Drilling Parameters Research Articles

Advancing Geotechnical Evaluation of Wellbores: A Robust and Precise Model for Predicting Uniaxial Compressive Strength (UCS) of Rocks in Oil and Gas Wells

This study examines the efficacy of various machine learning models for predicting the uniaxial compressive strength (UCS) of rocks in oil and gas wells, which are essential for ensuring wellbore stability and optimizing drilling operations. The investigation encompasses Linear Regression, ensemble methods (including Random Forest, Gradient Boosting, XGBoost, and LightGBM), support vector machine-based regression (SVM-SVR), and multilayer perceptron artificial neural network (MLP-ANN) models. The results demonstrate that XGBoost and Gradient Boosting offer superior predictive accuracy for UCS in drillability, as indicated by low Mean Absolute Percentage Error (MAPE) values of 3.87% and 4.18%, respectively, and high R2 scores (0.8542 for XGBoost). These models emerge as optimal choices for UCS prediction focused on drillability, offering increased accuracy and reliability in practical engineering scenarios. Ensemble methods and MLP-ANN emerge as frontrunners, providing valuable tools for improving wellbore stability assessments, optimizing drilling parameter selection, and facilitating informed decision-making processes in oil and gas drilling operations. Moreover, this study lays a foundation for further research in drillability-centred predictive modelling for geotechnical parameters, advancing our understanding of rock behaviour under drilling conditions.

THE EVOLUTION OF A CLAY CRUST IN A BOREHOLE

Based on the previously proposed quasi-stationary model of clay crust formation when drilling wells in depth intervals with permeable rocks, software was created and computational experiments were performed, which made it possible to clarify the contribution of various physical parameters to the process of its growth.Based on the analysis of the results of computational experiments, the contribution of the physical parameters of the formation and clay crust to the dependence of its size on time has been clarified. The model assumes that the filtration pressure fields are described by stationary piezo conductivity equations. This made it possible to construct explicit dependences of pressure, thickness of the clay crust, radius of the zone of pressure disturbances in the reservoir during drilling and other parameters on time. Simple approximate formulas have been found for the dependence of the thickness of the clay crust, the filtration rate and the radius of the pressure disturbance zone in the reservoir on time, which describe their evolution with high accuracy.Based on the analysis of the calculation results, it was found that the thickness of the clay crust significantly depends on the permeability of the reservoir and repression, and these parameters determine the process of its formation. The porosity of the collector makes a smaller contribution, and the filtration and capacitance parameters of the clay crust have little effect on its thickness.New possibilities for estimating the physical parameters of reservoirs based on cavernometry have been identified. The solution of this problem is especially important for horizontal wells, in which the clay crust intervals have a significant length, and its formation occurs under conditions of a wide range of reservoir properties of the formation. The considered problem is of practical importance, since the zone of penetration of drilling mud filtrate into the formation has a screening effect on the use of geophysical methods to determine reservoir saturation. The results obtained can be used both to improve the interpretation of geophysical methods and to develop those.When conducting computational experiments using an exact formula, the stochastic behavior of the calculated curves was found. It was found that the noted effect is associated with rounding error, and in this sense is a manifestation of the features of the processor. An approach is proposed to eliminate the detected stochastic errors.

Hole drilling in basalt-reinforced sustainable composites using abrasive waterjet for construction applications

This study aimed to develop, characterize, and optimize abrasive waterjet (AWJ) machining of sustainable basalt fiber-reinforced polymer composites for construction and industrial applications. Dynamic mechanical analysis, thermogravimetric analysis, and X-ray diffraction revealed enhanced thermal stability, increased decomposition temperatures, and improved crystallinity, correlating with improved tensile strength of developed composites. To address drilling-induced damage that can compromise long-term quality and applicability, AWJ drilling parameters were optimized to minimize damage while enhancing material removal rates. A novel quantification method for entry total surface damage (ETD) was implemented to assess machining defects. Results showed that standoff distance significantly influences ETD and exit delamination, while higher water pressure reduces entry damage. Abrasive flow rate primarily affected the material removal rate. FE-SEM analysis revealed microstructural changes in drilled surfaces, including damage zones and matrix fractures specific to AWJ processing. Multi-objective optimization using Genetic Algorithm is performed to enable flexible parameter selection and informed decision making, balancing machining efficiency and minimal damage.

Effect of micro-electrical discharge drilling parameters on machining responses during machining of Al/(SiC/ZrO2/NiTi)-MMC

Effect of micro-electrical discharge drilling parameters on machining responses during machining of Al/(SiC/ZrO₂/NiTi)-MMC

Evaluation and optimization of drilling efficiency while drilling based on improved rock-breaking specific energy model of bit

Rock-breaking specific energy model of bit is the key foundation of evaluation and optimization of downhole drilling condition, while some necessary parameters for the existing models is difficult to measure directly while drilling. Aiming to improve the accessibility and accuracy of the model, this study proposes and illustrates an improved method by combining field tests and logging while drilling. The improved model was used to distinguish the inefficient drilling conditions and then to optimize drilling parameters. The results of application cases show that, the necessary parameters for the improved model could be obtained in time and the improved model helps to distinguish the reasons of stick–slip, whirling, load transfer difficulties in different horizontal wells. Based on the proposed model, the drilling parameters were evaluated and optimized, and then the rate of penetration get improved by 90.5% with higher energy efficiency. The proposed model and method could facilitate to realize automated and intelligent drilling.

Study on the Stress Distribution Characteristics of Rock in the Bottomhole and the Influence Laws of Various Parameters Under the Impact of a Liquid Nitrogen Jet

This study presents research on the stress distribution characteristics of rock in the bottomhole and the influence laws of various parameters under the impact of liquid nitrogen jet. A multi-field coupled numerical model considering transient flow field, conjugate heat transfer, and nonlinear solid deformation was established to investigate the damage-induced fracturing mechanism of rock under liquid nitrogen jet. The study compares the impact effects of liquid nitrogen jet and water jet on rock and analyzes the variations in the stress field under different parameters. Due to its extremely low temperature, the liquid nitrogen jet creates a strong thermal stress gradient in a short time, significantly increasing the maximum principal stress and Mises stress in the rock compared to a water jet. Solid parameters, particularly the confining pressure and elastic modulus of the rock, have a more significant impact on stress distribution, while fluid parameters such as outlet pressure and fluid temperature have a smaller and more volatile effect. An increase in confining pressure inhibits tensile failure in the rock, while a higher elastic modulus enhances both tensile and shear failure. The initial rock temperature significantly affects the stress distribution, with optimal tensile failure observed at intermediate temperatures. The liquid nitrogen jet achieves a higher maximum velocity and overflow velocity than the water jet, contributing to more effective rock fracturing. The results provide a theoretical basis for the optimization of liquid nitrogen jet drilling parameters, which can help improve drilling efficiency.

Rational parameters of drilling and blasting works providing the least costs of ore mining and processing

Отгрузка разрушенной горной массы требуемого качества и количества на обогатительную фабрику является одной из основных задач подготовительных работ при добыче полезных ископаемых. Основным способом регулирования этого процесса является оптимизация параметров и технологий ведения буровзрывных работ. На Актогайском месторождении возникла проблема с увеличением крепости добываемой руды по мере углубления карьера, что сильно влияет на производительность обогатительной фабрики. В статье приведен опыт проведения мероприятий по оптимизации БВР для улучшения работы обогатительной фабрики, а точнее стабилизации процесса первичного дробления руды. В статье приведены методы расчета рациональных параметров и результатов БВР. Проведен расчет рациональных параметров БВР, а также расчет гранулометрического состава взорванных пород при рациональных параметрах и при предложенных для экспериментальных взрывов Қажетті сападағы және көлемдегі бұзылған тау жынысын байыту фабрикасына жөнелту пайдалы қазбаларды өндіруге дайындық жұмыстарындағы негізгі міндеттердің бірі болып табылады. Бұл процесті реттеудің негізгі әдісі бұрғылау-жару жұмыстарының параметрлері мен технологияларын оңтайландыру болып табылады. Ақтоғай кен орнында карьердің тереңдеуімен өндірілетін кеннің беріктігінің артуы проблемасы туындады, бұл байыту фабрикасының өнімділігіне айтарлықтай әсер етеді. Мақалада байыту фабрикасының жұмысын жақсарту, дәлірек айтқанда, кенді бастапқы ұсақтау процесін тұрақтандыру мақсатында бұрғылау-жару жұмыстарын оңтайландыру шараларын өткізу тәжірибесі баяндалған. Мақалада бұрғылау-жару жұмыстарының ұтымды параметрлерін есептеу әдістері және нәтижелері келтірілген. Бұдан басқа, ұтымды параметрлерге және эксперименттік жарылыстар үшін ұсынылған параметрлерге сәйкес жарылған жыныстардың гранулометриялық құрамын есептеу жүргізілді One of the main tasks of preparatory work in mineral extraction is the delivery of the required quality and quantity of broken rock mass to the processing plant. The primary method of regulating this process is optimizing the parameters and technologies of drilling and blasting operations. At the Aktogay deposit, a problem has arisen with the increasing hardness of the mined ore as the pit deepens, significantly affecting the performance of the processing plant. The article presents the experience of implementing measures to optimize drilling and blasting operations to improve the performance of the processing plant, specifically to stabilize the primary ore crushing process. The article provides methods for calculating rational parameters and results of drilling and blasting operations. Calculations were made for the rational parameters of drilling and blasting operations, as well as for the granulometric composition of blasted rock under rational parameters and those proposed for experimental blasts

A multi-objective reinforcement learning framework for real-time drilling optimization based on symbolic regression and perception

In the context of the global energy transition, optimizing deep-water oil and gas drilling parameters is crucial for ensuring safety while improving efficiency. Traditional methods face limitations in highly dynamic and nonlinear drilling environments, struggling to balance speed and cost-effectiveness. Furthermore, these methods rely on real-time logging-while-drilling (LWD) data for decision-making, but delays in data collection and processing hinder timely adjustments of drilling parameters, affecting decision accuracy and responsiveness. This paper proposes a multi-objective drilling parameter optimization framework, incorporating symbolic regression, time-series networks, and Markov decision processes to precisely predict ROP, formation conditions, and optimize drilling parameters in real time. Key innovations include a multi-population evolutionary symbolic regression algorithm for constructing empirical equations, the integration of variational mode decomposition (VMD) and sample entropy for data preprocessing, and multi-head self-attention time-series networks to enhance prediction accuracy. Quantile regression further estimates the range of drilling parameter adjustments. Additionally, a drilling parameter optimization deep deterministic policy gradient (DPODDPG) algorithm was developed to automate real-time parameter adjustments. Empirical analysis on the Ledong 10-1 block in the South China Sea demonstrated significant improvements: ROP increased from 54.18 m/hr to 122.17 m/hr, mechanical specific energy (MSE) decreased from 100.82 MPa to 97.78 MPa, and cost per foot reduced from 121.16 × 102 CNY/m to 51.31 × 102 CNY/m. Compared to traditional methods, the proposed framework showed clear advantages in enhancing ROP, reducing MSE, and controlling costs, further validating its superiority in complex drilling environments. This method not only significantly improves drilling efficiency and economic benefits but also adapts to complex and changing drilling conditions, showing broad application potential, particularly in challenging deep-water oil and gas drilling operations, where it can provide more efficient and reliable optimization solutions.

Investigation of the specific charge variations in determining the optimal methods for drilling and blasting of tunnels

In this research, in order to compare and select the optimum patterns, two parameters of specific charge and specific drilling are used. Two explosive substances, including ammonium nitrate and fuel oil (ANFO) and Amulet, are used to charge the holes located on the cross-section of the tunnels in order to advance by 3 meters. Also, the cross-section of the selected tunnels was 19, 28, 32, 40, 48, 50, 65, and 76 square meters with horseshoe, circle and D-shaped. The diameter of the explosive hole is 48 mm for the Norwegian method and 51 mm for the two energy balance models and the Swedish method to compare them. A total of 160 designs are prepared for three types of limestone, sandstone and marl. The results obtained for two parameters of specific charge and special drilling for the selected rock material are completely opposite. Also, in the Swedish methods, according to the Amulet, the values of the calculated parameters are close to the energy balance model. Finally, according to the geomechanical parameters of the rock, for the Swedish method and the energy balance model in charging with amulet explosives, the energy balance model and the Holemberg-Persson method are proposed in the optimal design for the tunnel drilling and blasting pattern. In addition, for the Norwegian method and the energy balance model in charging the holes with ANFO, the energy balance model is prior to the Norwegian method. The amount of stemming of holes in different parts of the tunnel face is less for the Swedish method than the Norwegian and energy balance models.

Intelligent Lost Circulation Monitoring Method Based on Data Augmentation and Temporal Models

Deep and offshore drilling operations face complex geological formations, uncertain formation pressures, and narrow safety density windows, making them susceptible to lost circulation risks. To address these challenges, this paper introduces an innovative, intelligent lost circulation monitoring model that incorporates geological lithology information. This model not only utilizes real-time drilling parameters, but also encodes geological information such as rock type as inputs to the model. By combining these key lithological features, the model can comprehensively assess wellbore stability and reduce the lost circulation risks. In this paper, the Conditional Tabular Generative adversarial network (CTGAN) model is used to enhance the data of small-sample risk data, which can effectively expand the data distribution space and improve the performance of the model. This paper conducts a comparative analysis of intelligent monitoring results using artificial neural networks (ANNs), long short-term memory (LSTM), and temporal convolutional networks (TCNs). The results show that the TCN achieves an identification accuracy of 93.7%. Furthermore, the analysis reveals that the inclusion of lithology information significantly enhances the model’s performance, resulting in a 7.1% increase in accuracy. The false alarm rate of the model can be reduced by 10.2%, considering the fluctuation of the logging curve caused by the on/off condition of the pump. This indicates that the introduction of lithology information and the condition of the pump on−off provide advantages in monitoring and identifying lost circulation risks, enabling a more precise assessment of wellbore stability and a reduction in lost circulation incidents. The method of lost circulation monitoring proposed in this paper provides an important safety guarantee for the oil drilling industry.

Drilling Optimization for Ultra-long Slim Hole Horizontal Wells in Duvernay Shale project, Canada

Abstract Objective/Scope(30-75): Drilling contractors have always strived to pursue higher single well production and lower well-construction cost in order to achieve higher return on investment. Efforts have been made in recent years to break technological barriers to create ultra-long(>3500m) slim hole horizontal wells in Duvernay shale project. However, there were many challenges while extending the 6.75-in. slim hole laterals, such as 1) difficulty in weight transfer regarding motor slide drilling, 2) high down-hole friction torque and high ECD, 3) short servicing life and low efficiency of MWD, 4) inability to tracking thin substrata with limited logging tool, 5) production casing deployment challenges including stuck pipe risk and long running time. To overcome these obstacles, systematic solutions were proposed for unconventional ultra-long horizontal wells. Methods, Steps, and Process(75-100) : This paper proposes an integral drilling program to enhance overall drilling performance of ultra-long horizontal wells. First, Slim hole design to reduce well-construction cost through a reduction in steel, cement and fluid costs. Second, the upper drilling string upgraded from 4-in. drill pipes to 4.5-in. drill pipe with an advanced reduced OD premium connections, while Bottom Hole Assembly (BHA) employed even-wall stator PDM and Motorized RSS to improve drilling efficiency; Third, the OBM system is optimized for strong stability, lower friction, and clay-free invert emulsion to ensure safety drilling of longer laterals. Additionally, the MPD is equipped to maintain a lower ECD with minimal downhole losses; Then, a near-bit vibration sensor integrated into the RSS was deployed to provide real-time assessment of the severity of downhole shock and vibration. Reasonable drilling parameters were adjusted to reduce or eliminate downhole vibration and mitigate motor and MWD failure. Next, Azimuthal Gammy Ray was adopted and incorporated with dynamic drilling parameters data in real-time to optimize wellbore placement. More than 25 downhole drilling parameters were transmitted through high speed dual-telemetry MWD(xBolt) tool, boosting data transmission speeds and accuracy of wellbore placement in such a narrow stratigraphic window. Finally, a well-proven, external-grip mechanical casing running tool (CRT) was implemented specifically for smaller diameter 5.5-in. casing and a robust two-step wedge thread casing connection was designed to provide premium over torque capacity to manage longer lateral. Results, Understanding and Conclusions (100-200): Through continuous optimization and improvement, several major milestones and records were achieved such as longest 6.75-in. slim hole section (4875m) with one bit run and Bottom Hole Assembly, longest single run 5.5-in. & 4.5-in. hybrid casing in Duvernay at 8157m utilizing CRT tool at the time, a recorded 19.2 days drilling performance from spud to TD was achieved without any accidents or incidents. More than 6 horizontal wells lateral length exceeds 4,000m, with an average horizontal ROP above 50m/h. Single well EUR increasing from 131,000 tons to 190,000 tons, much of this improvement was due to the use of longer Hz laterals drilling technologies. Innovation points, technological contributions, and Significance (30-75): The drilling technologies developed in Duvernay have significantly reduced costs per meter and improved efficiency, setting a new lateral record in the Western Canadian Sedimentary Basin. These advancements offer practical and effective references for horizontal wells in other regions, especially for unconventional gas/oil reservoir.

Calibration modeling of drilling fluid rheological parameters in variable temperature environment based on support vector machine.

Traditional measurement of drilling fluid rheological parameters suffers from significant lag due to the inability of the instruments to promptly capture real-time parameters of the drilling fluid. These measurement models are typically constructed based on fixed temperature conditions and empirical formulas, rendering them inadequate for complex temperature gradient environments. Consequently, this limitation results in increased prediction errors, severely compromising the precise monitoring of drilling fluid performance. Aiming at the problems of low accuracy and poor stability of drilling fluid measurements under variable temperature conditions, a support vector machine-based calibration model for drilling fluid rheological parameters in a variable temperature environment is proposed in this paper. First, the measurement principle of the double-tube differential pressure rheology real-time measurement device is analyzed. The relationship between shear stress and shear rate is then established using differential pressure sensor and flow rate data. Utilizing the gray wolf optimization algorithm to optimize the kernel function weights and parameters, an SVM-based calibration model for predicting drilling fluid rheology correction parameters is constructed. Finally, a real-time monitoring platform for drilling fluid is developed. Experimental results show that the maximum relative errors for the predictions of apparent viscosity, plastic viscosity, and yield point are within ±5%, with coefficients of determination (R2) all greater than 0.95. These results validate the effectiveness of the proposed method in accurately monitoring the rheological performance of drilling fluids.

Stop Using Black-Box Models: Application of Explainable Artificial Intelligence for Rate of Penetration Prediction

Summary Rate of penetration (ROP) prediction plays a crucial role in optimizing drilling efficiency and reducing overall costs in the petroleum industry. Although modern artificial intelligence (AI) models have shown promising performance in this task, their lack of interpretability hinders their practical applications. This study introduces the neural basis model (NBM), a self-explainable model, for ROP prediction. The adopted NBM is benchmarked against some well-known methods using a publicly available data set, demonstrating its promising performance. The key advantage of the NBM lies in its ability to provide clear explanations, where the influence of the input drilling parameters on the predicted ROP can be clearly visualized and analyzed. The study also compares the models’ performance under two scenarios—continuous learning and all-for-one. The results indicate that the models’ performance under the continuous learning scenario, in which the models are iteratively updated with new data from the same well, outperforms that under the all-for-one scenario, where models are trained on data from previously drilled wells and applied to new wells. The discrepancy is probably due to the absence of detailed formation characteristics from the data set. Therefore, the model trained in other wells could not generalize well on new wells. Currently, in petroleum engineering, AI is gradually playing an increasingly important role; however, the majority of AI-related works often directly employ black-box models, which lack interpretability and might cause serious risks if deployed in practice. This work introduces an approach to using neural networks to build self-explainable AI (XAI), with the aim of promoting the application of XAI in the petroleum industry.

Research and Application of Plugging Drilling and Completion Technology for Difficult Old Well in Changchun Gas Storage

Abstract Changchun Gas Storage has been included in the 14th Five-Year Plan for the development of petroleum and natural gas in Jilin Province. Its smooth construction and safe operation are crucial to ensure the stable supply of natural gas in Changchun. Well X106F located in the construction area was abandoned in 1988 due to drilling tool falling and multiple salvage failures. In order to ensure the sealing and integrity of the gas storage, it is necessary to effectively plug the drilling cover. In view of the problems of low well history accuracy, poor well wall stability and difficulty in cementing large boreholes, open hole drilling, trajectory design and control, film-forming and wall-fixing drilling fluid and prestressed cementing technologies are applied. By optimizing drilling tools, optimizing drilling parameters, designing the three-opening well structure and “five-section” profile, the plugging well construction requirements are met. The first and second open drilling along the old well borehole, 1313m deep on the first try to find top of the fish, after cementing plug, side tracking to 50m below the top of the fish and then cementing;for third spud control trajectory to accompanied the old well, according to the results of passive magnetic guidance, real-time adjustment of the trajectory scheme and construction plan, finally successfully collided with the old well at 1893m deep, after cementing the drilling plug, perforating and extruding cement, the cement job quality is good. The whole well construction period of 100 days, creating the fastest record of the old well plugging without trajectory of the fish type, providing technical support for the construction of Changchun gas storage, and providing experience for the same type of old well plugging and complex well treatment in China.

Real-time lithology identification from drilling data with self & cross attention model and wavelet transform

Accurate lithology identification during drilling operations is pivotal for optimizing drilling efficiency and informed decision-making. Traditional methods, such as mud logging, Logging While Drilling (LWD), and Measurement While Drilling (MWD), often face challenges such as delays and inaccuracies, lacking consistent utilization of real-time engineering data across all drilling sites. Consequently, these methods frequently overlook the complex interactions of influencing factors, resulting in underutilized geological information that could significantly enhance operational outcomes. This paper introduces the SelfAttention-CrossWT (SACWT) model, an innovative approach that integrates self-attention and cross-attention mechanisms with Wavelet Transform (WT) to utilize real-time drilling parameters, including Weight on Bit (WOB) and Rate of Penetration (ROP). The SACWT model effectively harnesses both temporal and frequency-domain characteristics of drilling data, facilitating comprehensive extraction of latent patterns and dynamics, which substantially improves lithology identification accuracy. The output of the model is the real-time lithology classification at the drill bit's depth. The performance of the SACWT model is compared with Long Short-Term Memory (LSTM) networks and a Self-Attention (SA) model that does not utilize frequency-domain data. When applied to a dataset from the Volve oil field, the SACWT model achieved identification accuracies of 87% and 91% in two separate test wells, outperforming traditional methods. These results underscore the model's efficacy and the significant potential of utilizing real-time drilling data for enhanced lithological characterization. This breakthrough offers a robust framework for future exploration and development operations, providing a more precise, efficient, and cost-effective approach to geological analysis.

How oil and gas industry are transforming with AI and ML

The Oil and Gas Industry is witnessing a major transformation due to the advent of Artificial Intelligence (AI) and Machine Learning (ML). These advances are changing operations by making things work better, cheaper and safer. Companies are using Artificial intelligence and Machine Learning to analyze large data points generated due to exploration, production and distribution activities which generate actionable insights leading to data driven decision making. AI and ML techniques for exploration, well placement optimization such as mount point selection or drilling parameters suggest based on geological data analysis including a historical performance. Using data in a real-time and predictive manner, manufacturing plants can catch early signs of equipment issues such as rising temperature encouraging proactive measures to be taken which reduces downtime and maintenance costs. Furthermore, reservoir management, hydrocarbon extraction and energy efficiency are optimized via AI-based optimization strategies.

Enhancing Drilling Performance in Natural Fiber-Reinforced Biocomposites Using Taguchi Method for Sustainable Manufacturing

The current research work focuses on optimizing drilling parameters for Sesbania rostrata fiber-reinforced polycaprolactone (PCL) biocomposites using the Taguchi method and ANOVA to improve hole quality, particularly to minimize delamination. The Taguchi L9 orthogonal array was employed with three factors: spindle speed (300, 750, and 1800 rpm), feed rate (0.05, 0.12, and 0.25 mm/rev), and drill size (4, 8, and 10 mm). The experimental results showed that drill size had the most significant effect on thrust force, with a contribution rate of 99.29%, whereas spindle speed primarily influenced delamination, contributing 67.65%. Optimal parameters were determined to be a spindle speed of 300 rpm, a feed rate of 0.25 mm/rev, and a drill size of 10 mm. These findings are significant for industries using biocomposites, offering sustainable solutions with enhanced machining performance.

Real-Time Lithology Prediction at the Bit Using Machine Learning

Real-time drilling analysis requires knowledge of lithology at the drill bit. However, logging-while-drilling (LWD) sensors in the bottom hole assembly (BHA) are usually positioned 2–50 m (7–164 ft) above the bit (called the sensor offset), leading to a delay in real-time drilling analysis. The current industry solution to overcome this delay involves stopping drilling to perform a bottoms-up circulation for cuttings evaluation—a process that is both time-consuming and costly. To address this issue, our study evaluates three methodologies for real-time lithology prediction at the bit using drilling and petrophysical parameters. The first method employs a petrophysical approach, which involves using bulk density and neutron porosity predicted at the bit. The second method combines unsupervised and supervised machine learning (ML) for prediction. The third method employs classification algorithms on manually labeled lithology data from mud log reports, a novel approach used in this work. Our results show varying degrees of success: the bulk density versus neutron porosity cross-plot method achieved an accuracy of 58% with blind-well test data; the ML approach improved accuracy to 66%; and the Random Forest (RF) classification with manual labeling significantly increased accuracy to 86%. This comparative analysis of three different methodologies for lithology prediction has not been previously explored in the literature. While clustering and classification methods have been regarded as the most effective, our study demonstrates that they do not always yield the best result. These findings demonstrate that ML models, particularly the manual labeling approach, substantially outperform the petrophysical method. This new algorithm, designed for real-time applications, uses selected input parameters to effectively minimize problems associated with the sensor offset of LWD tools. It rapidly adapts to changes, offering a quicker and more cost-effective interpretation of lithology. This eliminates the need for time-consuming bottoms-up circulation to evaluate cuttings. Ultimately, this approach enhances drilling efficiency and significantly improves the accuracy of lithology prediction, notably in identifying interbedded geological layers.

Multi response optimization of process parameters in titanium alloy minimum quantity lubrication drilling operation

Abstract This work investigates the application of minimal quantity lubrication (MQL) in the drilling process, where a combination of liquid and air creates an aerosol in the form of a fine mist. This protective layer decreases friction and tool wear, hence improving overall efficiency. The study examines the conventional Gulfcut oil blend drilling technique to enhance drilling performance on the titanium alloy Ti-6Al-4V under MQL circumstances. The key drilling parameters, namely spindle speed (N), feed rate (F), and point angle (D), were analyzed using a Taguchi L16 orthogonal array. The experimental inquiry aimed to identify the most favorable conditions that lead to the least amount of torque (TQ), thrust force (TF), and surface roughness (SR). An Analysis of Variance (ANOVA) was used to examine the impact of control factors on drilling performance. The optimized drilling parameters led to a reduction in torque, thrust force, and surface roughness by 12.88%, 21.29%, and 25.76%, respectively. Furthermore, microstructure analysis demonstrated that the Gulfcut lubricant plays a pivotal role in reducing grain size during drilling. This research provides valuable insights into optimizing drilling conditions for titanium alloy using a conventional Gulfcut oil blend with MQL, aiming to reduce torque, thrust force, and surface roughness.

Optimizing drilling parameters for unidirectional glass fiber/nanoclay-epoxy matrix composites using gray relational analysis and response surface methodology

Optimizing drilling parameters for unidirectional glass fiber/nanoclay-epoxy matrix composites using gray relational analysis and response surface methodology