Automated Hole Cleaning Model for Vertical and Directional Wells Improves Drilling Efficiency

Abstract

Abstract: Hole cleaning is a major factor in drilling hydrocarbon wells in a safe and competent manner with cost effectiveness. Hole cleaning contributes to minimizing drilling troubles such as stuck pipe incidents and avoiding well loss if hole cleaning is not managed properly. Ensuring adequate hole cleaning efficiency will help drill fast with a smooth rate of penetration (ROP) with the desired drill cuttings transport. In this paper, a new real-time hole cleaning model is developed to evaluate and monitor hole cleaning effectiveness while drilling and ensure drilling efficiency optimization with high quality and economics in a safe and environmental manner. Moreover, an artificial intelligence (AI) tool, an artificial neural network (ANN), was applied to confirm and validate the selected parameters of the model to show similar real-time profiles. The methodology to develop a real-time hole cleaning model is based on the carrying capacity index that was developed earlier only for vertical wells. The original carrying capacity index will be optimized and enhanced to consider other mechanical drilling parameters and drilling fluid rheological properties. The model will account for the wellbore inclination, average hole cleaning annular, cuttings, hydraulic velocities based on the impact of cutting accumulation, jetting drill bit nozzles, mud rheology, gravity, ROP, temperatures, pressures and altered drilling fluid viscosities with rig and bit hydraulics. Many offset mechanical drilling parameters and drilling fluid properties were collected to study the influences and relationships on the hole cleaning efficiency and rate of penetration. The developed model will be fed by the real-time values of the sensors of the drilling rig and generate a real-time profile of the hole cleaning efficiency for evaluating, monitoring, and improving the ROP by allowing immediate intervention by the drilling team while drilling operations. The model can be used in the planning phase and different drilling scenarios to have an evident imagination of downhole cleaning effectiveness. On the other hand, ANN application was run by selecting inputs of mud pump flow rate (Q), standpipe pressure (SPP), rate of penetration (ROP), plastic viscosity (PV), yield point (YP), mud weight (MW) and low shared yield point (LSYP), which were collected and used for a total of 5563 real-time readings. The newly developed real-time model was applied in the field in vertical and directional hole sections with water base mud and oil base mud to improve the rate of penetration (ROP) and evaluate the capability of mud rheological properties to effectively transport drill cuttings. The drilling efficiency was obtained, and the ROP improved by 55%. The ANN model showed regressions R2 0.961 and 0.956 with absolute average percentage errors (AUEs) of 2.595 and 2.621 for training and testing validations, respectively. The real-time model was applied as well in real-time offset well parameters and confirmed the importance of the real-time hole cleaning model. The real-time hole cleaning model can ensure consistency of evaluation, monitoring, and optimization for the drilling operation in real time bases by using real-time values of sensors available in all drilling rigs. The model can interpret the downhole measurements and give clear indications about hole cleaning efficiency.