Modeling and Optimizing Rate of Penetration Using Intelligent Systems in an Iranian Southern Oil Field (Ahwaz Oil Field)

Abstract

For drilling optimization, an equation for the rate of penetration (ROP) is necessary. The rate of penetration depends on many factors such as formation properties, mud properties, weight on the bit, rotary speed, mud hydraulics, and size/type of bit. Due to the difficulty of mathematical modeling of ROP, researchers have used experimental results or field data to develop a correlation for ROP. In this study, a new model based on artificial neural networks (ANNs) is designed that is able to predict the ROP using real field data gathered in an Iranian oilfield (Ahwaz oilfield). The new model was successful in predicting ROP. To obtain operating parameters that lead to maximum ROP, the corresponding mathematical equation of an ANN model was implemented in a procedure using a genetic algorithm, which is one of the most reliable methods of optimization, and at different depths the parameters leading to maximum ROP were obtained. This model and its results can be used in Pabdeh and Gurpi formations in all Iranian oilfields and similar shaly formations in the Middle East such as the Iraq, Jaddia, and Aaliji formations corresponding to the Pabdeh formation and the Shiranish formation corresponding to Gurpi.