The SPE has split the former "Management & Information" technical discipline into two new technical discplines:
- Data Science & Engineering Analytics
The SPE has split the former "Management & Information" technical discipline into two new technical discplines:
|Theme||Visible||Selectable||Appearance||Zoom Range (now: 0)|
Krikor, Ara (ADNOC Offshore) | Bimastianto, Paulinus Abhyudaya (ADNOC Offshore) | Khambete, Shreepad Purushottam (ADNOC Offshore) | Cotten, Michael Bradley (ADNOC Offshore) | Toader, Lucian (ADNOC Offshore) | Landaeta Rivas, Fernando Jose (ADNOC Offshore) | Duivala, Shahid Yakubbhai (ADNOC Offshore) | Mughal, Muhammad Idrees (ADNOC Offshore) | Al Ameri, Suhail Mohammed (ADNOC Offshore) | AlMarzooqi, Adel AbdulRahman (ADNOC Offshore) | Chevallier, Bertrand (SLB) | Vallet, Laurent François (SLB) | Ullah, Nadeem Hidayat (SLB) | Qadir, Ahsan (SLB) | Al Khufash, Hassan Walid (SLB) | Shareef, Raneef Mohamed (SLB) | Ul Islam, Muhammad Ashar (SLB)
Abstract Digital Twin has become pillar of Oil and Gas industry. Previously, there was no solution / tool available to detect early bit failure, therefore Real Time Operations Centre (RTOC) team decided to develop and implement Mechanical Specific Energy (MSE) Ratio in real time to detect drilling dysfunctions and consequently prevent Non-Productive Time (NPT). The paper aims to demonstrate how MSE ratio helps to enhance the performance efficiency in real time while drilling operation. RTOC aggregates data from all the operational Rigs in real time and digital twin solution was developed to compute MSE Ratio in real time from downhole and surface MSE. Automated Machine Learning workflows compute downhole Weight on Bit and downhole Torque to compute downhole MSE. Surface MSE is automatically computed based on surface parameters. Output is filtered with Machine Learning Rig State workflow to avoid any false computation. The algorithmic outputs are calculated in time dataset and then converted to depth-based data in real time. Trend analysis of outputs will help to identify inefficiency and take decision on time. The Dynamic Solution can be used as smart drilling decision tool to detect bit performance abnormality and to enhance the efficiency for drilling operation. Trend of MSE Ratio output has helped to identify the bit failure in real time which further paves the way to decide bit trip and optimize the performance of the well. Case Study will demonstrate where trend of MSE ratio reached below the defined baseline and provided alert for potential bit failure. Bit trip was performed and based on bit dull grading, it was decided to run with new bit. MSE ratio observed on the new bit reached back to normal trend as per defined baseline. New bit was able to drill and complete the section within the plan. This tool has been implemented successfully on all the operational Rigs to monitor performance in real time and can help to take decisions to safeguarding and optimize the performance of the sections and well. Trend analysis of MSE Ratio along with other parameters can help to detect inefficiency and optimize rate of penetration (ROP) in real time. This innovative approach of using MSE Ratio can help to build new digital twin solutions and enhance utilization of MSE output. Machine Learning workflows leverages the objective of digital drilling transformation and to optimize drilling efficiency in real time. Output helps to improve performance and prevent unwanted events. Solution can be further enhanced to detect other drilling dysfunctions and define efficiency roadmap with the combination of Drilling Strength.
Al-Riyami, N. (Exebenus, Stavanger, Norway) | Revheim, O. (Exebenus, Stavanger, Norway) | Robinson, T. S. (Exebenus, Stavanger, Norway) | Batruny, P. (PETRONAS Carigali, Kuala Lumpur, Malaysia) | Meor Hakeem, M. H. (PETRONAS Carigali, Kuala Lumpur, Malaysia) | Tze Ping, G. (Faazmiar Technology Sdn Bhd, Kuala Lumpur, Malaysia)
Abstract O&G operators seek to reduce CAPEX by reducing unit development costs. In drilling operations this is achieved by reducing flat time and bit-on-bottom time. For the last five years, we have leveraged data generated by drilling operations and machine learning advancements in drilling operations. This work is focused on field test results using a real-time global Rate of Penetration (ROP) optimization solution, reducing lost time from sub-optimal ROPs. These tests were conducted on offshore drilling operations in West Africa and Malaysia, where live recommendations provided by the optimization software were implemented by the rig crews in order to test real-world efficacy for improving ROP. The test wells included near-vertical and highly deviated sections, as well as various formations, including claystones, sandstones, limestones and siltstones. The optimization system consisted of a model for estimating ROP, and an optimizer algorithm for generating drilling parameter values that maximize expected ROP, subject to constraints. The ROP estimation model was a deep neural network, using only surface parameters as inputs, and designed to maximize generalizability to new wells. The model was used out-of-the-box, with no specific retraining for the field testing. During field-tests, increased average ROP was observed after following recommendations provided by the optimizer. Compared to offset wells, higher average ROP values were recorded. Furthermore, drilling was completed ahead of plan in both cases. In the Malaysian test well, following the software's advice yielded an increase in ROP from 10.4 to 31 m/h over a 136 m drilling interval. In the West Africa well, total depth was reached ∼24 days ahead of plan, and ∼2.4 days ahead of the expected technical limit. Importantly, the optimization system provided value in operations where auto-driller technologies were used. This work showcases field-test results and lessons learnt from using machine learning to optimize ROP in drilling operations. The final plug-and-play model improves cycle efficiency by eliminating model training before each well and allows instantaneous, real-time intervention. This deployable model is suitable to be utilized anytime, anywhere, with retraining being optional. As a result, minimizing the invisible lost time from sub-optimal ROP and reducing costs associated with on-bottom drilling for any well complexity and in any location is now part of the standard real-time operation solutions. This deployment of technology shows how further optimization of drilling time and reduction in well cost is achievable through utilization of real time data and machine learning.
Zhu, Jun (Vertechs Energy Group) | Zhang, Wei (Vertechs Energy Group) | Zeng, Qijun (Vertechs Energy Group) | Liu, Zhenxing (Vertechs Energy Group) | Liu, Jiayi (PetroChina Southwest Oil & Gas Field Company) | Liu, Junchen (PetroChina Southwest Oil & Gas Field Company) | Zhang, Fengxia (PetroChina Southwest Oil & Gas Field Company) | He, Yu (PetroChina Southwest Oil & Gas Field Company) | Xia, Ruochen (PetroChina Southwest Oil & Gas Field Company)
Abstract In the past decade, the operators and service companies are seeking an integration solution which combines engineering and geology. Since our drilling wells are becoming much more challenging than ever before, it requires the office engineer not only understanding well construction knowledge but also need learn more about geology to help them address the unexpected scenarios may happen to the wells. Then a novel solution should be provided to help engineers understanding their wells better and easier in engineering and geology aspects. The digital twin technology is used to generate a suppositional subsurface world which contains downhole schematic and nearby formation characteristics. This world is described in 3D modelling engineers could read all the information they need after dealt with a unique algorithm engine. In this digital twin subsurface world, the engineering information like well trajectory, casing program, BHA (bottom hole assembly) status, are combined with geology data like formation lithology, layer distribution and coring samples. Both drilling or completion engineers and geologist could get an intuitive awareness of current downhole scenarios and discuss in a more efficient way. The system has been deployed in a major operator in China this year and received lot of valuable feedback from end user. First of all, the system brings solid benefits to operator's supervisors and engineers to help them relate the engineering challenges with according geology information, in this way the judgement and decision are made more reliable and efficiently, also the solution or proposal could be provided more targeted and available. Beyond, the geology information from nearby wells in digital twin modelling could also provide an intuitional navigation or guidance to under-constructed wells avoid any possible tough layers via adjusting drilling parameters. This digital twin system breaks the barrier between well construction engineers and geologists, revealing a fictive downhole world which is based on the knowledge and insight of our industry, providing the engineers necessary information to support their judgement and assumption at very first time when they meet downhole problems. For example, drilling engineers would pay extra attention to control the ROP (rate of penetration) while drilling ahead to fault layer at the first time it is displayed in digital twin system, which prevent potential downhole accident and avoid related NPT (non-production time). The integration of engineering and geology is a must-do task for operators and service companies to improve their performance and reduce downhole risks. Also, it provides an interdisciplinary information to end user for their better awareness and understanding of their downhole asset. Not only help to avoid some possible downhole risks but also benefit on preventing damage reservoir by optimizing the well construction parameters.
Al-Sahlanee, Dhuha T. (BP) | Allawi, Raed H. (Thi-Qar Oil Company) | Al-Mudhafar, Watheq J. (Basrah Oil Company) | Yao, Changqing (Texas A&M University)
Abstract Modeling the drill bit Rate of Penetration (ROP) is crucial for optimizing drilling operations as maximum ROP causes fast drilling, reflecting efficient rig performance and productivity. In this paper, four Ensemble machine learning (ML) algorithms were adopted to reconstruct ROP predictive models: Random Forest (RF), Gradient Boosting (GB), Extreme Gradient Boost (XGB), and Adaptive Boosting (AdaBoost). The research was implemented on well data for the entire stratigraphy column in a giant Southern Iraqi oil field. The drilling operations in the oil field pass through 19 formations (including 4 oil-bearing reservoirs) from Dibdibba to Zubair in a total depth of approximately 3200 m. From the stratigraphic column, various lithology types exist, such as carbonate and clastic with distinct thicknesses that range from (40-440) m. The ROP predictive models were built given 14 operating parameters: Total Vertical Depth (TVD), Weight on Bit (WOB), Rotation per Minute (RPM), Torque, Total RPM, flow rate, Standpipe Pressure (SPP), effective density, bit size, D exponent, Gamma Ray (GR), density, neutron, and caliper, and the discrete lithology distribution. For ROP modeling and validation, a dataset that combines information from three development wells was collected, randomly subsampled, and then subdivided into 85% for training and 15% for validation and testing. The root means square prediction error (RMSE) and coefficient of correlation (R-sq) were used as statistical mismatch quantification tools between the measured and predicted ROP given the test subset. Except for Adaboost, all the other three ML approaches have given acceptable accurate ROP predictions with good matching between the ROP to the measured and predicted for the testing subset in addition to the prediction for each well across the entire depth. This integrated modeling workflow with cross-validation of combining three wells together has resulted in more accurate prediction than using one well as a reference for prediction. In the ROP optimization, determining the optimal set of the 14 operational parameters leads to the fastest penetration rate and most economic drilling. The presented workflow is not only predicting the proper penetration rate but also optimizing the drilling parameters and reducing the drilling cost of future wells. Additionally, the resulting ROP ML-predictive models can be implemented for the prediction of the drilling rate of penetration in other areas of this oil field and also other nearby fields of the similar stratigraphic columns.
Abstract In Brazil, pre-salt assets account for 70% of the national oil and gas production. Even after 15 years of Brazilian pre-salt exploration and development, modelling these complex reservoirs remains a challenging and uncertain task. With such high geological uncertainty, drilling campaigns experience unplanned bottomhole-assembly (BHA) trips due to severe shock and vibration, low rate of penetration (ROP), and premature polycrystalline diamond compact (PDC) drill-bit cutting structure damage. This paper presents a case study of the successful use of an acoustic logging-while-drilling (LWD) borehole image log for drilling optimization. The ultrasonic image was acquired at high-resolution (0.2 in.), displaying clear rock formation textural and hardness variations. These contrasts are the key for understanding and simulation of drill bit-rock interaction; therefore, using the high-resolution LWD borehole image log has the potential to optimize and reduce uncertainty in the operator's upcoming drilling campaign.
Summary The rate of penetration (ROP) refers to the speed at which a drill bit breaks through rock and deepens the drill hole. ROP is of great significance for drilling optimization and drilling cost savings. In real-world settings, the ROP data available for learning and training in a new oil field are scarce or even completely missing. In this paper, we propose a novel unsupervised multisource domain adaptation (MSDA) regression method for ROP that considers transferring the knowledge learned from a well-labelled source domain to the target domain with few labeled ROP data. First, we build a multisource unsupervised domain adaptation framework based on adversarial learning (WD-MUDA) which uses a weighted combination of multiple source domains to realize the fine-grained alignment of different data distributions. Specifically, we define a new similarity metric for different domains based on the Wasserstein distance. Furthermore, considering the uneven distribution of real drilling data samples, a novel regression loss is introduced to minimize the gradient discrepancy between multisource and target samples and improve the prediction accuracy of target samples. Extensive experiments on real drilling data sets reveal that the proposed method is effective and outperforms the state-of- the-art domain adaptation methods for ROP prediction. Introduction In the process of drilling, the drilling ROP is a measure of the drilling speed per unit time per unit area (Bourgoyne et al. 1986). ROP is a key index reflecting drilling efficiency and is affected and restricted by factors such as bit size, weight on bit (WOB), and rock lithology. ROP modeling can effectively improve drilling efficiency and optimize drilling costs (Schreuder and Sharpe 1999). The traditional ROP method determines physical equations and bases mathematical equation modeling on the bit size, rotational speed, rock lithology, etc., and the prediction accuracy of these models depends on empirical correlations (Al-AbdulJabbar et al. 2021). With the development of high-performance computer systems, the accuracy and complexity of prediction models have been significantly improved. Classic machine learning methods are usually built on the assumption that training data and test data are independent and identically distributed (Tan et al. 2018).
Addresses considerations involved in drilling abnormal pressures, working in sour gas environments and planning fishing operations. Discusses procedures for optimizing bit hydraulics, bit weight and rotary speed to attain minimum cost drilling. This online training course is categorized under the Drilling discipline.
Al Fakih, Abdulqawi M. (SLB) | Dorantes, Arnott Dorantes (SLB) | Perez, Carlos Alberto (SLB) | Duque, Gerardo Javier (SLB) | Dewidar, Mohamed Nabil (SLB) | Nafi, Mohamed Khalil (SLB)
Abstract Optimizing well time and its expenditures have become a necessity for which all drilling operators and service companies are challenged on. This requires a combination of well engineering and operations efforts, from avoiding service quality issues that lead to Non-Productive Time (NPT) to reducing or eliminating Invisible Lost Time (ILT). Traditionally, more focus and efforts are concentrated around NPT avoidance, as its impact is visible and has a huge and direct financial consequence that leads to an impact on well cost. The ILT was left out of focus due to needing proper measurement tools. In turnkey projects, the real-time monitoring concept was adopted to reduce the ILT and, at the same time, the NPT. From 2018 to 2022, the time interval selected for this study, nearly 800 wells were drilled with good progressive performance of feet per day (Ft/day) year on year and continuous reduction in NPT impact. The performance was measured on 40,000 days of operating time which was impacted by almost 5,000 days of related non-productive time. The multi-hour loss events were classified according to their root cause, divided into four major categories, hole condition, human decision, tool failure, and other external (i.e., waiting times). This paper will describe the solution for the first two causes categories of time losses. During the problem definition process, a common factor was the criticality of having a short response time at the early stages of the events. The evidence showed a direct correlation between the response time and the total lost hours in any event; hence the efforts focused on reducing the time between early detection and execution of corrective actions. Implementing an Operational Integrity Center aimed to standardize the detection of events and establish a central support team that will recognize wrong actions and recommend corrective actions quickly. The Center integrated multiple digital solutions to maximize the accuracy and reliability of predictions. The introduction of the digital operation integrity center (DOIC) resulted in a 30% reduction in the global NPT in terms of the number of days up to the end of 2022, considering the increasing operating time. This success is based on three major pillars: process, people, and tools. In terms of process, the team established a new set of processes (SOP)to monitor operations and set an iterative do-learn-improve cycle. Those processes have enhanced the workflows of transforming data into insights and delivering these insights to Well Site Leader (WSL), reducing the response time. In terms of people, the team was trained in process assurance, digital tools, event detection, stress management, and effective communication; the training focused on reducing the response time after identifying signs of possible events. The final pillar was implementing digital tools; the DOIC used monitoring and prediction tools. Monitoring tools are well known and have been used for many years to detect early signs of problems and deviation of trends from the drilling program; however, these tools rely majorly on human interpretation, becoming susceptible to bias or noise. Predictive tools will resolve the human impact since they are based on algorithms, and the new generations of algorithms have a certain level of interpretation. These tools have been identified as the major step toward reducing the response time to signs of events and increasing the reliability of the alerts. The new version of predictive tools is being introduced and trailed one by one in DOICs based on their maturity and business needs. The manuscript describes the methodology to implement a Digital Operation Integrity Centre, the lessons learned, and an in-depth view of the digital tool's capabilities to increase the prediction of events and their capability to advise on corrective actions before the event happens.
Abstract A drill-off test is a special drilling test where the drawworks is locked and the string elasticity causes the bit to penetrate the formation at a decreasing weight on bit (WOB). It is often used as a tool for finding how the rate of penetration (ROP) varies as a function of WOB and for finding optimal drilling parameters. This paper sheds a critical light on the use of drill-off test by discussing various errors and pitfalls usually ignored today. The paper starts by presenting a simple but widely used method for converting surface hookload data into an ROP vs. WOB curve, commonly known as a drilling performance curve. Next, it discusses and tries to quantify various error sources, such as hookload sensor errors, residual wellbore drag, and formation inhomogeneities. The paper uses real field data and a comprehensive simulation model to illustrate the magnitude of the various errors and how they affect the drilling performance curve. Finally, the paper suggests ways to check the accuracy and validity of the drill-off tests. The analysis shows that the variable wellbore friction is an error source that depends on many parameters, such as string length, wellbore inclination, rotational string speed, and ROP. It also shows that it is possible to model the errors and apply correction formulas to improve the quality and accuracy of WOB and ROP. Although friction-related errors can be reduced by applying proper corrections to the estimated WOB and ROP, there is still a need to check the validity of the drill-off test results with other types of drilling tests. The paper presents several proposals for alternative and complementary drilling tests, such as drill-on test (here defined as a test where WOB is continuously increased), steady state (constant WOB) drilling test, combo test, and sinusoidal perturbations test.
Fernandez Berrocal, Miguel (University of Stavanger, UiS) | Shashel, Alina (University of Stavanger, UiS) | Usama, Muhammad (University of Stavanger, UiS) | Hossain, Md Akber (University of Stavanger, UiS) | Baris Gocmen, Emre (University of Stavanger, UiS) | Tahir, Ali (University of Stavanger, UiS) | Sui, Dan (University of Stavanger, UiS) | Florence, Fred (Rig Operations, LLC)
Abstract The work focuses on the drilling control algorithms as well as Artificial Intelligence (AI) technique implementation into an in-house real-time drilling simulator developed by the Drillbotics® Virtual Rig Team from the University of Stavanger, the winner of 2021-2022 Drillbotics Competition. The designed simulator consists of a topside model capable of calculating block position, surface hookload, surface torque, and bottom hole pressure. To achieve drilling efficiency, a formation-based rate of penetration (ROP) optimization module is running in real-time, where the safe-operational windows are considered to reduce/avoid drilling accidents, like stick-slip, axial vibrations, poor hole cleaning, and low efficiency etc. The obtained optimal WOB and RPM by solving such ROP optimization are used as setpoints and then fed into the rotary steerable system module (RSS module) to steer the bit following a planned path. Such path is designed with multiple Bezier curves that can pass given target coordinates and maintain low dogleg severity (DLS). Furthermore, the high-tech AI methodologies are integrated to the simulator to smartly manage downhole pressure via perceiving and interpreting the data, learning through the trial, training through given policy, and taking optimal actions offered by the AI-agent. The simulator is demonstrated to be a powerful and user-friendly tool for path design and optimization, real-time path control, and drilling performance optimization. It provides interactive and automatic operations of steering a bit passing multiple given target points and optimizing drilling behaviors to achieve high efficiency and low costs. From the results, the simulated (real-time) trajectory steered by the automatic RSS module integrating with surface drilling/control modules has small deviations from the planned trajectory. In the meanwhile, the simulator can precisely detect formation changes, accurately control the downhole pressure, and automatically optimize the drilling speed. The progress of the whole simulation can be followed through the web-based graphical user interface (GUI) remotely, where the depth-base data view, time-base data view and 3D graphical wellbore trajectories are visualized. After drilling, data analytics is conducted so that useful information from operational drilling data can be extracted and subsequently evaluated for post well-analysis.