The researchers in the drilling engineering fields are always looking for the prediction of unexpected events and optimizing the related parameters. Predicting the Rate of Penetration (ROP) is of a great attention for drilling engineers due to its effect on the optimization of various parameters that leads to reduction of the costs. Artificial neural network (ANN) has an efficient capability of combining different parameters to predict different situations. According to ANN structure, it can get the effective parameters as the inputs to predict and evaluate the value of the target parameter(s) as an output. Since formation type and rock mechanical properties, hydraulics, bit type and its properties, weight on the bit and rotary speed are the most important parameters that affect ROP, they have been considered as the input parameters to predict ROP. In this study, ROP has been investigated and predicted in one of Southern Iranian oilfields through an ANN model. Finally, ROP has been predicted prosperously by the developed ANN which has been checked with the field measurements of drilled wells. The results indicate the efficiency of ANN in this field which can be used in drilling planning and real-time operation of any oil and gas wells in the related field that can result in costs reduction.
Analyzing real-time data is an efficient tool for improving drilling operation which leads to reduction in drilling costs. For developing advanced real-time analysis, rate of penetration (ROP) prediction is always one the most key aspects among drilling engineers, because it makes the possibility to optimize drilling parameters to achieve the minimum cost per foot Drilling optimization using ROP models is done by changing the drilling parameters and/or bit design to find the optimum drilling scenario for an entire bit run [1, 2].
