Hydrocarbon use has been increasing and will continue to increase for the foreseeable future in even the most pessimistic energy scenarios. Over the past few decades, natural gas has become the major player and revenue source for many countries and multinationals. Its presence and power share will continue to grow in the world energy mix. Much of the current gas reserves are found in gas condensate reservoirs. When these reservoirs are allowed to deplete, the pressure drops below the dew point pressure and a liquid condensate will begin to form in the wellbore or near wellbore formation, possibly affecting production. A field optimization includes determining the number of wells, type (vertical, horizontal, multilateral, etc.), trajectory and location of wells. Optimum well placement has been studied extensively for oil reservoirs. However, well placement in gas condensate reservoirs has received little attention when compared to oil. In most cases involving a homogeneous gas reservoir, the optimum well location could be determined as the center of the reservoir, but when considering the complexity of a heterogeneous reservoir with initial compositional variation, the well placement dilemma does not produce such a simple result. In this research, a horizontal well placement problem is optimized by using a modified Genetic Algorithm. The algorithm presented has been modified specifically for gas condensate reservoirs. Unlike oil reservoirs, the cumulative production in gas reservoirs does not vary significantly (although the variation is not economically negligible) and there are possibly more local optimums. Therefore the possibility of finding better production scenarios in subsequent optimization steps is not much higher than the worse case scenarios, which delays finding the best production plan. The second modification is developed in order to find optimum well location in a reservoir with geological uncertainties. In this modification, for the first time, the probability of success of optimum production is defined by the user. These modifications magnify the small variations and produce a faster convergence while also giving the user the option to input the probability of success when compared to a Standard Genetic Algorithm.

Vehicle acoustic signals have long been considered as unwanted traffic noise. In this research acoustic signals generated by each vehicle will be used to detect its presence and classify its type. Circular arrays of microphones were designed and built to detect desired signals and suppress unwanted ones. Circular arrays with multiple rings have an interesting and important property that is constant sidelobe levels. A modified genetic algorithm that can work directly with real numbers is used in the circular array design. It offers more effective ways to solve numerical problems than a standard genetic algorithm. In classifier design two main paradigms are considered: multilayer perceptrons and adaptive fuzzy logic systems. A multilayer perceptron is a network inspired by biological neural systems. Even though it is far from a biological system, it possesses the capability to solve many interesting problems in variety fields. Fuzzy logic systems, on the other hand, were inspired by human capabilities to deal with fuzzy terms. Its structures and operations are based on fuzzy set theory and its operations. Adaptive fuzzy logic systems are fuzzy logic systems equipped with training algorithms so that its rules can be extracted or modified from available numerical data similar to neural networks. Both fuzzy logic systems and multilayer perceptrons have been proved to be universal function approximators. Since there are approximations in almost every stage, both of these system types are good candidates for classification systems. In classification problems unequal learning of each class is normally encountered. This unequal learning may come from different learning difficulties and/or unequal numbers of training data from each class. The classifier tends to classify better for a well-learned class while doing poorly for other classes. Classification costs that may be different from class to class can be used to train and test a classifier. An error backpropagation algorithm can be modified so that the classification costs along with unequal learning factors can be used to control classifier learning during its training phase. / Ph. D.

Submitted by Renata Lopes (renatasil82@gmail.com) on 2016-04-28T12:35:55Z No. of bitstreams: 1 karinalinomirandadeoliveira.pdf: 2833590 bytes, checksum: ce6010a8e780599c20721f9546fa946f (MD5) / Approved for entry into archive by Adriana Oliveira (adriana.oliveira@ufjf.edu.br) on 2016-06-02T15:19:31Z (GMT) No. of bitstreams: 1 karinalinomirandadeoliveira.pdf: 2833590 bytes, checksum: ce6010a8e780599c20721f9546fa946f (MD5) / Made available in DSpace on 2016-06-02T15:19:32Z (GMT). No. of bitstreams: 1 karinalinomirandadeoliveira.pdf: 2833590 bytes, checksum: ce6010a8e780599c20721f9546fa946f (MD5) Previous issue date: 2016-03-10 / CNPq - Conselho Nacional de Desenvolvimento Científico e Tecnológico / Dentre as diversas fontes de energia renovável, a energia eólica se destaca como uma das mais promissoras. Em meio ao cenário de crise energética em muitos países, crescimento da demanda, maior conscientização ambiental e maior exigência por uma energia de qualidade por parte das sociedades modernas, a energia eólica tem ganhado importância econômica e estratégica. No Brasil, os empreendimentos eólicos são contratados por meio de leilões através dos quais são declarados vencedores aqueles empreendimentos que ofertam o menor preço pela energia gerada. Este modelo vigente é responsável por acirrar a concorrência e, consequentemente, instigar a busca pela otimização das propostas. Considerando este aspecto, é de grande interesse o desenvolvimento de ferramentas computacionais que auxiliem profissionais a desenvolver projetos viáveis técnica e economicamente na fase de planejamento, e de preferência otimizados. Parques eólicos são compostos basicamente por aerogeradores, transformadores responsáveis por elevarem a tensão de saída das turbinas para níveis adequados de distribuição, cabos de média tensão e subestações. A construção da rede coletora de média tensão (rede interna), responsável pela interconexão de todos os aerogeradores e subestações, constitui parcela considerável dos custos globais, o que tem motivado diversos pesquisadores a publicar trabalhos que objetivam encontrar a melhor topologia da rede elétrica que, ao mesmo tempo, minimize os custos e respeite os critérios técnicos estabelecidos, tais como: radialidade, conectividade, variação da tensão nos barramentos, máxima condução de corrente pelo condutor (sobrecarga nos ramos), entre outras. Tendo em vista tais considerações, é proposto nesse trabalho um novo algoritmo de solução para otimização da rede coletora de média tensão de parques eólicos, englobando a determinação da topologia de conexão entre os aerogeradores e subestações e o dimensionamento dos condutores, baseado na utilização de um algoritmo genético modificado como método de otimização. Objetiva-se com esse método minimizar os custos com a aquisição de alguns equipamentos e com as perdas de energia ao longo de um horizonte de planejamento. O método proposto foi testado em parques eólicos fictícios e os resultados obtidos comprovam que o modelo elaborado pode ser utilizado para projetar uma arquitetura otimizada da rede de distribuição interna de parques eólicos. / Among the various sources of renewable energy, wind energy stands out as one of the most promising. Amid the energy crisis scenario in many countries, the demand growth, greater environmental awareness and greater demand for energy quality on the part of modern societies, wind energy has gained economic and strategic importance. In Brazil, wind projects are contracted by means of auctions through which are declared winners those projects that offer the lowest price for energy generated. This current model is responsible for increase competition and consequently instigate the search for optimization of the proposals. Considering this aspect, it is of great interest the development of computational tools to assist professionals to develop technical and economically viable projects in the planning stage, and preferably optimized. Wind farms are basically composed of wind turbines, transformers responsible for raise the output voltage of the turbines for adequate levels of distribution, medium voltage cables and substations. The construction of the medium voltage collector network (internal network), responsible for the interconnection of all wind turbines and substations, constitutes a considerable share of the overall costs, which has motivated many researchers to publish works that aim to find the best grid topology of the electrical network that, at the same time, minimizes costs and respects the technical criteria established, such as: radial configuration, connectivity, voltage variation in bus, current conduction maximum through the cable (overhead in the branches), among others. In view of these considerations, it is proposed in this paper a new solution algorithm to optimization of the medium voltage collector network of wind farms, comprising the determination of topology of connection between the turbines and substations and the sizing of conductors, based on the use of a modified genetic algorithm as optimization method. The objective of this methodology is to minimize the costs of acquisition of some equipment and energy losses over a planning horizon. The proposed method was tested on fictitious wind farms and the results show that the model developed can be used to design the optimized architecture of internal distribution network of wind farms.

The genetic algorithm (GA) is a popular random search and optimization method inspired by the concepts of crossover, random mutation, and natural selection from evolutionary biology. The real-valued genetic algorithm (RGA) is an improved version of the genetic algorithm designed for direct operation on real-valued variables. In this work, a modified version of a genetic algorithm is introduced, which is called a modified genetic algorithm with micro-movement (MGAM). It implements a particle swarm optimization(PSO)-inspired micro-movement phase that helps to improve the convergence rate, while employing the e'cient GA mechanism for maintaining population diversity. In order to test the capability of the MGAM, we firrst implement it on five generally used test functions. Then we test the MGAM on two typical nonlinear dynamical systems. The performance of the MGAM is compared to a basic RGA on all these applications. Finally, we implement the MGAM on the most important application, which is the plasma physics-based model of the solar wind-driven magnetosphere-ionosphere system (WINDMI). In order to use this model for real-time prediction of geomagnetic activity, the model parameters require up-dating every 6-8 hours. We use the MGAM to train the parameters of the model in order to achieve the lowest mean square error (MSE) against the measured auroral electrojet (AL) and Dst indices. The performance of the MGAM is compared to the RGA on historical geomagnetic storm datasets. While the MGAM performs substantially better than the RGA when evaluating standard test functions, the improvement is about 6-12 percent when used on the 20D nonlinear dynamical WINDMI model.