Simulator Based Testing and Validation of a Drilling Optimization System

During the drilling operations, optimizing the rate of penetration (ROP) is very crucial, because it can significantly reduce the overall cost of the drilling process. ROP is defined as the speed at which the drill bit breaks the rock to deepen the hole, and it is measured in units of feet per hour or meters per hour. ROP prediction is very challenging before drilling, because it depends on many parameters that should be optimized. Several models have been developed in the literature to predict ROP. Most of the developed models used drilling parameters such as weight on bit (WOB), pumping rate (Q), and string revolutions per minute (RPM). Few researchers considered the effect of mud properties on ROP by including a small number of actual field measurements. This paper introduces a new robust model to predict the ROP using both drilling parameters (WOB, Q, ROP, torque (T), standpipe pressure (SPP), uniaxial compressive strength (UCS), and mud properties (density and viscosity) using 7000 real-time data measurements. In addition, the relative importance of drilling fluid properties, rock strength, and drilling parameters to ROP is determined. The obtained results showed that the ROP is highly affected by WOB, RPM, T, and horsepower (HP), where the coefficient of determination (T2) was 0.71, 0.87, 0.70, and 0.92 for WOB, RPM, T, and HP, respectively. ROP also showed a strong function of mud fluid properties, where R2 was 0.70 and 0.70 for plastic viscosity (PV) and mud density, respectively. No clear relationship was observed between ROP and yield point (YP) for more than 500 field data points. The new model predicts the ROP with average absolute percentage error (AAPE) of 5% and correlation coefficient (R) of 0.93. In addition, the new model outperformed three existing ROP models. The novelty in this paper is the application of the clustering technique in which the formations are clustered based on their compressive strength range to predict the ROP. Clustering yielded accurate ROP prediction compared to the field ROP.

Drilling performance is becoming the top differentiator in the market, especially in highly competitive US land basins. This drives operators to input more energy into the system with higher rev/min, flow, and weight on bit (WOB). In many cases this energy is transformed into drilling dysfunction (shock and vibration [S&V]) instead of higher rate of penetration (ROP). To minimize drilling dysfunction and maximize energy efficiency, a fully digital and closed-loop workflow was developed. The workflow begins with use of a proprietary at-bit sensor, which captures high-resolution at-bit measurements of three-axis acceleration, torsional vibration, and rev/min. The tool is placed inside any existing bit and does not require an additional sub, thus not introducing extra connections, bottomhole assembly (BHA) integrity risk, and/or length. The high-resolution data is automatically processed and analyzed to reveal critical drilling dynamics, which are replicated in a digital model. This creates a highly accurate virtual environment in which to evaluate bit design, eliminating the cost and risk of real-world trial and error, enabling efficient, fit-for-purpose introduction of new technologies. The new digital workflow was first used in a challenging, interbedded application in East Texas. High frequency at-bit measurements were used to develop a new bit and data-driven operating parameter roadmaps. These yielded improved drilling performance, with 69% higher ROP, better dull conditions, and 67% lower vibrations locally, when compared to the direct operator offsets. The workflow was then used in a curve/lateral application in the Permian Basin, known for challenging S&V conditions. Key performance targets were single-run to total depth (TD), high dogleg severity (DLS) output in the curve, and record ROP in the lateral. A new bit was designed, and recommended drilling parameters were defined within the data-driven virtual environment. Field testing confirmed the model’s predictions, with a 10% average increase in ROP. High-resolution at-bit downhole measurements coupled with digital simulation capabilities have led to development of a new workflow driving the evolution of drill bit design. Instead of the traditional trial and error approach that costs resources, time, and performance, the new workflow with data-enhanced digital modelling and virtual drilling environment enables increased confidence, optimized solutions, and decreased cycle time.

Summary Positive displacement motor (PDM) bottomhole assemblies (BHAs) are widely used in horizontal drilling due to their low cost and high rate of penetration (ROP) under rotary conditions. However, their limited-trajectory control ability often requires switching to sliding drilling for sharp corrections, which significantly reduces efficiency. Moreover, the quantitative relationship between build up rate (BUR) and controllable parameters such as revolutions per minute (RPM) and mud flow rate (MFR) remains unclear under rotary conditions. To address these issues, we propose a machine learning (ML)–based model predictive control (MPC) framework that regulates trajectory solely through real-time optimization of drilling parameters. A hybrid prediction model, integrating mechanical principles and ML, is developed to map weight on bit (WOB), RPM, and MFR to BUR, with a Lipschitz continuity constraint enhancing stability and robustness. The MPC objective function is improved by incorporating adaptive weighting, which accelerates convergence, reduces overshoot, and improves control consistency. The proposed method is evaluated across five simulation scenarios, which are analysis of control behavior, objective function enhancement, piecewise setpoint tracking, comparison with classical controllers, and robustness testing. The approach is validated using field data from a horizontal well in the Junggar Basin, northwest China. The results show that the ML-MPC strategy achieves accurate setpoint tracking under various conditions, maintains strong robustness to input noise, initialization variations, and measurement disturbances (with steady-state error < 0.2°/30 m), and meets real-time computation requirements (<20 seconds per control step). Analysis of the optimized control parameters provides data-driven insights into how WOB, RPM, and MFR influence BUR. Notably, a control inertia effect is observed: When the control objective aligns with the existing trend of variation, the system responds more efficiently; when it opposes the trend, the response becomes slower and more prone to overshoot. Overall, this work presents a practical framework for real-time trajectory control and contributes to the automation and intelligent drilling technologies in the oil and gas industry.

This study investigates the intricate relationship between bit rock interactions and drilling parameters for multiple-diameter hole drilling scenarios. Two sets of experiments were conducted in the Drilling Technology Laboratory at Memorial University of Newfoundland (DTL-MUN) using a fully instrumented Large-scale laboratory Drilling Simulator (LDS). The study contained two critical stages. Pre-coring operations using various diameter coring bits were completed to ensure thorough analysis. Next, drilling using a 5-cutter Polycrystalline Diamond Compact (PDC) bit with a larger diameter than all pre-cored holes, at constant Weight on Bit (WOB) and Revolution per Minute (RPM), was performed. The type of rock used in the experiments is a high-strength gabbro formation. Results indicate that pre-cored holes exhibited higher Rates of Penetration (ROP) than un-pre-cored holes, reflecting improved drilling performance and higher torque due to reduced bit–rock interaction area. A distinct relationship was observed between bit–rock interactions, torque, ROP, Mechanical Specific Energy (MSE), and applied WOB in multi-diameter drilling. ROP decreased as the pilot hole diameter decreased due to increased bit–rock interaction. The recorded data of WOB and the torque responses showed a decrease in amplitude as the bit–rock interface area increased, suggesting a positive interaction between drilling efficiency and downhole conditions. The modified Maurer model found a correlation between increased pilot hole diameter and decreased effective rock strength. These results highlight the significance of conducting a thorough drilling parameter analysis and the need for additional study to clarify the underlying mechanisms influencing drilling performance in multi-diameter hole drilling scenarios.

Establishment of data-driven multi-objective model to optimize drilling performance

The demands of the oil and gas industry are placing an increased importance on drilling harder, faster, and longer, giving rise to the challenge of premature bit failure due to drilling through transitions of varying rock strength. To address this, new strategies have become more prevalent, such as using automatic drillers operating with a constant rate of penetration (ROP). In this study, a method was developed to analyze the effects of drilling through transitions on bit cutting structures and construct an ideal drilling strategy to mitigate the forces overloading cutters using a detailed drilling model. A digital environment was created to model transitional drilling with the capability to predict downhole conditions when provided with various complex inputs. A polycrystalline diamond compact (PDC) bit design, including cutting structure and other features was first loaded into the model. The desired drilling parameters were provided, and the lithologies of the rock transitions throughout the interval were set. Drilling was then simulated within this digital environment, producing the bit performance data. The data included several high-level performance indicators, such as weight on bit (WOB), ROP, and torque, as well as detailed transient information on individual cutter loading and stress levels. Additionally, the simulation can be viewed as an animation to allow intuitive visualization of the effects of varying transitions on bit performance. By analyzing the outputs from the simulated transitional drilling, conclusions were drawn relating certain drilling parameters and rock strengths to areas of cutting structure damage. When drilling with a constant WOB, it was observed that transitioning from soft to hard formations causes a large increase in instantaneous forces on the cutters in the nose of the bit. In contrast, when transitioning from hard to soft formations, the forces are increased on the cutters in the cone and shoulder. These observations correlate with drilling data and field dull observations. It was found that when drilling with a constant downhole ROP, the cutting structure does not experience transient spikes in cutter loads. The loads approach a new steady state distribution based on the compressive strength of the newly entered formation with little to no overshoot. However, when drillstring compliance was accounted for it was found that drilling at a constant surface ROP can still lead to transient spikes in cutter loads, especially when transitioning from hard to soft formations. Transient load overshoot can be minimized through the use of depth of cut (DOC) limiting features when drilling from hard to soft formations. Based on these observations, the ideal strategy for drilling interbedded transitions is to use a customized cutting structure including DOC features and drill at constant, controlled ROP. These findings, along with the virtual environment and digital simulation capabilities, have the potential to save operators time and resources, and decrease the overall environmental impact of future oil and gas exploration.

This study compares the performance of artificial neural networks (ANN) trained by grey wolf optimization (GWO), biogeography-based optimization (BBO), and Levenberg–Marquardt (LM) to estimate the weight on bit (WOB). To this end, a dataset consisting of drilling depth, drill string rotational speed, rate of penetration, and volumetric flow rate as input variables and the WOB as a response is used to develop and validate the intelligent tools. The relevance test is applied to sort the strength of WOB dependency on the considered features. It was observed that the WOB has the highest linear correlation with the drilling depth and drill string rotational speed. After dividing the databank into the training and testing (4:1) parts, the proposed LM-ANN, GWO-ANN, and BBO-ANN ensembles are constructed. A sensitivity analysis is then carried out to find the most powerful structure of the models. Each model performs to reveal the relationship between the WOB and the mentioned independent factors. The performance of the models is finally evaluated by mean square error (MSE) and mean absolute error criteria. The results showed that both GWO and BBO algorithms effectively help the ANN to achieve a more accurate prediction of the WOB. Accordingly, the training MSEs decreased by 14.62% and 24.90%, respectively, by applying the GWO and BBO evolutionary algorithms. Meanwhile, these values were obtained as around 9.86% and 9.41% for the prediction error of the ANN in the testing phase. It was also deduced that the BBO performs more efficiently than the other technique. The effect of input variables dimension on the accuracy and training time of the BBO-ANN clarified that the most accurate WOB predictions are achieved when the model constructs with all four input variables instead of utilizing either three or two of them with the highest linear correlation. It was also observed that the training stage of the BBO-ANN model with four input variables needs a little more computational time than its training with either two or three variables. Finally, the accuracy of the BBO-ANN model for the WOB prediction has been compared with the multiple linear regression, support vector regression, adaptive neuro-fuzzy inference systems, and group method of data handling. The statistical accuracy analysis confirmed that the BBO-ANN is more accurate than the other checked techniques.

The oil and gas industry is constantly motivated to implement strategies focusing on cost management and operational optimization to maximize productivity. Rate of Penetration (ROP) serves as a key performance metric, reflecting the speed at which a drilling bit penetrates subsurface formations. Increasing ROP can minimize costs by reducing drilling time. ROP prediction models aid drilling optimization plans since accurate models are required to find ideal controllable parameters to increase ROP using optimization algorithms. Drilling characteristics that significantly influence ROP include bit type, formation properties, and operation parameters, such as Weight on Bit (WOB) and Rotations per Minute (RPM). The number of significant parameters makes it difficult to develop analytical expressions for predicting ROP. The present work investigates the applicability of Artificial Neural Networks (ANN) for ROP prediction using public data from three wells extracted from the Volve oil field in the North Sea. The adopted strategy is to learn from offset wells, which means using data from two wells to predict the ROP for the third. This approach helps to address a practical scenario where historical data are used to make predictions for a new well in a close region. This study uses MLP (Multilayer Perceptron) networks with WOB, RPM, Torque, Fluid Flow rate, and Delta-T Compressional as features, and the training process is conducted using the GridSearchCV method for hyperparameter tuning, comparing different model architectures to improve results. To assess the final performance of the model, metrics such as Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) are applied to the tested well. The results show that the developed model can capture ROP patterns without requiring any data stratification of the two wells regarding lithology information.

Drilling operations in the US Permian Basin shale play with a new 4-¾" Rotary-Steerable Drilling System (RSS) revealed that with high Rates Of Penetration (ROP), high Weight On Bit (WOB) (and other drilling parameters) encountering stringers or interbedded formations can lead to unwanted effects. The Bottom Hole Assembly (BHA) can be deflected before the steering unit with its steering pads can counteract the deflection. This can lead to deviations from the directional plan and High Local Doglegs (HLD) when drilling in the horizontal/lateral section, which can have a negative impact on the electronics within the steering unit. As a countermeasure, a combination of a pin-down connection steering unit with a short box-up connection drill bit, or Integrated Bit (IB), was developed. This combination allows a much shorter bit to steering pad distance. Due to the shorter bit-to-pad-distance an improved steering response is expected resulting in fewer high local dogleg occurrences. The integrated box-up bit basically moves the drive-shaft pin-down connection into the drill bit. The remaining bit shank is very short requiring modifications to the make-up and break-out procedure. Results from the data acquired in the Permian Basin shale play yielded promising results in terms of steering accuracy. When comparing bending cycle load vs. local Dogleg Severity (DLS), local DLS are typically lower and have less bending cycles drilling through these critical local DLS when IB were deployed. The overall average ROP of runs with IB is higher than the overall average ROP of runs with standard bits. The amount of data collected for this study allows a good statistical approach for comparison of the performance of a standard drilling BHA and bit versus a BHA featuring an IB. It proves that by further reducing the distance between the first formation contact point at the drill bit to the second contact point at the steering unit there is an overall improvement in performance and wellbore placement. This provides opportunities for incremental future optimization of the drill bit and BHA system.

Several directional wells have been drilled in Majnoon oilfield at wide variation in drilling time due to different drilling parameters applied for each well. This technical paper shows the importance of proper selection of the bit, Mud type, applied weight on Bit (WOB), Revolution per minute (RPM), and flow rate based on the previous wells drilled. Utilizing the data during drilling each section for directional wells that's significantly could improve drilling efficiency presented at a high rate of penetration (ROP). Based on the extensive study of three directional wells of 35 degree inclination (MJ-51, MJ-52, and MJ-54) found that the applied drilling parameters for MJ-54 and the bit type within associated drilling parameters to drill 36", 24", 16" and 12 1/4" hole sections is the best, although the drilling parameters in 8 1/2" hole section for MJ-51 and selected bit type are the best for future wells.

One key objective in drilling is to maximize rate of penetration (ROP) while minimizing downhole vibrations and avoiding wellbore instability. ROP is sensitive to surface parameters like weight on bit (WOB), rotation speed, and flow rate. These must be carefully chosen to balance penetration rate and stability in avoiding drilling dysfunctions. This study presents an optimization algorithm combining machine learning (ML) and predictive vibration modeling to identify optimal parameters, which are then automatically transmitted to the rig for execution by the autodriller system. Combining physics-based modeling with machine learning enables rapid adaptation to actual drilling conditions, such as trajectory, formation characteristics, and well status, while ensuring predictions remain physically consistent. The approach includes predictive vibration modeling that computes resonant frequencies in axial, torsional, and lateral directions, generating a stable surface rotation speed roadmap. Simultaneously, a machine learning model predicts ROP, differential pressure, and surface torque from rotation speeds and WOB. Trained on data from 1000 wells and updated with live drilling data to ensure a better fit to the current well conditions. These models feed into an optimization algorithm that balances ROP maximization and MSE (Mechanical Specific Energy) minimization while respecting operational constraints and minimizing risks. The ML model is validated on historical data for which the predictions matched the actual measurements with high accuracy, reflecting its strength and generalization capability. The optimization algorithm is further validated on simulated wells, where the optimal drilling conditions are known in advance. The results show a successful identification of the optimal set of drilling parameters by the model, despite the inherent disparities between the training wells and the test environment. This confirms the capability of the proposed framework to adapt to real-time drilling conditions. The strength of the newly proposed methodology lies in its integration with the rig control system, which receives operating recommendations at regular intervals defined by the driller, who retains the ability to take back control whenever necessary. This application integrates physics-based modeling with machine learning techniques to optimize the ROP and minimize vibrations, resulting in more consistent drilling performance and a significant reduction in dysfunctions, ultimately saving valuable time for operators.

This article, written by Special Publications Editor Adam Wilson, contains highlights of paper SPE 172935, “Hydraulic Percussion Drilling System With PDC Bit Increases ROP and Lowers Drilling Costs,” by Scott W. Powell, NOV, and Ertai Hu, Greatwall Drilling Company, prepared for the 2015 SPE Middle East Unconventional Gas Conference and Exhibition, Muscat, Oman, 26–28 January. The paper has not been peer reviewed. Drilling the Severnaya Truba field in Aktobe, Kazakhstan, has been costly and time consuming. In combination with a drilling-fluid-powered percussion hammer (FPPH), a fit-for-application polycrystalline-diamond- compact (PDC) bit with depth-of-cut (DOC) -control features was used to minimize the exposure of the cutting structure and prevent breakage. The mechanical lifting and falling action creates a rapid variation in weight on bit (WOB), allowing the bit’s DOC to fluctuate while overcoming different stresses. These variations, along with the percussion pulse created with each stroke, led to increased rates of penetration (ROPs). Introduction Drilling with an air hammer is a technique whereby gases (typically compressed air or nitrogen) are used to operate a pneumatic hammer, to cool the drill bit, and to lift cuttings out of the wellbore. Air forced down the drillstring actuates the percussion tool, which, in turn, creates an axial percussion force directed down to a specially designed drill bit. The advantages of air drilling are that it is usually much faster than using drilling fluid and may eliminate lost-circulation problems. The disadvantages are the inability to control the influx of formation fluids into the wellbore and the destabilization of the borehole wall in the absence of wellbore pressure typically provided by the mud column. Air hammers are also limited to a lower WOB and will stop working if that weight is exceeded. An FPPH is the next step in performance drilling. Using the same flow rates and operating WOB of a conventional assembly, the tool offers the benefit of an axial percussion force to facilitate the cutting action of the bit. Like an air hammer, the axial percussion force is generated near the bit to give the cutting structure more energy and overcome the formation’s compressive strength.

Salt is typically underreamed in the deepwater Gulf of Mexico wells to manage equivalent circulating density (ECD) and creep. Rapidly drilling the long salt sections is an opportunity to significantly reduce the overall drilling time and cost of deepwater wells. Rapid penetration rates while under-reaming through salt have been achieved by running near maximum torque with high weight on bit (WOB) and rotation speeds (RPM). However, the consequence of these parameters is high vibration and an increased potential for downhole tool failure. The operator's well was located in over 3000 feet of water in Mississippi Canyon and the well plan included a hole-enlargement-while-drilling (HEWD) interval opening a 12-1/4?? pilot hole to 14-3/4?? from 13,000ft MD to the base of the salt at 21,222ft MD while building angle at 1.5°/100ft, holding tangent for 4500ft and dropping back to vertical. The formation was evaluated using sonic and gamma ray offset data to confirm the interval was homogeneous salt. To optimize the penetration rate while maintaining low vibration, the service provider utilized proprietary technologies to assess the drill bit, BHA and drilling parameters using laboratory data derived from physical testing of salt formations. The BHA was assessed using finite element simulation software to model the behavior of the drillstring and BHA, including the bit and reamer as a drilling system in the geometry of the wellbore. An optimization process was followed to determine sequentially the allowable surface torque, fastest penetrating drill bit, most stable BHA and finally optimized parameters. The process involves running hundreds of iterations using different BHA configurations and parameter combinations in a virtual environment. The parameters were checked for optimization at specific measured depths representing build, tangent and drop sections of the interval. In the simulated BHA, the recommended weight on bit was limited to maintain the neutral point below the heavy weight drill pipe (HWDP) and the torque was restricted to a factor of safety below the make-up torque of the drill pipe. Two candidate PDC bits were modeled for ROP, torsional oscillation and surface torque. Four BHA combinations were simulated using different stabilizer configurations. The optimal BHA was selected based on evaluation of lateral bit/reamer vibrations, stick-slip and torsional oscillation. The dynamic parameter analysis used permissible bit and reamer vibration levels, torsional oscillations and surface torque to determine the maximum recommended parameters of 30 klbs WOB and 150 RPM in salt. The parameter analysis was conducted for the vertical section which encountered transitions of sub-salt and parameters of 20klbf WOB & 125 RPM were recommended The operator ran the recommended BHA and documented an increase of 24% in ROP compared to the vertical offset well. Excluding the directional portions, the increase in penetration rate was 43%. This resulted in 13.4 hrs of reduced drilling time saving the operator $558,000USD. Introduction Sub-salt exploration in the Gulf of Mexico (GoM) routinely requires drilling through salt sections in excess of 6000ft. As these salt-sections account for a significant portion of the total drilled depth, it is necessary to drill them efficiently. Due to the higher fracture gradient of salt, it is possible to drill these long sections without intermediate casings. However, the length of these sections coupled with the tendency of salt to creep can introduce problems with tight spots while running casing.

In the oil and gas drilling industry, optimizing key operational parameters—such as weight on bit (WOB), rate of penetration (ROP), and Revolutions Per Minute (RPM)— is essential for maximizing drilling efficiency, minimizing costs, and ensuring operational safety. Drilling environments are highly dynamic, influenced by constantly changing geological formations, mud properties, and downhole conditions. This research addresses the critical need for real-time optimization of drilling parameters. Despite significant advancements in drilling automation, many existing systems still lack the adaptability to respond effectively to changing downhole conditions and transparency in decision-making. This study proposes an adaptive machine learning (ML) and optimization model framework to bridge this gap. The goal is to both validate the performance of models in dynamic drilling environments and assess how interpretability methods can foster operator trust. Using the dataset provided, the framework simulates real-time adaptability through an offline, condition-segmented analysis approach. The dataset is divided into subsets representing distinct drilling conditions, such as variations in depth or Mud Weight (MW). For each condition, regression and time series models are trained to predict the rate of penetration, and an optimization algorithm is then implemented to continuously provide optimum controllable parameters, for maximum penetration rates within safe Formation Pressure ranges. The results show significant improvements in drilling efficiency and cost reduction, demonstrating the potential of the proposed framework for real-time optimization. Additionally, the study highlights the importance of integrating ML and optimization techniques in drilling operations, enabling more accurate and informed decision-making, and paving the way for further advancements in autonomous drilling systems and digital transformation in the oil and gas industry, with potential applications in various drilling scenarios.

On most onshore rigs, weight on bit (WOB) is usually obtained from the deadline hook load measured by deadline the sensor installed on the deadline of the block-and-tackle system. To obtain a more accurate WOB, a measurement tool, called torque and tension sub (TTS), has been developed to measure the load below the quill of a top-drive system. Theoretically, the load from the TTS, called the TTS hook load, is more accurate than the deadline hookload because the TTS measurement is not affected by the friction between the drilling lines and sheaves and the top drive rails. The downhole weight on bit (DWOB) is a key parameter in optimizing rate of penetration (ROP) and drilling optimization because accurate DWOB plays a very important role in improving the overall performance of a bit run. The objective of the work presented herein is to acquire rig parameters such as sheave efficiency, static weight of travelling block and friction between top drive and the rail by using theoretical analysis and regression analysis of acual drilling data. These parameters can further be used for DWOB automation calculation, which will greatly improve the overall drilling efficiency and save drilling cost. A set of drilling data was collected from a well in western Canada, including bit depth, hole depth, deadline hookload, TTS hookload, surface measured WOB and standpipe pressure. Force analysis to the upper part of a top drive system was conducted, and a theoretical equation derived which reflects the relationship between the deadline hook load and the TTS hook load. An empirical relationship is also obtained by regression analysis of the drilling data. The results show that there is a good agreement between the theoretical equation and the empirically-derived relationship. Therefore, the empirical relationship can be used to get the sheave efficiency, static weight of travelling block and friction between the top drive and the rail. The relationship between the deadline hook load and TTS hook load established in this paper brings about a new method to acquire rig parameters which are usually obtained by experience or a rule of thumb. This will potentially improve the calculation of DWOB automation. The proposed new correlation method will find a wide range of potential applications, such as on new types of automation drilling systems being developed in the drilling industry, which is especially suitable for horizontal drilling.