In this work, an application of artificial intelligence in the oils & gas industry is developed to iden-tify flow patterns in horizontal and vertical pipes of two-phase flow of oil and water, normalizing the word information and converting it to numerical values through the development of an artifi-cial neural network, whose input layer is composed of the surface velocities of each fluid, the ve-locity of the mixture, the volumetric fraction of the substances, diameter and the inclination of pipelines and the oil viscosity. The Artificial Neural Networks (ANN) has two hidden layers composed of 45 neurons. The database with which the model was trained, validated, and tested has 6993 rows of information corresponding to the inputs of the intelligent system and particular-ized for annular flow in horizontal pipes and DO/W in vertical pipelines. Notice that the infor-mation was obtained after re-engineering the information presented by 12 and 18 authors for hor-izontal and vertical piping, respectively. Finally, the mean square error obtained by the model was around 1.38%, with a maximum coefficient of determination of 0.79.