检索结果-内蒙古大学图书馆

Desenvolvimento de metodologia para diagnóstico de falhas incipientes em transformadores de potência utilizando análise de gases e aprendizado de máquina

Desenvolvimento de metodologia para diagnóstico de falhas i...

引用

作者： Ikeshoji, Marco Akio Universidade Estadual Paulista

O transformador de potência é um elemento essencial para funcionamento e estabilidade do sistema elétrico. Sua saída repentina de operação por falha, ocasiona desde transtornos sociais, a prejuízos financeiros proporcionais ao tempo de atendimento e correção da interrupção no fornecimento de energia. Descobrir de modo incipiente falhas em transformadores, além de evitar esses problemas, contribui para o aumento da segurança e confiabilidade do sistema elétrico. Nesse contexto, esta tese apresenta uma metodologia que emprega os algoritmos Floresta de Caminhos Ótimos e K Vizinhos mais Próximos para auxílio na gestão da manutenção desses equipamentos que, diferentemente dos métodos convencionais e inteligentes de análise de gases que apenas classificam padrões, utilizam uma nova abordagem no diagnóstico de falhas com uso dos registros (recentes e históricos) de análises dos gases dissolvidos no óleo, tornando o método mais informativo, uma vez que permite observar a evolução dos eventos e distinguir tendências de falhas. Assim, diferentes estratégias e ações programadas de manutenção podem ser elaboradas, reduzindo-se o risco de interrupções de energia repentinas e suas consequências. Portanto, este trabalho inicialmente revê os custos estimados nos casos de falhas, apresenta as estatísticas dos tipos e localizações delas, as características básicas do sistema isolante e como os gases são gerados devido aos estresses térmicos e elétricos. Em seguida são apresentadas as técnicas normatizadas (convencionais) e inteligentes de classificações empregadas na análise de falhas com gases dissolvidos, algumas técnicas de otimização e de seleção de atributos, e uma proposta alternativa de diagnóstico de falhas. Posteriormente, é mostrado um método de geração de dados sintéticos baseado em incertezas de medições, segundo a IEC, para o caso de dados escassos, bem como são feitas simulações e análises com dados reais da concessionária de energia para validar a metodologia proposta,

关键词： Transformadores de potência Análise de gases dissolvidos Aprendizado de máquina Algoritmos Inteligentes Diagnóstico de falhas Power transformers Dissolved gas analysis Machine learning intelligent algorithms Faults diagnosis Tese de doutorado

来源：评论

学校读者我要写书评

暂无评论

Using Monarch Butterfly Optimization to Solve the Emergency Vehicle Routing Problem with Relief Materials in Sudden Disasters

引用

OPEN GEOSCIENCES 2019年第1期11卷 391-413页

作者： Yi, Jiao-Hong Wang, Jian Wang, Gai-Ge China Univ Min & Technol Sch Environm Sci & Spatial Informat Xuzhou 221116 Jiangsu Peoples R China Ocean Univ China Dept Comp Sci & Technol Qingdao 266100 Shandong Peoples R China Jilin Univ Minist Educ Key Lab Symbol Computat & Knowledge Engn Changchun 130012 Jilin Peoples R China Jiangsu Normal Univ Sch Comp Sci & Technol Xuzhou 221116 Jiangsu Peoples R China Northeast Normal Univ Inst Algorithm & Big Data Anal Changchun 130117 Jilin Peoples R China Northeast Normal Univ Sch Comp Sci & Informat Technol Changchun 130117 Jilin Peoples R China

China has one of the highest rates of natural disasters in the world. In recent years, the Chinese government has placed a high value on improving emergency natural disaster relief. The goal of this research was to resolve a key issue for emergency natural disaster relief: the emergency vehicle routing problem (EmVRP) with relief materials in sudden disasters. First, we provided a description of the EmVRP, and defined the boundary conditions. On this basis, we constructed an optimization model of EmVRP with relief materials in sudden disasters. To reach the best solution in the least amount of time, we proposed an enhanced monarch butterfly optimization (EMBO) algorithm, incorporating two modifications to the basic MBO: a self-adaptive strategy and a crossover operator. Finally, the EMBO algorithm was used to solve the EmVRP. Our experiments using two examples EmVRP with relief materials in a sudden-onset disaster proved the suitability of EMBO. In addition, an array of comparative studies showed that the proposed EMBO algorithm can achieve satisfactory solutions in less time than the basic MBO algorithm and seven other intelligent algorithms.

关键词： Emergency vehicle routing problem relief materials sudden disasters intelligent algorithms monarch butterfly optimization self-adaptive crossover operator

来源：评论

学校读者我要写书评

暂无评论

Optimizing Energy Consumption in Transportation: Literature Review, Insights, and Research Opportunities

引用

ENERGIES 2020年第5期13卷 1115-1115页

作者： Corlu, Canan G. de la Torre, Rocio Serrano-Hernandez, Adrian Juan, Angel A. Faulin, Javier Boston Univ Metropolitan Coll Adm Sci Dept Boston MA 02215 USA Univ Publ Navarra INARBE Inst Pamplona 31006 Spain Univ Publ Navarra Inst Smart Cities Pamplona 31006 Spain Univ Oberta Catalunya Dept Comp Sci Internet Interdisciplinary Inst IN3 Barcelona 08018 Spain Euncet Business Sch Barcelona 08018 Spain

From airplanes to electric vehicles and trains, modern transportation systems require large quantities of energy. These vast amounts of energy have to be produced somewhere-ideally by using sustainable sources-and then brought to the transportation system. Energy is a scarce and costly resource, which cannot always be produced from renewable sources. Therefore, it is critical to consume energy as efficiently as possible, that is, transportation activities need to be carried out with an optimal intake of energetic means. This paper reviews existing work on the optimization of energy consumption in the area of transportation, including road freight, passenger rail, maritime, and air transportation modes. The paper also analyzes how optimization methods-of both exact and approximate nature-have been used to deal with these energy-optimization problems. Finally, it provides insights and discusses open research opportunities regarding the use of new intelligent algorithms-combining metaheuristics with simulation and machine learning-to improve the efficiency of energy consumption in transportation.

关键词： transportation systems optimization problems efficient energy consumption intelligent algorithms sustainability

来源：评论

学校读者我要写书评

暂无评论

Experimental investigation and statistical modelling for assessing the tensile properties of FDM fabricated parts

引用

Procedia Structural Integrity 2020年 26卷 139-146页

作者： N.A. Fountas P. Kostazos H. Pavlidis V. Antoniou D.E. Manolakos N.M. Vaxevanidis Laboratory of Manufacturing Processes & Machine Tools (LMProMaT) Department of Mechanical Engineering Educators School of Pedagogical and Technological Education (ASPETE) Amarousion GR 151 22 Greece School of Mechanical Engineering National Technical University of Athens (NTUA) Athens Greece

Owing to its ability to manufacture complex parts without expensive tooling requirement or human intervention, fused deposition modelling (FDM) is gaining distinct advantage in manufacturing industry. As it occurs to any other engineering process, the properties of FDM-built products exhibit high dependence on process parameters which may be improved by setting suitable levels for parameters associated to FDM. Anisotropic and brittle nature of build part makes it essential to examine the effect of process parameters to the resistance of tensile loading for improving strength of functional parts. This paper focuses on the experimental study of examining the effect of five fused deposition modeling parameters such as layer height, shell thickness, infill density, orientation angle and printing speed on the tensile strength of standard ASTM 638-10 type 1 tensile specimens. The experimental study involved a fractional factorial design involving 16 runs. This design was then converted to a custom response surface design to examine the non-linearity presented by the curvature when examining independent variables in continuous form. The study not only gives an insight concerning the complex dependency of tensile load by the process parameters corresponding to FDM but also generates a statistically validated regression model. The regression model adequately explains the variation and the non-linear influence of FDM parameters on tensile strength and thus, it can be implemented to find optimal parameter settings with the use of any artificial intelligent algorithm or neural network.

关键词： Fused deposition modeling-FDM 3D printing tensile strength regression modelling intelligent algorithms neural network

来源：评论

学校读者我要写书评

暂无评论

Stability Prediction Techniques for Electric Power Systems based on Identification Models and Gramians

引用

IFAC-PapersOnLine 2019年第13期52卷 481-485页

作者： Bakhtadze, N. Yadykin, I. V.A. Trapeznikov Institute of Control Sciences of the Russian Academy of Science Moscow Russia 65 Profsoyuznaya Moscow117997 Russia

The methods for developing predictive models in control systems and decision-making support for nonlinear non-stationary objects are proposed. The methods are based on the application of associative search procedure to virtual model identification as well as Gramian techniques. The associative search methods use intelligent process knowledge analysis. The knowledge base is created and extended in real-time process operation. intelligent algorithms are offered for predicting power plant dynamics in optimization tasks. Gramian technique of stability analysis for discrete system is used for investigating linear virtual model stability. It is shown that the bilinear Lyapunov equation solutions can be calculated as an infinite sum of the matrix quadratic forms made up by the products of the Faddeev matrices obtained by decomposing of linear subsystem dynamic matrix resolvents. © 2019, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.

关键词： Predictive analytics Decision making Electric power system stability Knowledge based systems Lyapunov functions Matrix algebra Number theory Wavelet analysis Associative Search Decision making support Gramians Identification model intelligent algorithms Knowledge base Non stationary objects Process identification

来源：评论

学校读者我要写书评

暂无评论

Machine Learning algorithms in Forecasting of Photovoltaic Power Generation 2

Machine Learning Algorithms in Forecasting of Photovoltaic P...

引用

2nd International Conference on Smart Energy Systems and Technologies (SEST)

作者： Su, Di Batzelis, Efstratios Pal, Bikash Imperial Coll London Elect & Elect Engn London England

ISBN: (纸本)9781728111568

Due to the intrinsic intermittency and stochastic nature of solar power, accurate forecasting of the photovoltaic (PV) generation is crucial for the operation and planning of PV-intensive power systems. Several PV forecasting methods based on machine learning algorithms have recently emerged, but a complete assessment of their performance on a common framework is still missing from the literature. In this paper, a comprehensive comparative analysis is performed, evaluating ten recent neural networks and intelligent algorithms of the literature in short-term PV forecasting. All methods are properly fine-tuned and assessed on a one-year dataset of a 406 MWp PV plant in the UK. Furthermore, a new hybrid prediction strategy is proposed and evaluated, derived as an aggregation of the most well-performing forecasting models. Simulation results in MATLAB show that the season of the year affects the accuracy of all methods, the proposed hybrid one performing most favorably overall.

关键词： Forecasting intelligent algorithms machine learning neural networks photovoltaic

来源：评论

学校读者我要写书评

暂无评论

Meta-heuristic bus transportation algorithm

引用

Iran Journal of Computer Science 2019年第1期2卷 23-32页

作者： Bodaghi, Mohammad Samieefar, Koosha Amirkabir University of Technology Tehran Iran

Over recent decades, several experience-based mathematical models have been proposed. In addition to collective intelligence, in recent years some efforts have been made to apply human experience-based intelligence to open up a new world of possibilities to design new meta-heuristic algorithms for solving NP problems. In these algorithms instead of only relying on collective intelligence, each individual tries to search for optimal solution based on her or his own experience and others. In this paper, we use a social behavior of humans in transportations to reach their destination and we took experience-based human behavior and smartness of humans as an inspiration to propose our meta-heuristic algorithm and we name it bus transportation algorithm. As a simple example, we restrict our paper to solve a well-known problem integer programming which is known as an NP-Complete problem. Compared to other algorithms, the results in these papers show that our algorithm outperforms PSO (particle swarm optimization), GA (genetic algorithm) and SA (simulated annealing) in terms of efficiency and convergence. © Springer Nature Switzerland AG 2018.

关键词： Bus transportation algorithm Empiricism Human intelligence intelligent algorithms Meta-heuristic algorithm

来源：评论

学校读者我要写书评

暂无评论

Real-time bio-signal-processing of students based on an intelligent algorithm for Internet of Things to assess engagement levels in a classroom

引用

FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE 2018年 86卷 716-722页

作者： Kim, Pyoung Won Incheon Natl Univ Coll Educ Dept Korean Language Educ 12 Gaetbeol Ro Incheon South Korea

The level of student engagement refers to the degree of immersion of students during a class. This paper presents an intelligent algorithm that provides information to the teacher by measuring the level of engagement in real time. The Internet of Things (IoT) algorithm for assessing student engagement levels is presented in this study, evaluating the psychical state of students by measuring the electrodermal activity (or galvanic skin response). The algorithm proposed in this study is innovative in that it allows teachers to provide feedback to students while monitoring students in real time. This study provides a basis for IoT applications for teaching and learning. In particular, this study constructs a color fuzzy model to represent student engagement levels by saturation. An application on the teacher's mobile phone transforms like a chameleon, in real time, according to the immersion of students during class. If students learn this algorithm, they can monitor their own immersion levels. This is to encourage students to perform some kind of engineering thinking. (C) 2018 Elsevier B.V. All rights reserved.

关键词： intelligent algorithms Internet of Things Engagement Immersion Galvanic skin response Engineering thinking

来源：评论

学校读者我要写书评

暂无评论

Cancers classification based on deep neural networks and emotional learning approach

引用

IET SYSTEMS BIOLOGY 2018年第6期12卷 258-263页

作者： Jafarpisheh, Noushin Teshnehlab, Mohammad KN Toosi Univ Technol Dept Elect Engn Tehran Iran

In the present era, enormous factors contribute to causing cancer. So cancer classification cannot rely only on doctor's thoughts. As a result, intelligent algorithms concerning doctor's help are inevitable. Therefore, the authors are motivated to suggest a novel algorithm to classify three cancer datasets;colon, ALL-AML, and leukaemia cancers. Their proposed algorithm is based on the deep neural network and emotional learning process. First of all, by applying the principal component analysis, they had a feature reduction. Then, they used deep neural as a feature extraction. Then, they implemented different classifiers;multi-layer perceptron, support vector machine (SVM), decision tree, and Gaussian mixture model. In the end, because in the real world, especially when working on systems biology, unpredictable events, and uncertainties are undeniable, the robustness of their model against uncertainties is important. So they added Gaussian noise to the input features of the first encoder in each dataset, then, they applied the stacked denoising method. Experimental results disclosed that, generally, using emotional learning increased the accuracy. In addition, the highest accuracy was gained by SVM, 91.66, 92.27, and 96.56% for colon, ALL-AML, and leukaemia, respectively. However, GMM led to the lowest accuracy. The best accuracy gained by GMM was 60%.

关键词： cancer learning (artificial intelligence) principal component analysis multilayer perceptrons feature extraction support vector machines pattern classification Gaussian processes decision trees Gaussian noise medical computing colon cancer Gaussian noise stacked denoising method SVM support vector machine emotional learning process cancer datasets intelligent algorithms cancer classification ALL-AML input features Gaussian mixture model decision tree multilayer perceptron feature extraction feature reduction principal component analysis deep neural network leukaemia cancers

来源：评论

学校读者我要写书评

暂无评论

Optimal participating of the distributed generation sources in the re-structured power systems with optimized fuzzy logic controller

引用

JOURNAL OF intelligent & FUZZY SYSTEMS 2018年第4期35卷 4573-4587页

作者： Afrakhte, Hossein Rouhani, Seyed Hossein Univ Guilan Fac Engn Dept Elect Engn Rasht Iran

Due to increasing the demand of electrical energy and non-economic development of the centralized power plant, the electrical industry has been tended toward using the decentralized power plant and distributed generation sources (DGS). In this paper, a three-area re-structured power system with the participation of DGS, hydro power plant, thermal power plant, wind turbine with doubly fed induction generator (DFIG) and photovoltaic system have been studied. The DGS due to the low capacity production and lack of cost effectiveness will not be participating in the electricity marketing. Injection the energy to power system by the DGS and how to participate these resources in the automatic generation control (AGC) is controlled by a separate controller (not main controller). This controller is designed based on the optimal fuzzy logic controller (OFLC). Load of this system has been considered as a random variable that continuously and randomly has the fluctuation number of 0.3 around nominal amount. Fluctuations occurred because of considering the load as a random variable and participation of the wind-powered turbine with DFIG, photovoltaic system and DGS as a source of generation in power system. Since the wind turbine and photovoltaic system don't produce power in the whole day, in this study capacitive energy storage (CES) units will be used parallel with this renewable energy source. To improve the response of power system, PID and OFLC will be utilized. Controller parameters can be optimized with three intelligent algorithms such as Imperialist Competitive Algorithm (ICA), Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) Algorithm and finally the results will be compared with each other.

关键词： DGS random variable load wind turbine with DFIG photovoltaic system restructured power systems OFLC intelligent algorithms

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：