Application of Artificial Intelligent Systems in ROP Optimization: A Case Study in Shadegan Oil Field

Abstract

Abstract According to the field data, there are several methods to reduce the drilling cost of other wells. One of these methods is the optimization of drilling parameters to obtain the maximum available ROP. Considering the geology and rock mechanic parameters, each part of well has different recommended parameters. There are too many parameters affecting in rate of penetration like hole cleaning (including drillstring rotation speed, mud rheology, weight on bit and floundering phenomena), tooth wear, formation hardness (including depth and kind of formation), differential pressure (including mud weight) and etc. Therefore, developing a logical relationship among them to assist in proper ROP selection is extremely necessary and complicated though. In such a case, Artificial Neural Networks (ANNs) is proven to be helpful in recognizing complex connection between these variables. Genetic Algorithm (GA), as a class of optimizing methods for the complex functions, is applied to help ROP optimization and its related drilling parameters. Optimization program will optimize drilling parameters which will be used in future works and also leads us to proper time estimation. The present study is predicting the proper penetration rate, optimizing the drilling parameters, estimating the drilling time of well and eventually reducing the drilling cost for future wells.