Ahmed Hadjadj’s research while affiliated with University of Boumerdes and other places

The rate of penetration (ROP) is the key parameter to enhance drilling processes as it is inversely proportional to the overall cost of drilling operations. Maximizing the ROP without any limitation can induce drilling dysfunctions such as downhole vibrations. These vibrations are the main reason for bottom hole assembly (BHA) tool failure or excessive wear. This paper aims to maximize the ROP while managing the torque to keep the depth of cut within an acceptable range during the cutting process. To achieve this, machine learning algorithms are applied to build ROP and drilling torque models. Then, a metaheuristic algorithm is used to determine the optimal technical control parameters, the weight on bit (WOB) and revolutions per minute (RPM), that simultaneously enhance the ROP and mitigate excessive vibrations. This paper introduces a new methodology for mitigating drill string vibrations, improving the rate of penetration (ROP), minimizing BHA failures, and reducing drilling costs.

Coiled tubing (CT) plays a pivotal role in oil and gas well intervention operations due to its advantages, such as flexibility, fast mobilization, safety, low cost, and its wide range of applications, including well intervention, cleaning, stimulation, fluid displacement, cementing, and drilling. However, CT is subject to fatigue and mechanical damage caused by repeated bending cycles, internal pressure, and environmental factors, which can lead to premature failure, high operational costs, and production downtime. With the development of CT properties and modes of application, traditional fatigue life prediction methods based on analytical models integrated in the tracking process showed, in some cases, an underestimate or overestimate of the actual fatigue life of CT, particularly when complex factors like welding type, corrosive environment, and high-pressure variation are involved. This study addresses this limitation by introducing a comprehensive machine learning-based approach to improve the accuracy of CT fatigue life prediction, using a dataset derived from both lab-scale and full-scale fatigue tests. We incorporated the impact of different parameters such as CT grades, wall thickness, CT diameter, internal pressure, and welding types. By using advanced machine learning techniques such as artificial neural networks (ANNs) and Gradient Boosting Regressor, we obtained a more precise estimation of the number of cycles to failure than traditional models. The results from our machine learning analysis demonstrated that CatBoost and XGBoost are the most suitable models for fatigue life prediction. These models exhibited high predictive accuracy, with R² values exceeding 0.94 on the test set, alongside relatively low error metrics (MSE, MAE and MAPE), indicating strong generalization capability. The results of this study show the importance of the integration of machine learning for CT fatigue life analysis and demonstrate its capacity to enhance prediction accuracy and reduce uncertainty. A detailed machine learning model is presented, emphasizing the capability to handle complex data and improve prediction under diverse operational conditions. This study contributes to more reliable CT management and safer, more cost-efficient well intervention operations.

This paper presents the Decaying swirl flow behaviors of turbulent flow in active mixer through a numerical examination and analysis. The numerical analysis was carried out by solving the 3D Navier-Stokes equations with the species transport equations using the computational fluid dynamic (CFD) tool. The computation of the hydrodynamic and decaying swirl flow efficiency yields an estimated index for various scenarios. The swirl number, the decay rate, the tangential velocity distribution, and the variation of pressure are analyzed. When it comes to hole cleaning, the swirl flow will be nearly parallel to the axial flow. Moreover, as the helical angle rises above the critical threshold, the swirl flow's rotational direction will alter.

O mapeamento 3D da resistência das rochas desempenha um papel crucial na otimização da perfuração, fornecendo informações detalhadas sobre as propriedades geomecânicas do subsolo, que são essenciais para a otimização da perfuração. Ao criar uma representação tridimensional das variações de resistência da rocha, os engenheiros podem identificar áreas de alta e baixa resistência, permitindo-lhes adaptar técnicas e equipamentos de perfuração a condições geológicas específicas. Esta precisão reduz o risco de falha do equipamento, minimiza a probabilidade de instabilidade do poço e aumenta a eficiência operacional geral. Além disso, compreender a distribuição da resistência das rochas ajuda a prever riscos potenciais de perfuração, como fraturas e falhas, permitindo uma tomada de decisão proativa que pode economizar tempo e recursos. Em última análise, o mapeamento 3D da resistência das rochas não só melhora o desempenho e a segurança da perfuração, mas também contribui para uma extração de recursos mais econômica, otimizando a colocação dos poços e reduzindo o tempo não produtivo durante as campanhas de perfuração. Este estudo apresenta uma abordagem para prever a resistência das rochas no espaço tridimensional usando métodos geoestatísticos. Utilizamos um conjunto de dados, incluindo propriedades geológicas e mecânicas obtidas de vários furos de sondagem no campo. Ao empregar técnicas geoestatísticas avançadas, particularmente ponderação de distância inversa e krigagem ordinária, desenvolvemos um modelo preditivo que interpola espacialmente os valores de resistência da rocha em toda a área modelada.

The rig state plays a crucial role in recognizing the operations carried out by the drilling crew and quantifying Invisible Lost Time (ILT). This lost time, often challenging to assess and report manually in daily reports, results in delays to the scheduled timeline. In this paper, the Naive Bayes algorithm was used to establish a novel rig state. Training data, consisting of a large set of rules, was generated based on drilling experts’ recommendations. This dataset was then employed to build a Naive Bayes classifier capable of emulating the cognitive processes of skilled drilling engineers and accurately recognizing the actual drilling operation from surface data. The developed model was used to process high-frequency drilling data collected from three wells, aiming to derive the Key Performance Indicators (KPIs) related to each drilling crew’s efficiency and quantify the ILT during the drilling connections. The obtained results revealed that the established rig state excelled in automatically recognizing drilling operations, achieving a high success rate of 99.747%. The findings of this study offer valuable insights for drillers and rig supervisors, enabling real-time visual assessment of efficiency and prompt intervention to reduce ILT. Graphical abstract

This article presents a novel Artificial Intelligence (AI) workflow to enhance drilling performance by mitigating the adverse impact of drill-string vibrations on drilling efficiency. The study employs three supervised machine learning (ML) algorithms, namely the Multi-Layer Perceptron (MLP), Support Vector Regression (SVR), and Regression Decision Tree (DTR), to train models for bit rotation (Bit RPM), rate of penetration (ROP), and torque. These models combine to form a digital twin for a drilling system and are validated through extensive cross-validation procedures against actual drilling parameters using field data. The combined SVR-Bit RPM model is then used to categorize torsional vibrations and constrain optimized parameter selection using the Particle Swarm Optimization block (PSO). The SVR-ROP model is integrated with a PSO under two constraints: Stick Slip Index (SSI<0.05) and Depth of Cut (DOC<5 mm) to further improve torsional stability. Simulations predict a 43% increase in ROP and torsional stability on average when the optimized parameters WOB and RPM are applied. This would avoid the need to trip in/out to change the bit, and the drilling time can be reduced from 66 to 31 h. The findings of this study illustrate the system's competency in determining optimal drilling parameters and boosting drilling efficiency. Integrating AI techniques offers valuable insights and practical solutions for drilling optimization, particularly in terms of saving drilling time and improving the ROP, which increases potential savings.

Drill string vibration is one of the limiting factors that affect the maximum drilling performance, and at the same time causes premature failure of drill string components. Optimizing the drilling process in order to enhance efficiency requires a valuable vibration mitigation scheme to increase penetration rate. This article introduces a novel strategy to control drilling parameters to reduce drill string vibration and optimize ROP. In the system development process, various interesting topics have been studied, such as the performance of the controller (using MATLAB Fuzzy Logic toolbox), the application of artificial neural networks in ROP prediction, and drill string modeling. The proposed strategy uses multiple inputs such as surface drilling parameters variation (RPM, WOB, and Torque) together with predictive vibration severity estimate to detect drilling vibrations and adjust related parameters to suppress severe oscillations and avoid unexpected events that lead to non-productive time. The fuzzy logic controller shows overall stability and robustness, the controlled parameters follow the rules used in the fuzzy set which are developed by analyzing data from Algerian oil wells and simulating the "experience and expertise" of decision-makers. The system is multi-objective optimization; can detect inefficiencies, mitigate vibration, and enhance ROP. The artificial neural network ROP model, when simulated using the field data, shows an improvement of ROP by 12% on average across all the drilled formations when compared to the recorded data. A case study is presented to illustrate the application of this method in drilling practice.

The effective determination of pressure losses depends on accurate knowledge of the drilling fluid rheology. As the fluid circulates deeper around the wellbore, its rheological behavior undergoes significant alterations due to the variations in downhole conditions encountered. The present study investigates the effects of the rheological properties of Yield-power law fluid at various pressures and temperatures on annular pressure losses and velocity profiles. Simulations were performed using Computational Fluid Dynamics to examine the fluid flow in turbulent and laminar regimes. Comparison between numerical, experimental and slot approximation model results showed a good agreement. Results indicated that pressure losses have reduced in both regimes with increasing temperature, at a constant pressure. However the pressure has the opposite effect at a constant temperature. For a drilling fluid flow velocity of 1 m/s, the elevation of temperature from 25 °C to 90 °C, decreases the pressure drop gradient by (31% to 48%) at low and high- pressure conditions respectively. Whereas, the influence of increasing pressure on pressure losses is more apparent at 25 °C. Earlier transition from laminar to turbulent is observed with temperature rise. Therefore, the temperature effect on pressure losses in the turbulent region; is shown for different Generalized Reynolds numbers.

A correct prediction of drilling fluid pressure drop is considered as a key parameter to carry out an efficient drilling operation and avoid non-productive time (NPT) during enrollment of the process. In this paper, a numerical approach is employed to analyze frictional pressure loss of Herschel-Bulkley (yield power-law) fluid flowing through an annular geometry in which the inner pipe makes a helical buckling motion in laminar and turbulent regimes. Results showed that rotation of the helically-buckled inner pipe induces a decrease of 10% and 6% of the pressure loss gradient of the Herschel-Bulkley fluid in the laminar regime for the helical pitch lengths of 6.9 m and 10 m, respectively. Also, increasing the pitch length of a helically-shaped inner pipe reduces the pressure loss gradient, particularly for low angular speeds. Moreover, the helical pitch length increment from 6.9 m to 10.7 m slightly affects the pressure loss gradient for the turbulent regime.

This paper aims to estimate surge pressure resulting from the flow of a Herschel-Bulkley fluid through concentric annuli during tripping operations. A semi-analytical model which includes new constraints to avoid non-physical solutions was developed then solved numerically. Moreover, a numerical model was implemented using finite difference method for which accurate solutions were obtained. Besides, the commercial software (Ansys-Fluent 19R3) was employed. The results are compared with existing experimental data from literature where a good agreement is observed with a maximum average relative error of 4% and 7.8% for the two studied drilling fluids, respectively. These models were successfully extended to power-law fluids. On the other hand, numerical results were collected by varying the relevant drilling parameters. The outputs indicated that the increase in the pipe tripping velocity causes an increase of the surge pressure independently of the parameter of interest, however, the rate of increase changes from one parameter to another. Based on this parametric study, a surrogate model using the Random Forest algorithm is constructed. This model predicts surge and swab pressures without requiring cumbersome numerical calculations. The model predictions have shown a satisfactory matching with an R 2 equals to 0.99 for both training and test data.