Journal de génie chimique avancé

Abstrait

Mathematical Modeling of Alagoas well Density using Artificial Neural Networks

Tatiana G.D Da Silva, Everton Lourenco, Marcio A. Sampaio Pinto’s, Dheiver Santos

Density is a physical-chemical characteristic that is commonly applied to analyze the quality of oil and is fundamental to the sizing and application of equipment, which makes processes more efficient. The same is used during production and oil refining to verify the properties of the oil to be explored. Therefore, this work analyzed oil samples from the Sergipe-Alagoas basin, from the Pilar and Tabuleiro do Martins fields, through the characterization of the density and the training and prediction through Artificial Neural Network (ANN). The research showed that the data obtained from the oil density of the Sergipe-Alagoas Basin were in the light oil frame, and that from the analysis performed on the ANN the desired output data are very close to the network output. Therefore, the characterization of density becomes fundamental in several industrial processes where there is fluid transfer from one place to another, besides being indispensable to find useful techniques for an adequate flow.