Houdaifa Khalifa

The oil and gas industry faces significant challenges due to wear on drilling motor components, such as thrust pins and inserts. These components are critical to the efficiency and reliability of drilling operations, yet are susceptible to wear, leading to significant economic losses, operational downtime, and safety risks. Despite previous research on wear-resistant materials and surface treatments, gaps exist in understanding the unique properties of thrust pins and inserts. The aim of this study is to enhance mechanical system performance by characterizing the wear resistance of these components. Through chemical analysis, hardness assessments, and metallographic examinations, the study seeks to identify specific alloys and microstructures conducive to wear resistance. Key findings reveal that AISI 9314 thrust pins exhibit superior wear resistance with a tempered martensite microstructure and a hardness of 41 HRc, whereas AISI 9310 inserts are less resistant, with a hardness of 35 HRc. The research employs advanced techniques, including a pin-on-disc tribometer, scanning electron microscopy (SEM), energy-dispersive X-ray spectroscopy (EDS), and profilometry, to evaluate wear behavior, visualize wear patterns, analyze elemental composition, and quantify material loss and surface roughness. Our findings demonstrate that optimizing the material selection can significantly enhance the durability and efficiency of drilling motors. This has profound implications for the oil and gas industry, offering pathways to reduce maintenance costs, improve operational efficiency, and contribute to environmental sustainability by optimizing energy consumption and minimizing the carbon footprint of drilling operations.

Accurately forecasting oil and gas well production, especially in complex unconventional reservoirs, is vital. Leveraging advanced techniques like machine learning and deep learning is becoming more common due to ample historical data availability. While traditional methods work for conventional reservoirs, they struggle in unconventional scenarios. Modern machine and deep learning models excel in such challenges, offering insights while bypassing temporary disruptions or pressure issues. This study compares ten empirical production forecast models with state-of-the-art deep learning and time series models (ARIMA, LSTM, GRU) in the Bakken shale play of the Williston Basin. After thorough calibration using extensive data, model efficacy is assessed using R2-score and MSE. Results highlight well-specific performance, with no single model consistently outperforming across all wells. Notably, optimally adjusted ARIMA produced commendable results for many wells. This research aids reservoir engineers by simplifying production decline trend identification, reducing reliance on intricate decline curve analyses. It ushers in a streamlined and dependable paradigm for production forecasting.

Re-fracturing has been suggested to address the rapid decline of oil production in the Bakken Formation. Creating new fractures between the pre-existing ones allows access to the unstimulated reserves and consequently increases production. This study aims to optimize the completion design parameters of the Re-fracturing in the Bakken formation. A numerical model was built using a physics-based simulator that combines hydraulic fracturing, geomechanics, and reservoir numerical modeling as a continuous simulation. The study conducted sensitivity analyses to evaluate the effect of different completion parameters on the re-fractured well performance, including the time between the initial fracture stimulation and re-fracturing, the injection volume of the re-fracturing fluid, and the design of the re-fracturing treatment to achieve better oil production performances. The study found that the re-fracturing operations can lead to promising results, with a significant increase in the incremental oil recovery. Overall, the outcomes of this study provide valuable insights for optimizing re-fracturing operations in the Bakken formation and similar unconventional reservoirs. It shows how the depleted zone affects the propagation of new fractures beyond the depleted area. As a result of this study, higher injection volumes with moderate fracture spacing and shorter time before refracturing resulted in a better performance.

Hole deviation in drilling, influenced by geological formations and drilling mechanics, brings about increased operational costs, boundary disputes, collision risks, and safety concerns. Traditional measurement tools, susceptible to magnetic interference, often produce skewed readings. In addressing this challenge, our research introduces an ML model leveraging data from gyro runs, which are immune to magnetic interferences. After processing a comprehensive dataset of geophysical well log parameters, various ML models were trained. The Random Forest Classifier emerged as the most efficient, boasting a 97% accuracy rate. To validate its robustness, the model underwent a blind test on two distinct new wells, achieving an overall accuracy of 89%, further underscoring its reliability. This model, aptly named "Path Guard", was subsequently deployed as a user-friendly web application, offering the industry an accessible tool for predicting drilling path deviations. Through the integration of artificial intelligence and data science into drilling and geomechanics, our approach not only enhances current operations but also paves the way for potential real-time, automated systems in drilling deviation management.

Fishbone drilling (FbD), a premier method in multilateral well drilling, has been adopted in numerous global hydrocarbon fields. Its application leads to notable improvements in recovery rates while diminishing carbon emissions from the drilling process. The essence of FbD lies in constructing several minor holes that radiate in diverse directions. However, a significant obstacle with Fishbone drilling is the absence of comprehensive models to understand the impact of each Fishbone variable on total production, and their interplay. This research delves into the intricacies of fishbone well productivity prediction by leveraging a suite of machine learning algorithms, including RandomForest, GradientBoost, LinearSVC, AdaBoost, and KNeighbors. Through extensive model evaluation metrics such as MSE, RMSE, MAE, and the R-squared score, the study offers insights into the relative weightage of input features, with bottom-hole pressure emerging as paramount. The culmination of the research is the DrillFish Web App, an innovative platform designed for industry professionals to predict fluid flowrate and optimize fishbone drilling designs.

Fishbone drilling (FbD) involves drilling multiple micro-holes branching out in various directions from the primary vertical or deviated wellbore. FbD is similar to multilateral micro-hole drilling and can be employed to boost hydrocarbon production in naturally fractured formations or during refracturing operations by connecting existing natural fractures. Key design elements in fishbones include determining the number, length, and spacing between the branches, and the angle at which the branches deviate from the main borehole. Fishbone wells have emerged as a promising technology for improving well performance and reducing environmental impact. In this paper, we present a comprehensive review of the different applications of fishbone wells in conventional and renewable energy systems. We discuss the potential of fishbone wells for enhanced oil and gas recovery, as well as their application in unconventional resources such as coal bed methane. Moreover, we examine the feasibility of fishbone wells in renewable energy systems, such as geothermal energy and carbon capture, utilization, and storage (CCUS). We highlight the various benefits of fishbone wells, including reduced carbon footprint, enhanced efficiency, and increased sustainability. Finally, we discuss the challenges and limitations associated with fishbone wells in different energy systems. This review provides a comprehensive overview of the potential and challenges of fishbone wells in reducing carbon footprint and improving well performance in a wide range of energy systems.

The accurate prediction of underground formation lithology class and tops is a critical challenge in the oil industry. This paper presents a machine-learning (ML) approach to predict lithology from drilling data, offering real-time litho-facies identification. The ML model, applied via the web app “GeoVision”, achieves remarkable performance during its training phase with a mean accuracy of 95% and a precision of 98%. The model successfully predicts claystone, marl, and sandstone classes with high precision scores. Testing on new data yields an overall accuracy of 95%, providing valuable insights and setting a benchmark for future efforts. To address the limitations of current methodologies, such as time lags and lack of real-time data, we utilize drilling data as a unique endeavor to predict lithology. Our approach integrates nine drilling parameters, going beyond the narrow focus on the rate of penetration (ROP) often seen in previous research. The model was trained and evaluated using the open Volve field dataset, and careful data preprocessing was performed to reduce features, balance the sample distribution, and ensure an unbiased dataset. The innovative methodology demonstrates exceptional performance and offers substantial advantages for real-time geosteering. The accessibility of our models is enhanced through the user-friendly web app “GeoVision”, enabling effective utilization by drilling engineers and marking a significant advancement in the field.

This paper presents an intelligent modeling approach to individual thermal comfort and energy optimization problem, which aims to minimize energy consumption and improve thermal environmental conditions for human occupancy. In our previous study, this optimization problem was solved under the assumption of the existence of information about the thermal comfort preferences of individuals. A traditional optimization method is used to calculate off-line optimum solutions to this problem at numerous operating points. These solutions are used to train an intelligent system such as a fuzzy logic system under the same assumption resulting in a control system which encapsulates the behavior of the collection of optimum solutions. This methodology is named "intelligent modeling of optimized systems" (IMOS) in this paper. However, it is hard to gather information about individuals' thermal comfort preferences in practice. The sensitivity analysis on the optimization problem and its approximation with fuzzy logic system regarding individual thermal comfort preferences has been investigated in this paper.