Evaluating Wellbore Tortuosity in Horizontal Wells Caused by RSS Steering Mechanism

Oliveira, Victor; Zahrani, Bader; Alrushud, Albaraa; Mohammad, Muntasar

doi:10.2118/192211-ms

Cited by 3 publications

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

A supervised machine learning model to select a cost-effective directional drilling tool

Nour,

Elsayed,

Mahmoud

2024

Sci Rep

View full text Add to dashboard Cite

With the increased directional drilling activities in the oil and gas industry, combined with the digital revolution amongst all industry aspects, the need became high to optimize all planning and operational drilling activities. One important step in planning a directional well is to select a directional tool that can deliver the well in a cost-effective manner. Rotary steerable systems (RSS) and positive displacement mud motors (PDM) are the two widely used tools, each with distinct advantages: RSS excels in hole cleaning, sticking avoidance and hole quality in general, while PDM offers versatility and lower operating costs. This paper presents a series of machine learning (ML) models to automate the selection of the optimal directional tool based on offset well data. By processing lithology, directional, drilling performance, tripping and casing running data, the model predicts section time and cost for upcoming wells. Historical data from offset wells were split into training and testing sets and different ML algorithms were tested to choose the most accurate one. The XGBoost algorithm provided the most accurate predictions during testing, outperforming other algorithms. The beauty of the model is that it successfully accounted for variations in formation thicknesses and drilling environment and adjusts tool recommendations accordingly. Results show that no universal rule favors either RSS or PDM; rather, tool selection is highly dependent on well-specific factors. This data-driven approach reduces human bias, enhances decision-making, and could significantly lower field development costs, particularly in aggressive drilling campaigns.

show abstract

A supervised machine learning model to select a cost-effective directional drilling tool

Nour,

Elsayed,

Mahmoud

2024

Sci Rep

View full text Add to dashboard Cite

show abstract

Quantification and Correction of Lateral Motion Effects on NMR Logging While Drilling

Haji

Tisdale

Muslem

et al. 2020

Day 1 Mon, November 09, 2020

View full text Add to dashboard Cite

Monitoring downhole drilling dynamics is an essential element to quality check the measurements provided in logging while drilling (LWD). LWD nuclear magnetic resonance (NMR) is sensitive to the motion induced from the bottom-hole assembly (BHA) during drilling, therefore, quantifying the motion effects becomes important to understand how to correct the measurements. Quantification and correction of lateral motion effects on NMR LWD are the objectives of this paper. Data was collected from various BHA combinations with LWD NMR to model the responses, which were compared with actual downhole conditions to assess the need for the lateral motion correction (LMC). Vibrational assessment criteria are utilized to assign a severity level, which dictates the level of the LMC. The LMC applies an algorithm to differentiate true formation signal responses from the vibration signal response. Specifically, the motion effect function was integrated into the forward matrix of the NMR joint inversion, and a nonlinear optimization algorithm was used to determine the four motion parameters, and if present, compensate for lateral motion effects. In wellbores with severe motion vibration there were large discrepancies between real-time and memory data, which resulted in mismatches with the measured partial porosities. Investigations were conducted on the BHA design, well trajectories, and wellbore environment to quantify the lateral motion effect on the NMR measurement. This information was then compiled to incorporate all aspects of BHA design techniques to mitigate the lateral motion effects on the NMR measurement. The LMC algorithm gives added confidence to ensure all data collected is consistent and reliable even in more challenging wellbore environments, which could be subjected to unanticipated lateral motion. This paper highlights an approach to integrate BHA simulation principles to anticipate severe motion effects during drilling. This knowledge, coupled with the LMC, creates a platform to enhance NMR data quality.

show abstract

Executing the Digital Well Plan - Enhancing Process Automation

Hummes

Macpherson

Bone

et al. 2023

Middle East Oil, Gas and Geosciences Show

View full text Add to dashboard Cite

Automation of well construction combines process and machine automation to deliver cost savings and efficiency gains, alongside safer operations and faster collaborative decision making. Integration of well planning and execution improves performance, minimizes risk, and creates the framework for batch control of well construction. Generating intuitive and standardized insights from historical and live data streams enables reducing uncertainty and driving technical limit performance at every stage, for the safest and most economical well delivery possible. Remote operations have become standard practice in well construction and drilling automation is rapidly growing. Machine-learning based models can predict hazards and best operating parameters. The paper describes how these elements are combined to easily analyze offset well data from multiple sources for performance benchmarking, deep technical analysis, and risk management. Integration with physics-based models (the digital-twin) establishes a coherent execution roadmap, a real-time digital recipe that is directly used in rigsite automation. During execution, model assumptions are replaced by live sensor data. Those models are then re-calculated in real-time for automated process control and become available for future planning. The viability of integrated well planning and automation systems is no longer disputed, and industry focus has shifted towards proving the potential of this approach. Pertinent case examples from drilling operations are examined in the paper, including optimizing performance through harnessing analytics of large data sets from offset wells, and on exploring the integration of AI techniques for risk prediction and mitigation. The insights gained, coupled with the digital well plan, are instrumental for optimization and automation of tripping equipment in and out of hole, and of drilling ahead operations. Integrating the digital well plan with "lessons learned" from the analysis of all available data and using a digital-twin concept with physics-based and data driven models, provides the foundation for the next step in process automation: the creation of digital procedures for process automation of well construction. This capability extends the cost savings and efficiency gains realized in recent years through remote operations.

show abstract

Evaluating Wellbore Tortuosity in Horizontal Wells Caused by RSS Steering Mechanism

Cited by 3 publications

References 6 publications

A supervised machine learning model to select a cost-effective directional drilling tool

A supervised machine learning model to select a cost-effective directional drilling tool

Quantification and Correction of Lateral Motion Effects on NMR Logging While Drilling

Executing the Digital Well Plan - Enhancing Process Automation

Contact Info

Product

Resources

About