3Faculty Engineering of Technology, Tarbiat Modares University, Tehran, Iran
In the level of preservation of oil wells in upstream oil industries, complicated experiments, called PVT are done for the recognition of reservoir fluid properties. The existence of problems such as probable dangers, be in time consuming, and samples inaccuracy and limitations in temperature and pressure have fostered the use of intelligent methods in this field. In this study, in order to avoid the mentioned problems and finding the complex and nonlinear relationships between data and PVT experiments, Artificial Neural Network has been used. In addition, as the suitable choice of the initial weights increases the Neural Network’s efficiency, Genetic Algorithm is used in order to adjust the initial weights. For evaluating the proposed approach, the Iranian oil reservoir fluid properties are implemented. The results of research showed that the use of Genetic Algorithm-based Artificial Neural Network, in contrast to the classical methods; predict the reservoir fluid properties in less time and with high accuracy. So, proposed Neural Network can be seen as a powerful approach for prediction of Iranian oil PVT properties.