Low rates of penetration (ROP) were experienced in an area with well-known lithology. The vast drilling experience and similarity of drilling conditions in the area, provided the operator with enough data to improve the well schedule and cost performance through the use of machine learning. Machine learning, specifically artificial neural networks (ANN), is a statistical tool to find relations between multiple inputs. Details that would have been missed or considered outliers by a mathematical model can be accounted for and explained in the ANN model. The ANN was trained on thousands of real time data points recorded from selected wells in a specific depth interval. Typical drilling parameters such as weight on bit, rotary speed, bit hydraulics, lithological properties, and dogleg severity were the input parameters chosen in the model to generate ROP. Once the model was calibrated to historical data, it was used to find the best parameters to maximize ROP. R squared factors were 0.729 and 0.675 for 12.25 in. and 17.5 in. sections repectively. This was achieved with an ANN structure of 2 hidden layers consisting of 5 nodes each. Sensitivity analysis identified bit hydraulics, weight on bit, and rotary speed as the major parameters impacting ROP. The ROP model was used to conduct a "virtual drill-off test" to identify drilling parameters that maximize ROP. ROP dependency on weight on bit and lithological analysis suggests bit design can be further improved. Bit hydraulics showed that higher flow rate was needed in sections with higher overbalance. Optimum drilling parameters were tested on four wells and resulted in more than 50% higher ROP compared to original field data. In an industry increasingly dominated by big data, separating the clean data from the "noise" will be a vital topic. This paper aims to provide a blueprint for the use machine learning to optimize ROP in a manner that is simple and easily replicated.
Conventionally, a bit is selected from offset well bit run summaries. This method of selection is not always accurate since each bit is run under different conditions which might not be reflected in an offset study analysis. The large quantities of data generated from real time measurements in offset wells makes machine learning the ideal tool for analysis and comparison. Artificial Neural Network (ANN) is a relatively simple machine learning tool that combines inputs and calculation layers to compute a specified output layer. The ANN is fed over thousands of data points from 17-1/2 in hole sections across multiple wells. A specific model is then trained for every bit with weight on bit (WOB), rotary speed (RPM), bit hydraulics, and lithological properties as inputs and rate of penetration (ROP) as output. The model is finalized when a satisfactory statistical set of KPI's are achieved. Using a combination of Monte-Carlo analysis and sensitivity analysis, different bits are compared by varying parameters for the same bit and varying the bit under the same parameters. A bit and its optimized parameters are proposed, resulting in an average instantaneous ROP improvement of 32%. Performance benchmarked with individual drilling parameters shows improved ROP response to WOB, RPM, and bit hydraulics in the optimized run. This project solidifies machine learning as a powerful tool for bit selection and parameter optimization to improve drilling performance. Machine learning will become a significant part of well planning, design, and operations in the future. This study demonstrates how ANN's can be used to learn from previous operations and influence planning decisions to improve bit performance.
Subsurface uncertainty, inadequate offset wells correlation, and high investment cost are some of the biggest drilling challenges in any frontier environment or wild cat exploration wells. These challenges comes with inherent risk on people, environment, assets, and reputation. Mitigating these risks through contingency in the detailed well planning phase as well maximizing operational uptime and efficiency during the well delivery phase, greatly impact the outcome of the well. Digital tools and automation have been a cornerstone in the industry's latest tools to reduce personnel on the rig, as well as minimize downtime and inefficiency. A collaboration of experts between an Operator and Service company was formed during the well planning phase to evaluate the feasibility of an automation platform for a holistic drilling advisory platform that facilitates real time decision making based on downhole and surface data. An offset well study in the area showed that nearby wells experienced recurrence incidents of wellbore instability and downhole pore pressure uncertainty. Modeling iterations for dynamic and static drilling were simulated during pre-planning phase and optimized in real time based on actual downhole and surface data information. Real time models were compared against dynamic models such as Torque and Drag, Hole Cleaning, Pore pressure, ECD (Equivalent Circulating Density), ESD (Equivalent Static Density), and tripping speed (Swab, Surge, etc.). An automated directional drilling tool was run and compared to decisions made by the directional driller to improve the tool's decision-making process for predictive well trajectory parameters. Based on the resultant models, proactive advice was given to the rig in real-time to optimize the input parameters and reduce negative impact to well operation. For example, the practical, real-time visualization helped quickly identify a decreasing pore pressure trend and avoided resultant high overbalance while drilling the 17.5 in. × 22 in. section. The early warning alert allowed swift real time reaction sent to the rig, with mud weight subsequently decreased to 9.2 ppg, avoiding a potential risk of differential sticking stuck pipe incident due to high mud overbalance. Torque and Drag monitoring throughout the well accurately identified few instances of deviation from the trend and models, which detected an early sign of deteriorating wellbore condition which eventually led to a temporary stuck pipe event. Nevertheless, the pipe was freed, which demonstrate that the real time advisory helps in minimizing and avoiding the severe impact of the stuck pipe on the drilling operation. Automated advisory effectively delivered alerts on tight spots while drilling and casing running resulting in a faster 9-5/8 in. liner running in the deviated section. Tripping advisory mode and Real-time modelling of the swab-surge limits successfully allowed the team to avoid critical areas or swabbing events, which increased tripping speed where an opportunity was available and reduced tripping speed when risk of swab/surge was high avoiding well control/well loss events. The automated directional drilling tool increases in accuracy as the dogleg increased. The intelligent advice from the model got closest to the decisions taken by the directional driller, the closer the well got to the planned trajectory. These resulted in improvement and feedback for the pre-planning model such as target radius allowance, formation properties, and optimum drilling parameters. This work takes the first steps towards drilling automation and digital integration of insights and operation. The collaboration between operator and service company resulted in a successful deployment of an automation platform as a solution to manage and mitigate risks as well as optimize drilling operations in exploration wells.
In recent years, the industry has sought insights from abundant data generated by drilling operations. One of the key focus areas is the rate of penetration (ROP) which impacts costs directly, and emissions indirectly. Previous work has succeeded in predicting and optimizing ROP, however was limited to specific fields and small-scale applications. This limitation stems from unobserved information between different fields or operations that often impacts model usability. This paper provides a new way of well planning by leveraging the power of unsupervised machine learning to deliver higher drilling efficiency, lower costs, and less uncertainty. Unsupervised machine learning techniques are used to infer information about drilling operations from real-time data that is not directly measured. Certain well types seem to be separable in low dimensions, based on qualitative interpretation of clusters visualized in 2D, and according to analyzing cluster membership based on which wells the data came from, and by associating common characteristics of wells within clusters using external information. This work introduces a novel approach to collect, separate, and extract value from data that is otherwise unused. Data synthesized by Variational Autoencoders could be used for enhanced well planning, sold as a standalone product, or shared between industry players with reduced privacy concerns, increasing the wealth of data available.
Collapse loads from uneven salt loading have been and remain a topic of discussion in the oil and gas industry. Studying this phenomenon requires large amounts of resources and risk for operators and casing vendors alike. As Oil and Gas exploration and development moves into deeper waters and more challenging conditions, novel ways of design need to be adopted to keep costs low and maintain well integrity throughout the well life cycle. Different methods and concepts from vendors, operators, and engineering consultants in casing design for long term salt loading have been reviewed and analyzed. A common Casing design software was used to analyze the different methods through modelling and load analysis with the subsequent results compared. A reliability-based design approach incorporating deforming casing dimensions and failure probabilities is proposed. A decision-making flow chart is also developed to avoid over-designing and safely optimize casing design for an exploration keeper-well. Reducing uncertainty of uneven salt loading on production casing will pave the way for more fit-for-purpose well designs. By doing that, less material surplus is generated resulting in less waste and less emissions.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.