Programa de Pós-Graduação em Engenharia Elétrica - PPGEE/ITEC

URI Permanente desta comunidadehttps://repositorio.ufpa.br/handle/2011/2314

O Programa de Pós-Graduação em Engenharia Elétrica (PPGEE) do Instituto de Tecnologia (ITEC) da Universidade Federal do Pará (UFPA) foi o primeiro e é considerado o melhor programa de pós-graduação em Engenharia Elétrica da Região Amazônica. As atividades acadêmicas regulares dos cursos de mestrado e doutorado são desenvolvidas principalmente nas Faculdades de Engenharia Elétrica e Engenharia de Computação, supervisionadas pela Coordenação do Programa de Pós-Graduação em Engenharia Elétrica (CPPGEE).

Navegar

Agora exibindo 1 - 20 de 31

Acesso aberto (Open Access)
Algoritmo genético retroviral iterativo
(Universidade Federal do Pará, 2010-09-10) MOREIRA, Renato Simões; AFFONSO, Carolina de Mattos; http://lattes.cnpq.br/2228901515752720
This work presents the development of a hybrid meta-heuristic based on the viral life cycle, specifically from Retroviruses, which are part of nature’s swiftest forms. This algorithm is called Retroviral Iterative Genetic Algorithm (RIGA) and uses as computational basement Genetic Algorithm (GA) and biological basement retroviral replication characteristics, which provides a great diversity increasing the probability to find the solution, what is confirmed by better results obtained by AGRI than AG.
Acesso aberto (Open Access)
Amazonsocialdtn: IBR-DTN com bluetooth para inclusão digital na Amazônia
(Universidade Federal do Pará, 2015-05-29) FERREIRA, Ronedo de Sá; CERQUEIRA, Eduardo Coelho; http://lattes.cnpq.br/1028151705135221
Despite the evolution in deployed infrastructure and in the way that people access information, still there are those who are socially excluded and have no access to information due to their geographic location (e.g., riverside/countryside communities). This paper proposes an extension to a DTN architecture implementation to allow the dissemination of information in such communities, including educational short-video clips and audio books. The IBR-DTN architecture is complemented with a Bluetooth Convergence Layer, to facilitate the exchange of information over this short-range wireless technology, and with a Bundle Compression mechanism that aims at improving data exchange in short-lived opportunistic contacts happening among nodes. Experiments in a small-scale testbed and in a large-scale simulator environment show that nodes are indeed able to efficiently use contact opportunities to exchange an increased amount of data, allowing people in riverside communities to receive more content related to digital inclusion services.
Acesso aberto (Open Access)
Análise de handover a partir do uso de femtocells em redes LTE: abordagem baseada em simulação discreta
(Universidade Federal do Pará, 2014-06-13) SILVA, Ketyllen da Costa; FRANCÊS, Carlos Renato Lisboa; http://lattes.cnpq.br/7458287841862567
The volume of data traffic in mobile networks is growing exponentially. The explosion of mobile devices and applications in recent years has led to an overload of the network infrastructure responsible for disposing of this traffic, thus affecting the performance of the network as the user experience. One of the key elements in the networks (LTE) Long Term Evolution is the possibility of deploying multiple femtocells for the improvement of coverage and data rate. However, arbitrary overlapping coverage of these cells makes the handover mechanism complex and challenging. Thus, this dissertation proposes a methodology to study the impact of handover in LTE networks with femtocells. From a discrete simulation approach, the effects of the deployment of femtocells were evaluated. This study aimed to measure the impact and correlation of the use of femtocell parameters of QoS (Quality of Service) and performance indicators handover.
Acesso aberto (Open Access)
Análise de propagação de ondas eletromagnéticas na faixa de microondas em ambiente indoor com método 3D FDTD e FDTD 2D modificado
(Universidade Federal do Pará, 2012-03-08) RIBEIRO, Dionisio Raony de Souza; DMITRIEV, Victor Alexandrovich; http://lattes.cnpq.br/3139536479960191
This work presents tools of low computing cost and good accuracy to characterize the electromagnetic microwave propagation in indoor environments. It was studied the Finite- Difference Time-Domain (FDTD) method applied to model the propagation in these environments. The study deals with the implementing of a new approach of this method which converses a 3D problem in a 2D one. It is presented a comparative study between the two formulation of the method regarding accuracy, speed and the requirement of computing resources. To apply the 3D formulation, a software was written in FORTRAN with the FDTD 3D parallelized by the MPI library. Then, a cluster with Beowulf architecture was set up run the routine. After the validation of the modified FDTD method, it is applied to characterize an indoor environment regarding its losses. This data was used to obtain the statistical distribution of the parameter n of propagation loss of the environment. The contribution of this work lays on the fact that the researched literature do not present the modified FDTD 2D method applied to indoor environments and the use of simulated data to statistical analysis.
Acesso aberto (Open Access)
Aplicação de redes neurais artificiais na classificação de padrões filogeográficos com base na variabilidade genômica do DNA mitocondrial
(Universidade Federal do Pará, 2007-12-20) GOMES, Larissa Luz; SANTOS, Ândrea Kely Campos Ribeiro dos; http://lattes.cnpq.br/3899534338451625; OLIVEIRA, Roberto Célio Limão de; http://lattes.cnpq.br/4497607460894318
Historically, the process of formation of the populations of the Amazon, as well as from all Brazilian territory, involved three main ethnic groups: the Amerindian, European and African. As a result, these populations have in general admixed constitution the point of view of social and biological. Since the end of the last century, studies of mitochondrial DNA (mtDNA) has been developed for the purpose of estimating the mixture inter present in these populations. For this, it is of fundamental importance classification of a particular strain of mtDNA in one of more than 250 haplogroups/sub-clades proposed in the literature. With the goal of developing an automated system, precise and accurate classification of the sequences (strains) of mtDNA, this has worked hand of the art of Artificial Neural Networks (RNAs) on the basis of the studies of Philogeography. For this classification, four networks have been developed artificial neural direct, with multiple layers and the learning algorithm to backpropagation. The entries of each network equivalent positions at nucleotide polymorphic region's hipervariable of mitochondrial DNA, which returned as output classification specific to each lineage. Subsequent to the training, all the networks had indices of adjustment of 100%, demonstrating that the technique of Artificial Neural Network (ANN) can be used, with success, in the classification of standards Philogeography based on mitochondrial DNA.
Acesso aberto (Open Access)
Aplicação de sensores virtuais na inferência da temperatura de banho no processo de fabricação de alumínio primário
(Universidade Federal do Pará, 2009-12-14) SOARES, Fábio Mendes; OLIVEIRA, Roberto Célio Limão de; http://lattes.cnpq.br/4497607460894318
Nowadays, industries worldwide are looking forward to enlarge their profits and become more competitive. A good management is a key factor to accomplish the company’s target, however all management decisions are supported by tools that provide good and relevant information for the process, which usually influences decision making strategically. Soft Sensors have been applied in industries which are aiming that target and its use has been growing lately. A soft sensor can be adapted to any application regarding variable measurement, therefore reducing operational costs without compromising the current information quality, and in some cases, better results can be obtained. Since they are software based, they are not subjected to physical damages as real sensors are, so they can be adapted virtually to hostile environments. The key of this kind of sensor success is the use of computational intelligence techniques, which has been heavily used in nonlinear and highly complex process modeling. Currently, many industries already use them successfully, and this work exploits its use with Neural Networks in a chemical process in an important Brazilian Aluminum Smelter whose control is very hard to maintain once it is not easy to retrieve information from the plant due to its corrosive nature and whose measurements require some operational resources. The usage of soft sensors within it may reduce costs and delays of measures drastically. A case of use of the soft sensor for temperature measure is presented on this work, since its design through implementation at production, according to a researched methodology.
Acesso aberto (Open Access)
ClasSIS: uma metodologia para classificação supervisionada de imagens de satélite em áreas de assentamento localizados na Amazônia
(Universidade Federal do Pará, 2015-03-12) MONTEIRO, Flavia Pessoa; FRANCÊS, Carlos Renato Lisboa; http://lattes.cnpq.br/7458287841862567
Amazon has one of the most complex and diversified biome of the planet. Its environmental preservation has an impact in the global scenario. However, besides the environmental factors, the complexity of the region involves other different aspects such as social, economical and cultural. In fact, they are intrinsically interrelated in such a way, that, for example, cultural features may affect land use/land cover. Moreover, depending on the scale of such changes, there may be consequences on the planet. Due to the criticality involving the region, several actions of governments, organizations and social movements and the international community, has been trying to rationalize the land use/land cover, in order to create a sustainable exploitation of available natural resources. An important government program is based on the creation of settlements, with respective support, with regard to certain infrastructure financing, machinery, seeds and seedlings, technical assistance, etc. However, despite the efforts made, the solution is extremely complex, given the extensive correlation of factors to be assessed and combined in search of success and improvement of such programs. So, because of all complexity involved, it is of paramount importance that there are methodologies that contemplate the complexity and inherent interdisciplinarity. Intending to have a closer look at this whole issue, an Amazonian set of institutions drew up and approved the project Skills Development and Training of Human Resources for Degraded Areas Recovery in Settlement Projects in Amazonian Areas – Public Notice Nº047 / 2012 - CAPES/Pró-Amazônia Programme. This work presents an innovative methodology for land use/land cover analysis, in projects of settlements located in the Amazon, as part of the above mentioned. Such methodology comprises two modules (image processing, and classification and patterns extraction), each module is subdivided into steps to performing their primary functions. The methodology proposed in this work, which has a high degree of generalization, aims to categorize the land use/land cover, through the association of each pixel to a predefined thematic class. In order to validate the proposed strategy, case studies are carried out in settlements located at the Southeast region of the Stat eof Pará, in the Brazilian Amazon.
Acesso aberto (Open Access)
Comparação de métodos baseados em algoritmos genéticos para ajuste coordenado de estabilizadores de sistemas de potência
(Universidade Federal do Pará, 2014-11-27) VIEIRA, Celivan Ferreira; VIEIRA, João Paulo Abreu; http://lattes.cnpq.br/8188999223769913
This work presents a comparison study among three methodologies based on genetic algorithms applied to solve the power system stabilizers (PSS) tuning problem. The PSS tuning procedures are formulated as an optimization problem in order to: 1) maximize the closed-loop minimum damping ratio; 2) maximize the sum of the spectrum damping ratios; and 3) shift the lightly damped and undamped electromechanical modes of all plants to a prescribed zone in the s-plane. The three methodologies taking into account a pre-specified operating conditions. For this purpose, the system is represented by the state-space equations and the matrices associated with this modeling are obtained by using the academic version of the commercial software PacDyn. The simulations are carried out using the MATLAB plataform. The methodologies are applied to the well-known New England test system.
Acesso aberto (Open Access)
Controle de qualidade para 3D-vídeo streaming em redes em malha sem fio
(Universidade Federal do Pará, 2013-02-20) QUADROS, Carlos Jean Ferreira de; CERQUEIRA, Eduardo Coelho; http://lattes.cnpq.br/1028151705135221
Wireless Mesh Networks (WMNs) are envisaged to be one of the most important wireless technologies to provide last mile access in future wireless multimedia networks. In this context, 3D-video is envisioned to attract more and more the multimedia market with the perspective for enhanced applications (video surveillance, mission critical control, entertainment, etc.). However, the challenge of dealing with the uctuating bandwidth, scarce resources and time-varying error rate of these networks, illustrates the need for error-resilient 3D-video transmission. In this context, Forward Error Correction (FEC) approaches are required to provide the distribution of video applications for wireless users with Quality of Service (QoS) and Quality of Experience (QoE) assurance. This study proposal puts forward a FEC-based mechanism with Unequal Error Protection (UEP) to enhance 3D-video transmission in WMNs, while increasing user satisfaction and improving the usage of wireless resources. The benefits and impact of the proposed mechanism will be demonstrated by using simulation, the assessment will be conducted with objective and subjective QoE metrics.
Acesso aberto (Open Access)
Desempenho do algoritmo genético com iteração retroviral para otimização de funções com representação real
(Universidade Federal do Pará, 2015-06-30) FRANCO, Dielle da Silva Corrêa; SANTANA, Ádamo Lima de; http://lattes.cnpq.br/4073088744952858; OLIVEIRA, Roberto Célio Limão de; http://lattes.cnpq.br/4497607460894318
Viral Infection is used to improve the performance in Genetic Algorithms (GA) by reducing premature convergence through the population diversity control, since viruses presents high replication and mutation rates in the nature. The metaheuristic called AGRI is inspired biologicaly in a viruses family based on RNA, which provide a high allelic variation to GA, since RNA doesn’t have genoma correction mechanisms to remove re-combined viral genetic material . In this algorithm, the viruses are a separate population. To each infection, the better performance viruses genomes are transmitted vertically spreading parts of solutions to GA population. The diversity viral is maintained through a mechanism that substitutes all viruses out of elitism viral rate. In this method, the virus population evolves along with GA population, so the inefficient viruses are created from genetic material of the better adapted individuals and other new genes. The algorithm AGRI follows biological principles in several viral infection and multiplication aspects. For example: it creates the first viral population without GA population genetic material; it sorts the viral population before infect an individual, making possible some viruses doesn’t infected a part of the population and other viruses infect more individuals. Since GA second-generation, the replaced viruses are created by both individuals genetic material and have different genes quantities. In this approach, the search space maximization is increased by three mechanisms: high viral population genetic variability by variety of sizes to solutions pieces; infection validation process that confirms the fitness increases in each individual and infection possibility by any viruses in the viral population. To analyse the AGRI’s viral infection parameters effects and comparate his performance with others high-performing metaheuristics, the following minimization benchmarking are selected: F1 (Shifted Sphere Function), F2 (Shifted Schwefel’s Problem), F3 (Shifted Rotated High Conditioned Elliptic Function) e F5 (Schwefel’s Problem 2.6 with Global Optimum on Bounds). The results to the functions unimodais proposed showed that AGRI has a good performance in comparison with others metaheuristics reaching in few iterations the global best or good results.
Acesso aberto (Open Access)
Designing cost-efficient transport solutions for fixed and mobile broadband access network
(Universidade Federal do Pará, 2016-03-03) FARIAS, Fabrício de Souza; COSTA, João Crisóstomo Weyl Albuquerque; http://lattes.cnpq.br/9622051867672434
This thesis undertakes a techno-economic evaluation of transport solutions for fixed and mobile broadband access. In the case of future mobile access networks, it is proposed to make use of backhaul architectures using fiber and microwave applied to Greenfield deployments and a copper-legacy backhaul infrastructure based on Brownfield migration, i.e. finding a way of using a legacy infrastructure to its full capacity. At the same time, protection deployments based on fiber-wireless schemes are recommended for future fixed broadband. The main contribution made by this thesis is to carry out a research investigation into the total investment cost of the broadband transport infrastructure. This will be determined by employing two sets of models to assess the capital and operational expenditures, (CAPEX and OPEX respectively), of mobile and fixed broadband access network operators. First, this involves a set of models for mobile broadband that are summarized in a general methodology that aims at providing: traffic forecasting, wireless deployment, mobile backhaul deployment and total cost assessment. It was found that, fiber-based backhaul through a Greenfield deployment is the most energy-efficient option. Furthermore, Brownfield reveals that copper-based backhaul can still play a key role if used up to its full capacity and sharply reduces the investment costs in infrastructure. Additionally, there is an examination of the main differences in cost and energy values between Greenfield and Brownfield. Finally, a methodology is employed for fixed broadband based on network dimensioning, failure costs and an assessment of the total cost of ownership. The models are used to assess five architectures that represent different protection schemes for fixed broadband. This research shows the economic benefits of using a hybrid protection scheme based on fiber-wireless architecture rather than fiber-based protection options and a sensitivity analysis is conducted to show that the extra CAPEX invested to protect the infrastructure might be recovered through the OPEX after a number of years. The results obtained in the thesis should be useful for network operators to plan both their fixed and mobile broadband access network infrastructure in the future.
Acesso aberto (Open Access)
Estimação da porcentagem de flúor em alumina fluoretada proveniente de uma planta de tratamento de gases por meio de um sensor virtual neural
(Universidade Federal do Pará, 2011-06-22) SOUZA, Alan Marcel Fernandes de; OLIVEIRA, Roberto Célio Limão de; http://lattes.cnpq.br/4497607460894318; AFFONSO, Carolina de Mattos; http://lattes.cnpq.br/2228901515752720
The industries have been often seeking to reduce operating expenses, as to increase profits and competitiveness. To achieve this goal, it must take into account, among other factors, the design and implementation of new tools that accurately, efficiently and inexpensively allow access to information relevant to process. Soft sensors have been increasingly applied in industry. Since it offers flexibility, it can be adapted to make estimations of any measurement, thus a reducing in operating costs without compromising the measurements, and in some cases even improve the quality of generated information. Since they are completely softwarebased, they are not subjected to physical damage as the real sensors, and are better adaptated to harsh environments with hard access. The success of this king of sensors is due to the use of computational intelligence techniques, which have been widely used in the modeling of several nonlinear complex processes. This work aims to estimate the quality of alumina fluoride from a Gas Treatment Center (GTC), which is the result of gaseous adsorption on alumina virgin, using a soft sensor. The model that emulates the behavior of a alumina quality sensor the plant was created using an artificial intelligence technique known as Artificial Neural Network. The motivations of this work are: perform virtual simulations without compromising the GTC and make accurate decisions based not only on the operator's experience, to diagnose potential problems before they can interfere with the quality of alumina fluoride; maintain the aluminum reduction pot control variables within normal limits, since the production from low quality alumina strongly affects the reaction of breaking the molecule that contains this metal. The benefits this project brings include: increasing the GTC efficiency, producing high quality fluoridated alumina and emitting fewer greenhouse gases into the atmosphere and increasing the pot lifespan.
Acesso aberto (Open Access)
Estratégia para análise da concentração de infraestrutura de acesso às tecnologias da informação e comunicação nos municípios da Amazônia legal Brasileira
(Universidade Federal do Pará, 2016-03-31) BRITO, Silvana Rossy de; COSTA, João Crisóstomo Weyl Albuquerque; http://lattes.cnpq.br/9622051867672434; FRANCÊS, Carlos Renato Lisboa; http://lattes.cnpq.br/7458287841862567
Access to information is a fundamental right in democratic societies, essential for economic development, social equality, improvement of social, health care, education services and governance. This study is situated on the Concentration of Access to Information and Communication Technologies (ICT) in the municipalities of the Brazilian Legal Amazon. For this, we developed the conceptual model from which we identify the main variables of ICT infrastructure in urban and rural households. Our strategy is to (i) analyze the ICT infrastructure concentration in Brazilian municipalities; (ii) analyze the spatial distribution of ICT infrastructure concentration in urban and rural households in Brazilian municipalities; and (iii) search for associations between parameters describing the ownership of ICT resources in urban and rural households with indicators for income, education, population size, and the existence of electricity in municipalities. To understand these associations at the municipality level, we use Bayesian Networks to reveal dependencies among the variables studied. The results of applying the proposed strategy show that for urban households, the average concentration in the municipalities of the Amazon for computers and Internet access and for fixed phones is lower than in other regions of the country; meanwhile, that for no access and mobile phones is higher than in any other region. For rural households, the average concentration in the municipalities of the Amazon for computers and Internet access, mobile phones, and fixed phones is lower than in any other region of the country; meanwhile, that for no access is higher than in any other region. The study shows that education, income, and population size are determinants of inequality in accessing ICT in Brazilian households. In addition, we advance to analyze the association between teenage motherhood and the representative variables of income, education, and computer and Internet access in the municipalities of the Brazilian Legal Amazon compared to other regions of the country. These networks pointed to the region as the influential variable on the high percentages of teenage mothers and households with computer and Internet access.
Acesso aberto (Open Access)
Estratégia para predição de consumo de energia elétrica de curto prazo: uma abordagem baseada em densificação com MEAN SHIFT para tratamento de dias especiais
(Universidade Federal do Pará, 2016-11-04) RÊGO, Liviane Ponte; FRANCÊS, Carlos Renato Lisboa; http://lattes.cnpq.br/7458287841862567; SANTANA, Ádamo Lima de; http://lattes.cnpq.br/4073088744952858
The use of short-term prediction strategies is an important tool for planning and operation of electrical systems, playing a crucial part in aiding the decision support process for buying and selling of electricity in the future market. For the energy market, in particular, an important component to take into account for consumption forecasting are the special days (holidays or atypical days, for example). Given its unusual behavior, the estimation of such events can be a complex task, when compared to the forecasting of ordinary days. In addition, as they are often found with only a small number of samples, it is difficult to adequately train and validate prediction algorithms. To tackle these problems, this work presents a model for short-term load forecasting using the Information Theoretic Learning Mean-Shift model to clustering and densify the sample size of special days's events on a time series, there on followed by the prediction using statistical and/or machine learning algorithms; in this work represented by artificial neural network algorithms and multiple Linear regression. The model was applied in a load forecasting problem for the electric utility in the northern region of Brazil, providing an improvement in the accuracy of results.
Acesso aberto (Open Access)
Identificação e estimação de ruído em redes DSL: uma abordagem baseada em inteligência computacional
(Universidade Federal do Pará, 2012-01-25) FARIAS, Fabrício de Souza; COSTA, João Crisóstomo Weyl Albuquerque; http://lattes.cnpq.br/9622051867672434
This paper proposes the use of computational intelligence techniques aiming to identify and estimate the noise power in Digital Subscriber Line (DSL) networks on real time. A methodology based on Knowledge Discovery in Databases (KDD) for detect and estimate noise in real time, was used. KDD is applied to select, pre-process and transform data before data mining step. For noise identification the traditional backpropagation algorithm based on Artificial Neural Networks (ANN) is applied aiming to identify the predominant noise during the collection of information from the user's modem and the DSL Access Multiplexer (DSLAM). While the algorithm for noise estimation, linear regression and a hybrid algorithm consisting of Fuzzy with linear regression are applied to estimate the noise power in Watts. Results show that the use of computational intelligence algorithms such as RNA are promising for noise identification in DSL networks, and algorithms such as linear regression and fuzzy with linear regression (FRL) are promising for noise estimation in DSL networks.
Acesso aberto (Open Access)
Imitação da voz humana através do processo de análise-por-síntese utilizando algoritmo genético e sintetizador de voz por formantes
(Universidade Federal do Pará, 2015-12-18) ARAÚJO, Fabiola Pantoja Oliveira; KLAUTAU JÚNIOR, Aldebaro Barreto da Rocha; http://lattes.cnpq.br/1596629769697284
Voice imitation through the utterance copy mechanism is estimating the value of the input parameters of a speech synthesizer to generate a similar signal with the original voice. This process is distinct from the more traditional text-to-speech, but yet used in many areas, especially, Linguistics and Health System. Imitate the human voice through this mechanism is a difficult inverse problem because the mapping is non-linear and from many to one. For instance, there are different combinations of the synthesizer input parameters values that produce the same synthetic voice signal. Therefore, perform voice imitation manually requires a considerable amount of time. In addition to automatic methods are our interest of study as well, as proposed here. This work presents our system based on Genetic Algorithm (GA) to automatically estimate the value of the input parameters of a speech formant synthesizer using the analysis-by-synthesis process. Results are presented for synthetic (computer-generated) and natural (human-generated) speech in American English, for male and female speakers. These results are compared with the ones obtained with Winsnoori, the only currently available software that performs the same task. The experiments showed that the proposed newGASpeech framework is an effective alternative to the laborious manual process of estimating the input parameters values of a formant synthesizer. Besides it has overcome the quality of the generated voices by the baseline if compared to five objective metrics and a subjective evaluation applied to twenty seven no-expert listeners in the speech area neither the adopted language.
Acesso aberto (Open Access)
Inteligência computacional aplicada à detecção e correção de outliers em séries temporais: estudo de caso em consumo de energia elétrica
(Universidade Federal do Pará, 2015-09-04) MELO, Diemisom Carlos Romano de; CASTRO, Adriana Rosa Garcez; http://lattes.cnpq.br/5273686389382860
The electric load prediction is a task that requires accurate models, as should properly influence the decision making in hydroelectric plants and power stations. These computer models are implemented from a data set that must faithfully represent the behavior of the variables. However, these data sets are quite common the presence of outliers, which arise due to sensor reading errors, errors in the actual processing system / storage of data or faults in the distribution system or power station. This paper proposes a new methodology based on Computational Intelligence for detection and treatment of outliers in time series of electric power load. An auto associative artificial neural network is used for outlier detection. Subsequently, it is reused together with a genetic algorithm to correct detected outliers. This approach was applied to a time series of electrical power load in the State of Pará. The computational experiments were performed using the MATLAB tool and the results demonstrate the efficiency of the proposal, which identified and corrected all virtual outliers introduced during the evaluation phase of the methodology.
Acesso aberto (Open Access)
Machine learning algorithms for damage detection in structures under changing normal conditions
(Universidade Federal do Pará, 2017-01-31) SILVA, Moisés Felipe Mello da; SALES JÚNIOR, Claudomiro de Souza de; http://lattes.cnpq.br/4742268936279649; COSTA, João Crisóstomo Weyl Albuquerque; http://lattes.cnpq.br/9622051867672434
Engineering structures have played an important role into societies across the years. A suitable management of such structures requires automated structural health monitoring (SHM) approaches to derive the actual condition of the system. Unfortunately, normal variations in structure dynamics, caused by operational and environmental conditions, can mask the existence of damage. In SHM, data normalization is referred as the process of filtering normal effects to provide a proper evaluation of structural health condition. In this context, the approaches based on principal component analysis and clustering have been successfully employed to model the normal condition, even when severe effects of varying factors impose difficulties to the damage detection. However, these traditional approaches imposes serious limitations to deployment in real-world monitoring campaigns, mainly due to the constraints related to data distribution and model parameters, as well as data normalization problems. This work aims to apply deep neural networks and propose a novel agglomerative cluster-based approach for data normalization and damage detection in an effort to overcome the limitations imposed by traditional methods. Regarding deep networks, the employment of new training algorithms provide models with high generalization capabilities, able to learn, at same time, linear and nonlinear influences. On the other hand, the novel cluster-based approach does not require any input parameter, as well as none data distribution assumptions are made, allowing its enforcement on a wide range of applications. The superiority of the proposed approaches over state-of-the-art ones is attested on standard data sets from monitoring systems installed on two bridges: the Z-24 Bridge and the Tamar Bridge. Both techniques revealed to have better data normalization and classification performance than the alternative ones in terms of false-positive and false-negative indications of damage, suggesting their applicability for real-world structural health monitoring scenarios.
Acesso aberto (Open Access)
Uma metodologia biologicamente inspirada para projeto automático de redes neurais artificiais usando Sistemas-L paramétricos com memória
(Universidade Federal do Pará, 2016-08-26) CAMPOS, Lidio Mauro Lima de; ROISENBERG, Mauro; http://lattes.cnpq.br/5872119613051645; OLIVEIRA, Roberto Célio Limão de; http://lattes.cnpq.br/4497607460894318
This thesis proposes a hybrid neuro-evolutive algorithm (NEA) that uses a compact indirect encoding scheme (IES) for representing its genotypes (a set of ten production rules of a Lindenmayer System with memory), moreover has the ability to reuse the genotypes and automatically build modular, hierarchical and recurrent neural networks. A genetic algorithm (GA) evolves a Lindenmayer System (L-System) that is used to design the neural network’s architecture. This basic neural codification confers scalability and search space reduction in relation to other methods. Furthermore, the system uses a parallel genome scan engine that increases both the implicit parallelism and convergence of the GA. The fitness function of the NEA rewards economical artificial neural networks (ANNs) that are easily implemented. The NEA was tested on five real-world classification datasets and three well-known datasets for time series forecasting (TSF). The results are statistically compared against established stateof- the-art algorithms and various forecasting methods (ADANN, ARIMA, UCM, and Forecast Pro®). In most cases, our NEA outperformed the other methods, delivering the most accurate classification and time series forecasting with the least computational effort. These superior results are attributed to the improved effectiveness and efficiency of NEA in the decisionmaking process. The result is an optimized neural network architecture for solving classification problems and simulating dynamical systems.
Acesso aberto (Open Access)
Metodologia para o despacho de potência reativa visando o controle de tensão baseado em algoritmos genéticos
(Universidade Federal do Pará, 2009-06-06) ROCHA, Marcus Guerra da; NUNES, Marcus Vinícius Alves; http://lattes.cnpq.br/9533143193581447
This work aims to present a software to support the planning of power systems, through a methodology of voltage control and losses minimization, by the optimization of reactive injection, keeping the voltage in the bus between the established boundaries. The developed methodology is based in a hybrid system, that use artificial intelligence based in a genetic algorithm linked to a load flow software(ANAREDE), that interact to produce an optimal solution. The results showed that the technique based in a genetic algorithm is adequate to the problem of minimization the reactive losses.