Most of drilling hole problems are attributed to wellbore stability issues which adversely cause excessive lost time and cost millions of dollars. The past drilling experiences in Kupal oilfield showed excessive mud losses, kick flows, tight holes and pipe stuck leading to repeated reaming, fishing and sidetracking. Most of the drilling-associated problems in this field occurred during drilling the 12 ¼-in. hole, which is across the non-reservoir Gachsaran formation (consisting of anhydrite, gypsum and marl with thin limestone layers). Mainly due to the lack of required formation evaluation data, no geomechanical studies of this formation have been conducted to date. In this work, first, we constructed a geomechanical model to investigate the root of the problems. This is a pioneer wellbore stability work for such a complex lithology formation which included finding the equations best-matching with core data and field observations. Finally, to overcome the field challenges and hole problems, the study proposes some field remedial actions. The results of the geomechanical modeling show that the pore pressure, shear and tensile failure gradients are greatly variable with the safe mud weight window becoming excessively narrow at some intervals. This accounts for the encountered wellbore stability issues as managing the mud weight in these situations requires several casing strings. To mitigate the extent of the problem, this study proposes the application of innovative drilling technologies including casing while drilling to eliminate the casing running time with potential reduction in drilling time, and continuous circulation system to prevent cuttings settling and kick flows during connections. These technologies are capable of elimination of the geomechanical part of the drilling delay (30% of the average 77 drilling days) per well.

Several mathematical ROP models were developed in the last five decades in the petroleum industry, departing from rather simple but less reliable R-W-N (drilling rate, weight on bit, and rotary speed) formulations until the arrival to more comprehensive and complete approaches such as the Bourgoyne and Young ROP model (BYM) widely used in the petroleum industry. The paper emphasizes the BYM formulation, how it is applied in terms of ROP modeling, identifies the main drilling parameters driving each subfunction, and introduces how they were developed; the paper is also addressing the normalization factors and modeling coefficients which have significant influence on the model. The present work details three simulations aiming to understand the approach by applying the formulation in a presalt layer and how some modification of the main method may impact the modeling of the fitting process. The simulation runs show that the relative error measures can be seen as the most reliable fitting verification on top ofR-squared. Applying normalization factors and by allowing a more wide range of applicable drillability coefficients, the regression could allow better fitting of the simulation to real data from 54% to 73%, which is an improvement of about 20%.

Over the past decade, several methods and techniques have been proposed to optimize drilling hydraulic's in real-time; one of these techniques is machine learning, which has shown promising results in prediction and optimization. Nevertheless, the real-time implementation of these techniques is still challenging since most of the published work tried to perform prediction tasks rather than the optimization task. In this regard, this paper tries to tackle the shortcomings of the recently published related methods by presenting a holistic model, based on a machine learning concept, focused on real-time optimization of drilling hydraulic's within a sufficiently short time span and without disturbing the drilling process. The presented approach relies on using two interconnected models to achieve the goal, which can be classified into, data-driven and analytical models. The real-time optimization process starts by using two predictive models to predict standpipe pressure and annular pressure losses and an analytical model to compute the drill-string pressure loss. Subsequently, the three generated values are used by an optimizer algorithm to generate the optimum combinations of surface drilling parameters, namely, weight on bit, flow rate, and rotation per minute, which are expected to optimize drilling hydraulic. Two case studies were conducted based on a historical drilling data set to assess the performance of the utilized predictive models and to measure the time required for the model to perform an optimization task. The results reveal that the predictive model demonstrated very high accuracy in terms of predicting SPP and APL as indicated by the determination coefficient value (R²), which was between 0.87 and 0.99. Moreover, the overall simulation time was within a range of between 2 to 4 minutes, which is considered a rational time frame for a real-time optimization task. The methodology applied allowed us to conclude, even showing some limitations, that machine learning techniques can be well used for hydraulic optimization in real-time.