Navegando por Assunto "Algoritmos inteligentes"
Agora exibindo 1 - 4 de 4
- Resultados por página
- Opções de Ordenação
Item Acesso aberto (Open Access) Identificação de fácies em perfis com rede neural direta(Universidade Federal do Pará, 2015) GOMES, Kivia do Carmo Palheta; ANDRADE, André José Neves; http://lattes.cnpq.br/8388930487104926The application of coring techniques is usually carried out in a limited number of vertical wells drilled in an oil field, causing the rarefaction of facies descriptions and not allowing a realistic characterization of reservoirs. Increased production of hydrocarbons in an oil field is extremely important for the oil industry and deeply dependent on the knowledge of the reserves in accordance with their petrophysical properties, which vary depending on geological facies. A better description of facies may reflect more realistic estimates of hydrocarbon volumes. This dissertation presents an intelligent algorithm capable of producing the transport of geologic information produced by the facies analysis of cores to the non-cored wells in an oil field, through the design of a direct neural network trained to perform a mapping of geological information in terms of the physical properties registered in the well logs. The intelligent algorithm processes the result produced by the neural network through a depth coherence filter to locate the boundaries of the layers along the well trajectory. For all of our cases the intelligent algorithm presented results compatible with the core analysis and independent of the size of the training set.Item Acesso aberto (Open Access) Reconhecimento de fáceis em perfis geofísicos de poços com rede neural competitiva(Universidade Federal do Pará, 2015-02-27) COSTA, Jéssica Lia Santos da; ANDRADE, André José Neves; http://lattes.cnpq.br/8388930487104926The description of a depositional system based on the recognition of sedimentary facies is critical to the oil industry to characterize the petroleum system. In the absence of these facies description by cores or outcrop, we present a methodology based on intelligent algorithm able to identify facies of interest in wireline logs. This methodology uses a competitive neural network to extract geological information from the physical properties mapped in the M-N plot. The competition among neurons identifies the facies of interest, which have been previously identified in a cored borehole in other non-cored boreholes in the same oil field. The purpose of this methodology is to encode and transmit the geological information gained in cored boreholes to non-cored wells and thus achieve the geological interpretation of the facies of interest in an oil field. This methodology has been evaluated with synthetic data and actual wireline logs from two cored boreholes drilled in the Namorado oil field, Campos Basin, Brazil.Item Acesso aberto (Open Access) Solução da equação de Archie com algoritmos inteligentes(Universidade Federal do Pará, 2011) SILVA, Carolina Barros da; ANDRADE, André José Neves; http://lattes.cnpq.br/8388930487104926Archie equation is a historical mark of Formation Evaluation establishing a relationship among the physical properties and the petrophysical properties of reservoir rocks, which makes possible the identification and quantification of hydrocarbon in subsurface. Water saturation is the solution of Archie equation obtained from the measure of formation deep resistivity and porosity estimated. However, the solution of Archie equation is no trivial, in the dependence of previous knowledge of formation water resistivity and Archie exponents (cementation and saturation). This thesis introduces a set new intelligent algorithm to solve Archie equation. A modification of competitive neural network, nominated as bicompetitive neural network produces the log zonation. A new genetic algorithm with evolutionary strategy based in the mushrooms reproduction produces estimates for the matrix density, the matrix transit time and the matrix neutron porosity, which associated to a new rock model, produces realistic porosity estimates considering shale effects. A new model of competitive neural network, nominated as angular competitive neural network is able to accomplish the interpretation of Pickett plot, supplying the information about formation water resistivity and cementation exponent. All results of the methodology hereintroduced are presented using synthetic data and actual wireline logs and core analysis results.Item Acesso aberto (Open Access) Zoneamento de poços através da inferência Fuzzy(Universidade Federal do Pará, 2015-06-26) RUIZ TAPIA, Alberto José; ANDRADE, André José Neves; http://lattes.cnpq.br/8388930487104926Well zoning may be understood as the geological characterization (location and facies description) of each layer crossed by the borehole trajectory. Well zoning is a common activity in conventional core analysis and important for petroleum geology, assisting the construction of stratigraphic column and also for petroleum engineering aiding in the development of the well exploitation plan. This work presents a method for well zoning wells of non cored boreholes, so that the information gained in these wells can contribute to improve the knowledge of sedimentology and oilfield engineering. The method showed here uses the core description for building the knowledge base of a fuzzy inference system, which operates with P parameter (a new combination of density log and sonic log), parameter M (M-N plot) and the natural gamma ray log and the deep resistivity log. Operation of this fuzzy inference system using log data from non cored borehole produces the well zoning of each non cored borehole. This method is presented with synthetic data satisfying the petrophysical model and the Archie Law, and real data of two cored boreholes from the Namorado oilfield, in the Campos Basin.