Programa de Pós-graduação em Engenharia Elétrica e da Computação

URI Permanente desta comunidade

http://200.137.215.59/tede/handle/tde/262

Navegar

Navegando Programa de Pós-graduação em Engenharia Elétrica e da Computação por Por Orientador "Brito, Leonardo da Cunha"

Agora exibindo 1 - 15 de 15
  • Nenhuma Miniatura disponível
    Item
    Transformada da incerteza puramente numérica para a avaliação de incertezas
    (Universidade Federal de Goiás, 2016-05-24) Brito Junior, Ademir Alves de; Brito, Leonardo da Cunha; http://lattes.cnpq.br/6660680440182900; Brito, Leonardo da Cunha; http://lattes.cnpq.br/6660680440182900; Rocha, Adson Silva; Ribeiro, Cacilda de Jesus
    In this work, a numerical version of Unscented Transform was developed. In the developed approach, any probability distributions can be mapped by means of linear or non-linear functions, thus allowing fast acquisition of the probability distributions of the outputs/ simulation model responses, or more specifically, the evaluation of the uncertainty model. For practical purposes of distribution mapping, the computational cost is considerably lower than that demanded by the Monte Carlo method, which is based on a massive random sampling, thus presenting high computational cost. The application in Biomechanics problems shows the efficiency of the proposed method.
  • Nenhuma Miniatura disponível
    Item
    Proposta de um sistema hipermídia adaptativo educacional para a personalização do processo de ensino atraves da web
    (Universidade Federal de Goiás, 2011-12-13) Bueno, Alexandre Martins Ferreira; Brito, Leonardo da Cunha; http://lattes.cnpq.br/6660680440182900; Brito, Leonardo da Cunha; Pato, Vinicius Sebba; Silva, João Carlos da; Cruz Júnior, Gélson da
    Nowadays, e-learning has become an important source of knowledge, providing content without the limitation of time or space. In this context, Web-based education became an important sector. A large number of e-learning applications have utilized the Web to teach, mainly to provide distance learning. As a result of the substantial growth in elearning there has been an increase in the diversity of students that uses this environment to achieve their academic or professional backgrounds. In general, these students have di erent personal, social-cultural and cognitive characteristics. Adaptive Hypermedia Systems provide resources to assist this diverse public, they are able to consider the individual characteristics of students during the learning process. It is known that the representation of these features are often associated with uncertain and imprecise information. Given this context, this work proposes a Web-based Adaptive Educational Hypermedia System (with instructional content) that aims to personalize the process of distance learning. It has a student model that is able to represent the uncertainties related to the student's knowledge (characteristic of the students considered by the system) through the use of a Bayesian Network. This model is adjusted according to the answers provided by students in ability tests, which in turn are evaluated by a mathematical model of Item Response Theory. The experiment realized compared the results obtained by the proposed system, that is provided with adaptation (personalization) mechanisms, and other system that has no such mechanisms, in which the same content was presented to all the students. Statistical analysis of the collected data has shown a signi cant improvement in knowledge retention by the students who used the system provided with adaptation. However, it was expected, as a result of this improvement, that the levels of satisfaction reported by the students who used the proposed system were better than the levels reported by the students who used the system without adaptation, which was not evidenced by the gathered data.
  • Nenhuma Miniatura disponível
    Item
    Método computacional para elaboração de projetos eletromecânicos de redes de distribuição de energia elétrica com condutores de alumínio Nu
    (Universidade Federal de Goiás, 2017-09-28) Carvalho, Denner Monteiro de; Brito, Leonardo da Cunha; http://lattes.cnpq.br/6660680440182900; Paula, Geyverson Teixeira de; Rocha, Adson Silva; Brito, Leonardo da Cunha
    The present work presents the development of a computational tool for the optimization of processes in the elaboration of electromechanical projects of conventional electricity distribution networks. The current process of elaboration of distribution network projects that has significant topographical interferences is slow and depends on software with a technological lag that requires post processing of the data to generate the final project, besides demanding specific technical knowledge and too much elaboration time. This elaboration time, as well as the errors occurred in the post-processing stage, hinder the approval process of the projects in the electric power concessionaires, and delay the connection of final consumers. For modeling the process, the typologies of the terrain where the network path is to be determined through surveys of the topographic data are verified first. Afterwards, mechanical forces and stresses are observed in each type of electromechanical structure, defining the minimum mounting distances in compliance with related technical norms, as well as incident variables such as wind speed and mechanical variations of the conductors during the operation. The modeling of the decision variables is applied a recursive heuristic method with the application of the Hill Climbing optimization method, which sweeps the entire line defined by topography, performing the mechanical evaluations and calculations with the optimization of technical budget criteria, generating uniform solutions and Automated. The tool obtained is developed in Web platform with friendly interface and updated, and can be used through any browser. The software, besides providing the elaboration of the project with embedded normative criteria, can be easily used for project analysis, providing integrated visualization of the planialtimetric profiles through Google Maps, optimizing the process of visual evaluation.
  • Nenhuma Miniatura disponível
    Item
    Rede bayesiana para estimativa da confiabilidade de transformadores de potência imersos em óleo mineral isolante utilizando técnicas preditivas de manutenção
    (Universidade Federal de Goiás, 2019-03-12) Dias, Yuri Andrade; Brito, Leonardo da Cunha; http://lattes.cnpq.br/6660680440182900; Brito, Leonardo da Cunha; Ribeiro, Cacilda de Jesus; Marques, André Pereira
    The knowledge of the criticality of the state of an electrical equipment is indispensable to the determination of efficient actions, regarding the preventive maintenance or, if necessary, corrective to it applicable. For power transformers, which, due of their strategic importance for the transmission and distribution of electric power, demands great attention from the companies maintaining the electric system, information about reliability are of great utility to decision making, assisting in determining which interventions are necessary to ensure the uninterrupted supply of electricity to the consumer units. In this context, this work presents, as contribution, a Bayesian network for determining the reliability of mineral insulating oil filled power transformers, whose evidence of the component nodes is obtained from the results of the application of the main predictive maintenance techniques, namely: electrical tests; degree of polymerization of paper, particle counting, dissolved gas analysis (chromatography), physicochemical tests and dibenzyl disulfide (DBDS) in mineral insulating oil; and visual inspections and local checks. The main objective is to provide, to the electrical system maintenance teams, concrete information about the criticality of the state of power transformers, providing adequate definition of the applicable interventions, optimizing the available technical and monetary resources and, at the same time, maximizing the reliability of the electric system to which these equipments belong. Therefore, it is expected that there will be a reduction of unscheduled supply interruptions associated with failures in power transformers operation. This way, we hope to reach a substantial improvement of the services provided to final consumers, with direct impacts on the quality indicators of the electricity supply established by the Regulatory Agent.
  • Nenhuma Miniatura disponível
    Item
    Sistema de comunicação alternativa para pessoas com distúrbios neuromotores severos usando redes neurais artificiais
    (Universidade Federal de Goiás, 2024-12-15) Floriano, Carolina de Souza; Silva, Adson Rocha; Brito, Leonardo da Cunha; http://lattes.cnpq.br/6660680440182900; Brito, Leonardo da Cunha; Rocha, Adson Silva; Gomide, Renato de Sousa
    Communication difficulties are frequent for many people with severe motor disabilities, making it difficult for them to interact with their families, caregivers and society in general. Augmentative and Alternative Communication (AAC) then aims to compensate for the communication deficit of these people, providing the individual with a better quality of life. However, these individuals with severe neuromotor disorders who have severe movement restrictions find great challenges in the use of several current assistive technologies. In this context, the objective of this research is to present an Alternative Communication System based on Artificial Neural Networks with a user-centered approach and their needs, for use by this public. The input and signal processing are carried out by reading facial landmark points, using the MediaPipe FaceMesh library. The development of the gesture/facial expression classifier is performed through the implementation and comparison of two different models: a Convolutional Neural Network (CNN) model and a Recurrent Neural Network model using Long Short-Term Memory (LSTM) units and dense layers. Dynamic challenges were implemented to conduct a more in-depth analysis of the models’ performance in various contexts, varying parameters such as the quantity of samples and the inclusion of similar gestures. Real-time overall results indicate a consistent performance of the proposed system, suggesting that, in both approaches, the Convolutional Neural Network (CNN) stands out significantly compared to the Long Short-Term Memory Recurrent Neural Network (LSTM) in gesture recognition.
  • Nenhuma Miniatura disponível
    Item
    Sistema de comunicação alternativa para pessoas com distúrbios neuromotores severos usando redes neurais artificiais
    (Universidade Federal de Goiás, 2023-12-15) Floriano, Carolina Souza; Silva, Adson Rocha; http://lattes.cnpq.br/4116708456419800; Brito, Leonardo da Cunha; http://lattes.cnpq.br/6660680440182900; Brito, Leonardo da Cunha; Gomide, Renato de Sousa; Rocha, Adson Silva
    Communication difficulties are frequent for many people with severe motor disabilities, making it difficult for them to interact with their families, caregivers and society in general. Augmentative and Alternative Communication (AAC) then aims to compensate for the communication deficit of these people, providing the individual with a better quality of life. However, these individuals with severe neuromotor disorders who have severe movement restrictions find great challenges in the use of several current assistive technologies. In this context, the objective of this research is to present an Alternative Communication System based on Artificial Neural Networks with a user-centered approach and their needs, for use by this public. The input and signal processing are carried out by reading facial landmark points, using the MediaPipe FaceMesh library. The development of the gesture/facial expression classifier is performed through the implementation and comparison of two different models: a Convolutional Neural Network (CNN) model and a Recurrent Neural Network model using Long Short-Term Memory (LSTM) units and dense layers. Dynamic challenges were implemented to conduct a more in-depth analysis of the models’ performance in various contexts, varying parameters such as the quantity of samples and the inclusion of similar gestures. Real-time overall results indicate a consistent performance of the proposed system, suggesting that, in both approaches, the Convolutional Neural Network (CNN) stands out significantly compared to the Long Short-Term Memory Recurrent Neural Network (LSTM) in gesture recognition.
  • Nenhuma Miniatura disponível
    Item
    Aplicação interativa em processos de otimização por método das estratégias de evolução
    (Universidade Federal de Goiás, 2017-05-15) Jesus, Luiz Henrique Reis de; Brito, Leonardo da Cunha; http://lattes.cnpq.br/6660680440182900; Paula, Geyverson Teixeira de; Ribeiro, Cacilda de Jesus
    This dissertation of master degree describes an approach of the interactive optimization process associate to the Evolution Strategies method for the evaluation of the loudspeaker optimization project, with the objective to present the advantages achieved after the user interventions throughout the optimization process. Its development is based on the methodology of the Evolution Strategies characterized by the concept of natural selection, which uses combination and mutation methods to generate new individuals. However, for greater efficiency in the responses of the objective function, as well as the reduction in its convergence time, the optimization process requires interventions in stabilization of local minima and maxima. In the interventions made available to the user, will be considered manipulations in the operators of mutation and combination, mutation of the parameters of self-adaptation, as well as the change of objective and the variation of their respective restriction. As a differential, an interface was developed to make feasible the user interventions applied to the optimization process, as well as the monitoring of the entire process. In this work, also evaluated optimization test functions with the objective of validating the proposed methodology.
  • Nenhuma Miniatura disponível
    Item
    Estratégias de otimização de trajetos e alocação de torres em projetos de linhas de transmissão aéreas
    (Universidade Federal de Goiás, 2018-03-22) Póvoa, Caio José Fernandes; Brito, Leonardo da Cunha; http://lattes.cnpq.br/6660680440182900; Brito, Leonardo da Cunha; Carneiro, Marcos Lajovic; Paula, Geyverson Teixeira de
    This dissertation of master degree describes methods of optimizing routes and allocating towers of overhead power lines, with the objective of meeting technical, structural and constructive constraints, and reducing financial costs. The generated solutions are graphically presented through the transmission line profile and its 3-dimension representation upon the elevation map of the area. For the projects evaluation, elements of structural analysis are used, highlighting the Matrix Structural Analysis for the study of efforts and deformations in the towers and their components. Three methods are proposed, each one using different approaches. First, it will be shown an optimization algorithm based on Evolutionary Computation, characterized by the application of natural selection on individuals generated from mutations and genetic crossover. The second algorithm was inspired by the well-known Nelder-Mead optimization method. The triangular transformations addressed in the original method were adapted and physically implemented to transmission lines. The last optimization algorithm presented is a hybridization of the two previous methods. Finally, a performance comparison of the algorithms, in which each one of them will be applied to three different cases, will be carried out in order to validate them.
  • Nenhuma Miniatura disponível
    Item
    Metodologia para eficientização do processo de elaboração e análise de projetos de linhas aéreas rurais de distribuição de energia elétrica
    (Universidade Federal de Goiás, 2017-09-29) Ribeiro, Cássio Landim; Brito, Leonardo da Cunha; http://lattes.cnpq.br/6660680440182900; Brito, Leonardo da Cunha; Ribeiro, Cacilda de Jesus; Rocha, Adson Silva
    This paper presents a new methodology aimed at increasing efficiency in the dimensioning and approval stage of aerial rural electricity distribution lines projects. As a substitute for the sequential process currently employed, the approach proposed here is based on Simultaneous Engineering, where all the actors of the process have access to the computational tool, in a web platform, that allows implementing the methodology, enabling the multidisciplinary activity to be carried out in a parallel way. The estimates gathered indicate that the tool will allow the reduction of the time spent for the elaboration and approval of the projects, allowing: to reduce the total cost in man-hour spent by the electric utility; satisfy the customer's needs more quickly; optimize the mechanical dimensioning of distribution lines; and provide additional financial gain to the concessionaire due to the reduction of the average time to effectively start supplying electric power.
  • Imagem de Miniatura
    Item
    Identificação, mensuração e localização tridimensional de descargas parciais em transformadores de potência com base em resultados de ensaios de emissão acústica
    (Universidade Federal de Goiás, 2014-02-27) Romualdo, Hudson de Paula; Brito, Leonardo da Cunha; http://lattes.cnpq.br/6660680440182900; Brito, Leonardo da Cunha; Menezes, Leonardo Rodrigues Araújo Xavier de; Rocha, Adson Silva; Ribeiro, Cacilda de Jesus
    The presence of partial discharges in power transformer represents a relevant indicator of incipient failure. Partial Discharges are lightning quick and incomplete, intermittent, that in power transformers can be detected by means of some methods, among them, the test of acoustic emission. Currently, the algorithms used by equipment that processes the information from testing of acoustic emission are owners, and thus not available for the scientific community. Still, it is usually not performed the separation of noise detected from partial discharge of the other noises in the results, and little information about the dynamics of the occurrence of noise is presented. In this work, are presented three methods, identification, measurement and three-dimensional location, that foster the development of a computational solution for the diagnosis of power transformers using data derived from testing of acoustic emission with focus on the occurrence of partial discharges, phenomenon harmful to the appropriate functioning of the equipment. After a substantiation based on literature review of the issues dealt with in the course of the study, are described methods for identification of noises coming only from partial discharges, among the total noise (of all kinds), and measurement of these noises and their attributes (already done in a separate manner). Then, reference-if the method for three-dimensional location and, finally, expose-if the results of the application of the methods developed in the form of a case study showing the benefits of the application of the methods described here. Thus Demonstrating the importance of their results in supporting the decision-making process and, consequently, in maintaining the operational condition of power transformers.
  • Nenhuma Miniatura disponível
    Item
    Desenvolvimento de uma metodologia de interpretação de análise de gases dissolvidos em óleo para transformadores de potência usando lógica Fuzzy
    (Universidade Federal de Goiás, 2017-05-25) Silva, Tiago Henrique Vivas e; Brito, Leonardo da Cunha; http://lattes.cnpq.br/6660680440182900; Brito, Leonardo da Cunha; http://lattes.cnpq.br/6660680440182900; Rocha, Adson Silva; Ribeiro, Cacilda de Jesus
    This work have its main theme on the maintenance in Power Transformers in energy substations. Power Transformers have great importance in power transmission and distribution systems. In addition to being essential to perform the transformation between diferent levels of electrical voltage from generation to consumption, the cost of these equipments represents a considerable part of the investment in the system. A failure in a transformer can compromise the supply of electricity to an entire region of the city, which represents a lack of billing and fines to the power distribution company, as well as the repair costs of the equipment that failed. In this dissertation one of the main techniques used to diagnose power transformers using the Dissolved Gas Analysis (DGA) are discussed, as well as the use of Fuzzy Logic in conjunction with the diferente analysis techniques. The differential of this work is the development of a computational tool that allows the grafical visualization of diagnosis evolution for each equipment over time and provides a final result by a flowchart that considers all diagnosis of the traditional techniques approached with application of Fuzzy Logic. The result obtained is the development of a software that implements the proposed methodology and graphically presents the diagnostics of each equipment present in the company’s database. The software allows the analysis of the current operational state of the equipment and his evolution over time, subsidizing the decision of the maintenance professional regarding maintenance in the equipment.
  • Nenhuma Miniatura disponível
    Item
    Uma contribuição computacional para a análise da migração de umidade em sistemas isolantes papel- óleo de transformadores de potência
    (Universidade Federal de Goiás, 2016-06-10) Sousa, Felipe Resende de Carvalho; Brito, Leonardo da Cunha; http://lattes.cnpq.br/6660680440182900; Brito, Leonardo da Cunha; Carvalho Júnior, Carlos Alberto Tenório de; Ribeiro, Cacilda de Jesus
    Prediction ofmoisture levels inside power transformers shown itselfas an important technique for maintenance engineering, because in addition to being associated with the useful life of equipment, it also provides arguments for decision making about intervention in them. Despite concerns about water in transformers existed for over half a century, the monitoring of this variable is still done in a simply way, given little information to weave a diagnosis, which can lead to superficial interpretations of equipment, and therefore, the misdiagnosis. Given such a scenario, this work aims to obtain an equation that models classical curves relative to moisture in transformers, as well as the development of a mathematical model that simulates water migration inside these equipments. For this purpose, computational techniques and numerich methods are used. Thus, the main contribution of this work is to optimize the above diagnostic process. During the work a literature review of the subject is presented, with further explanations of the mathematical tools used. To prove the effectiveness of the project presented, case studies with data from energized power transformers are analysed. Some values found in other works are also uses to validate the work. Ending with some conclusions, this paper proves that the use of the approach presented here is effective, and its application is fundamental in the area of maintenance engineering.
  • Nenhuma Miniatura disponível
    Item
    Modelagem e análise da migração da umidade em sistema isolante papel-óleo de transformadores de potência
    (Universidade Federal de Goiás, 2020-11-20) Sousa, Felipe Resende de Carvalho; Brito, Leonardo da Cunha; http://lattes.cnpq.br/6660680440182900; Brito, Leonardo da Cunha; Ribeiro, Cacilda de Jesus; Domingues, Elder Geraldo; Marques, André Pereira; Paula, Geyverson Teixeira de
    This thesis aims to present an innovative tool designed to study how the phenomenon of moisture migration occurs inside insulating paper-oil systems of power transformers. The tool consists of a two-dimensional mathematical model, representing the dynamics of humidity in the oil-paper set and including the variations in electrical charging, which was developed using mathematical tools, existing studies, and the experience of specialists/analysts. Furthermore, this study includes a classification method developed to investigate some of the harmful effects of moisture in power transformers, considering the possibility of bubbles and free water formation. The novelty of this numerical method consists of a calculation methodology that contemplates the use of the finite element method - in two dimensions - applied to the concepts of mass transfer and thermal modeling of the transformer loading, considering the temperature differences between two windings. Additionally, the classification method includes the creation of: a) a categorization system for the coupling of a transformer and electric charging in five levels, from “A” to “E”, with the respective recommended actions; and b) an analysis that involves varying the different levels of loading applied to the equipment. The contribution of this work is an efficient method, implemented via a computational algorithm, which provides support for the maintenance team's decision making when unfavorable phenomena and conditions occur that can critically affect the useful life of the equipment, especially its insulation. This thesis presents some case studies of transformers in operation, under real load conditions, in which the data validation is performed through the comparation of obtained data with experimental collection and analysis of oil samples and the results of monitoring device. Therefore, this work is useful in supporting the classification and diagnosis of power transformers, through the prediction of humidity levels in the oil-paper isolating system, assisting on failure prevention in this equipment and capital loss to the owners of the transformers and consumers supplied by these.
  • Nenhuma Miniatura disponível
    Item
    Aplicação da transformada de Hilbert-Huang e da seleção paraconsistente de características no campo da entomologia agrícola: uma abordagem para identificação e estimativa de densidade de cigarras em lavouras cafeeiras
    (Universidade Federal de Goiás, 2023-12-01) Souza, Uender Barbosa de; Escola, João Paulo Lemos; http://lattes.cnpq.br/5894769490673984; Brito, Leonardo da Cunha; http://lattes.cnpq.br/6660680440182900; Brito, Leonardo da Cunha; Vieira, Flávio Henrique Teles; Lemos, Rodrigo Pinto; Escola, João Paulo Lemos; Maccagnan, Douglas Henrique Bottura
    The sounds emitted by various insect species carry specific and reliable acoustic characteristics. For this reason, acoustic identification of insects has been widely investigated by the scientific community in the field of pattern recognition. In Brazil, the cicada species Quesada gigas is considered a pest in coffee crops due to its sap-feeding habits, which can cause losses to farmers during intense attacks. Given this scenario, and considering the fact that the most striking characteristic of cicadas is sound emission for reproductive purposes, this work proposes a system designed to assist in the management of pest insects in coffee crops. Specifically, this system aims to detect the presence of cicadas or estimate their density through acoustic signals. The approach innovatively combines the extraction and analysis/selection of sound features through the Hilbert-Huang Transform (HHT) and Paraconsistent Feature Engineering, two emerging methods of growing interest in the scientific community. A detailed study was conducted on the influence of eight stopping criteria for the Empirical Mode Decomposition, the first step of HHT, considering variations of parameters, temporality, signal sampling, and also the encoding of these signals in two formats. The first defines vectors by the energies of the Intrinsic Mode Functions (IMFs) in order of extraction, while the second distributes the energies of the IMFs according to the 25 frequency bands of the Bark Scale. Additionally, the dimensional variation of the vectors was analyzed. The experiments allowed determining low computational cost configurations, showcasing the efficacy of the proposed system, with models based on Support Vector Machines achieving accuracies above 98% in both identification and density estimation of cicadas. Thus, this document details the theoretical foundations, design, development of the system, discussions about possibilities for its practical application, and an initial analysis of a developed application for smartphones. This proposal has the potential to encourage the reuse of old electronic equipment, promoting sustainable and economically viable practices.
  • Nenhuma Miniatura disponível
    Item
    Metodologia Fuzzy aplicada ao triângulo de Duval para o diagnóstico de transformadores de potência por meio de análise de gases dissolvidos
    (Universidade Federal de Goiás, 2017-02-17) Veloso, Diogo Pereira; Brito, Leonardo da Cunha; http://lattes.cnpq.br/6660680440182900; Brito, Leonardo da Cunha; http://lattes.cnpq.br/6660680440182900; Ribeiro, Cacilda de Jesus; Rocha, Adson Silva
    Power transformers are essential equipment in eletric systems. Considered as highly expensive equipment it requires greater attention regarding the occurrence of failures. A failure on equipment can cause serious trouble to the concessionaire responsible for the generation, transmission and distribution of energy. In the present scenario, where legislation has increased the severity with which oversees these failures and demanding a higher efficiency of the same, it is necessary to create appropriate policies to investigas possible equipment failure. These failures can be caused by several factors, among them, the gases dissolved in the oil due to its degeneration. One of the most used techniques for the diagnosis of power transformers from these dissolved gases is the Duval Triangle, a method that has a precision and considerably high reliability. However, for proper planning of maintenance, avoiding a possible sudden withdrawal and supply cut, it is necessary to provide further information, including a quantitative analysis of the causes of failure and a history of the evolution of the operating status of the machine. To this end it is proposed to use a fuzzy logic by the method of Duval to provide an analysis of the transitions between the diagnostic originally presented to enable monitor the level of relevance of each possible cause for the diagnosis equipment allowing perform scheduled and preventive maintenance. The proposed methodology was validated using real data equipment in operation in the brazilian electric system.