classification SLS Skin lesion segmentation SLIC Simple linear iterative clustering SPEC Specificity SSL Self supervised learning Swin-transformer Shifted window-based vision transformers TN True negative TP True positive WOA Whale optimization algorithm

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：