STEP Change in Preventing Stuck Pipe and Tight Hole Events Using Machine Learning

2021 ◽  
Author(s):  
Salah Bahlany ◽  
Mohammed Maharbi ◽  
Saud Zakwani ◽  
Faisal Busaidi ◽  
Ferrante Benvenuti

Abstract Wellbore stability problems, such as stuck pipe and tight spots, are one of the most critical risks that impact drilling operations. Over several years, Oil and Gas Operator in Middle East has been facing problems associated with stuck pipe and tight spot events, which have a major impact on drilling efficiency, well cost, and the carbon footprint of drilling operations. On average, the operator loses 200 days a year (Non-Productive Time) on stuck pipe and associated fishing operations. Wellbore stability problems are hard to predict due to the varying conditions of drilling operations: different lithology, drilling parameters, pressures, equipment, shifting crews, and multiple well designs. All these factors make the occurrence of a stuck pipe quite hard to mitigate only through human intervention. For this reason, The operator decided to develop an artificial intelligence tool that leverages the whole breadth and depth of operator data (reports, sensor data, well engineering data, lithology data, etc.) in order to predict and prevent wellbore stability problems. The tool informs well engineers and rig crews about possible risks both during the well planning and well execution phase, suggesting possible mitigation actions to avoid getting stuck. Since the alarms are given ahead of the bit, several hours before the possible occurrence of the event, the well engineers and rig crews have ample time to react to the alarms and prevent its occurrence. So far, the tool has been deployed in a pilot phase on 38 wells giving 44 true alarms with a recall of 94%. Since mid-2021 operator has been rolling out the tool scaling to the whole drilling operations (over 40 rigs).

2010 ◽  
Vol 156-157 ◽  
pp. 1292-1296
Author(s):  
Jian Bing Sang ◽  
Su Fang Xing ◽  
Chen Hua Lu ◽  
Wen Jia Wang ◽  
Bo Liu

Maintaining the wellbore stability is a key factor for oil and gas drilling operations. In this paper, sock is regarded porous medium. Crevice pressure, effect of permeation and SD effect are considered. The elastic and plastic stresses around the wellbore sock were analysed according to MVM failure criterion. Distribution of stress and displacement was obtained, which can provide theory reference for the wellbore stability.


2014 ◽  
Vol 2014 ◽  
pp. 1-16 ◽  
Author(s):  
Titus N. Ofei ◽  
Sonny Irawan ◽  
William Pao

In oil and gas drilling operations, predictions of pressure losses and cuttings concentration in the annulus are very complex due to the combination of interacting drilling parameters. Past studies have proposed many empirical correlations to estimate pressure losses and cuttings concentration. However, these developed correlations are limited to their experimental data range and setup, and hence, they cannot be applicable to all cases. CFD methods have the advantages of handling complex multiphase flow problems, as well as, an unlimited number of physical and operational conditions. The present study employs the inhomogeneous (Eulerian-Eulerian) model to simulate a two-phase solid-fluid flow and predict pressure losses and cuttings concentration in eccentric horizontal annuli as a function of varying drilling parameters: fluid velocity, diameter ratio (ratio of inner pipe diameter to outer pipe diameter), inner pipe rotation speed, and fluid type. Experimental data for pressure losses and cuttings concentration from previous literature compared very well with simulation data, confirming the validity of the current model. The study shows how reliable CFD methods can replicate the actual, yet complex oil and gas drilling operations.


10.29007/4sdt ◽  
2022 ◽  
Author(s):  
Vu Khanh Phat Ong ◽  
Quang Khanh Do ◽  
Thang Nguyen ◽  
Hoang Long Vo ◽  
Ngoc Anh Thy Nguyen ◽  
...  

The rate of penetration (ROP) is an important parameter that affects the success of a drilling operation. In this paper, the research approach is based on different artificial neural network (ANN) models to predict ROP for oil and gas wells in Nam Con Son basin. The first is the process of collecting and evaluating drilling parameters as input data of the model. Next is to find the network model capable of predicting ROP most accurately. After that, the study will evaluate the number of input parameters of the network model. The ROP prediction results obtained from different ANN models are also compared with traditional models such as the Bingham model, Bourgoyne & Young model. These results have shown the competitiveness of the ANN model and its high applicability to actual drilling operations.


2021 ◽  
Author(s):  
Tesleem Lawal ◽  
Pradeepkumar Ashok ◽  
Eric van Oort ◽  
Dandan Zheng ◽  
Matthew Isbell

AbstractMud motor failure is a significant contributor to non-productive time in lower-cost land drilling operations, e.g. in North America. Typically, motor failure prevention methodologies range from re-designing or performing sophisticated analytical modeling of the motor power section, to modeling motor performance using high-frequency downhole measurements. In this paper, we present data analytics methods to detect and predict motor failures ahead of time using primarily surface drilling measurements.We studied critical drilling and non-drilling events as applicable to motor failure. The impacts of mud motor stalls and drill-off times were investigated during on-bottom drilling. For the off-bottom analysis, the impact of variations in connection practices (pick up practices, time spent backreaming, and time spent exposing the tools to damaging vibrations) was investigated. The relative importance of the various features found to be relevant was calculated and incorporated into a real-time mud motor damage index.A historical drilling dataset, consisting of surface data collected from 45 motor runs in lateral hole sections of unconventional shale wells drilled in early to mid-2019, was used in this study. These motor runs contained a mix of failure and non-failure cases. The model was found to accurately predict motor failure due to motor wear and tear. Generally, the higher the magnitude of the impact stalls experienced by the mud motor, the greater the probability of eventual failure. Variations in connection practices were found not to be a major wear-and-tear factor. However, it was found that connection practices varied significantly and were often driller-dependent.The overall result shows that simple surface drilling parameters can be used to predict mud motor failure. Hence, the value derived from surface sensor information for mud motor management can be maximized without the need to run more costly downhole sensors. In addition to this cost optimization, drillers can now monitor motor degradation in real-time using the new mud motor index described here.


2021 ◽  
Author(s):  
Sercan Gul

Abstract Drilling fluid (mud) serves various purposes in drilling operations, the most important being the primary well control barrier to prevent kicks and blowouts. Other duties include, but not limited to, maintaining wellbore stability, removing and transporting formation cuttings to the surface, cooling and lubricating downhole tools, and transmitting hydraulic energy to the drill bit. Mud quality is therefore related to most of the problems in drilling operations either directly or indirectly. The physics-based models used in the industry with drilling fluid information (i.e., cuttings transport, well hydraulics, event detection) are computationally expensive, difficult to integrate for real-time analysis, and not always applicable for all drilling conditions. For this reason, researchers have shown extensive interest in machine learning (ML) approaches to alleviate their fluid-related problems. In this study, a comprehensive review of the abundant literature on the various applications of ML in oil and gas operations, concentrating mainly on drilling fluids, is presented. It was shown that leveraging state-of-the-art supervised and unsupervised ML methods can help predict or eliminate most fluid-related issues in drilling. The review discusses various ML methods, their theory, applications, limitations, and achievements.


2021 ◽  
Author(s):  
Mario A. Rivas ◽  
Andres A. Ramirez ◽  
Bader S. Al-Zahrani ◽  
Khaled K. Abouelnaaj

Abstract One of the major challenges the Oil and Gas Industry faces nowadays during drilling operations is the twist-offs on Bottom Hole Assembly (BHA) components such as Drilling Jars, Shock Tools, Mud Motors, Roller Reamers, Stabilizers, Drill Collars, PBLs, Heavy Weight Drill Pipe (HWDP), Drill Pipe (DP), etc. To overcome this challenge, an initiative was proposed by performing a study based on twist-offs experienced on BHA components while drilling operations and recommendations are provided to reduce and eliminate twist-offs related to drilling with suboptimal drilling parameters. The statistical data for the twist-off events was collected coming from Daily Drilling Reports, and the analysis was limited to all wells which presented twist-offs on the drillstring and BHA components. Three examples of twist-offs due to drilling with erratic torque are discussed as well as a successful example of drilling parameters optimization. The three examples which presented drillstring and BHA twist-offs were analyzed using available BHA Dynamics and vibrations software and it was discovered that the parameters utilized (operational RPM) fell within the critical zone shearing force peaks (resonance vibrations). The components with the most twist-offs were identified. The hole size where we have the most twist-offs were also identified, which will help in focusing on these areas for the recommendations provided. This analysis will help Drilling Engineers and Foremen to foresee vibration dysfunctions and act accordingly by the use of available BHA Dynamics software in order to optimize drilling parameters before and during drilling. By drilling within a safe operating RPM window (away from resonant RPM), there will be reduction in the number of twist-offs and associated lost time.


2021 ◽  
Author(s):  
Khaqan Khan ◽  
Mohammad Altwaijri ◽  
Sajjad Ahmed

Abstract Drilling oil and gas wells with stable and good quality wellbores is essential to minimize drilling difficulties, acquire reliable openhole logs data, run completions and ensure well integrity during stimulation. Stress-induced compressive rock failure leading to enlarged wellbore is a common form of wellbore instability especially in tectonic stress regime. For a particular well trajectory, wellbore stability is generally considered a result of an interplay between drilling mud density (i.e., mud weight) and subsurface geomechanical parameters including in-situ earth stresses, formation pore pressure and rock strength properties. While role of mud system and chemistry can also be important for water sensitive formations, mud weight is always a fundamental component of wellbore stability analysis. Hence, when a wellbore is unstable (over-gauge), it is believed that effective mud support was insufficient to counter stress concentration around wellbore wall. Therefore, increasing mud weight based on model validation and calibration using offset wells data is a common approach to keep wellbore stable. However, a limited number of research articles show that wellbore stability is a more complex phenomenon affected not only by geomechanics but also strongly influenced by downhole forces exerted by drillstring vibrations and high mud flow rates. Authors of this paper also observed that some wells drilled with higher mud weight exhibit more unstable wellbore in comparison with offset wells which contradicts the conventional approach of linking wellbore stability to stresses and rock strength properties alone. Therefore, the objective of this paper is to analyze wellbore stability considering both geomechanical and drilling parameters to explain observed anomalous wellbore enlargements in two vertical wells drilled in the same field and reservoir. The analysis showed that the well drilled with 18% higher mud weight compared with its offset well and yet showing more unstable wellbore was, in fact, drilled with more aggressive drilling parameters. The aggressive drilling parameters induce additional mechanical disturbance to the wellbore wall causing more severe wellbore enlargements. We devised a new approach of wellbore stability management using two-pronged strategy. It focuses on designing an optimum weight design using geomechanics to address stress-induced wellbore failure together with specifying safe limits of drilling parameters to minimize wellbore damage due to excessive downhole drillstring vibrations. The findings helped achieve more stable wellbore in subsequent wells with hole condition meeting logging and completion requirements as well as avoiding drilling problems.


2021 ◽  
Author(s):  
Avirup Chatterjee ◽  
Amitava Ghosh ◽  
Priveen Raj Santha Moorthy

Abstract This paper presents a case study on the role of geomechanics to identify possible failure mechanisms for non-productive time (NPT), avoid drilling risks and minimize costs in a field development drilling campaign, Offshore Sarawak Malaysia. Drilling optimization and reducing NPT for the drilling campaign was one of the key focus for maintaining the drilling time and costs. Drilling of moderately to highly deviated wells in this field has proven to be extremely challenging. Numerous lost-time incidents due to tight hole, stuck pipe, pack-off, casing held up were experienced, particularly when drilling through the shallow overburden shales and deeper reservoirs interbedded with shales and coals. Faced with continually increased NPTs, a geomechanical model was developed using regional offset wells to understand the mechanism of failures. A geomechanical model was developed to quantify the minimum recommended mud weights and optimize the wellbore trajectories. The outcome of this study was used as key input for casing and mud design. The in-situ stress state derived from field wide geomechanical model indicates the field is associated with a normal faulting stress regime, i.e., Shmin < SHmax < SV. The presence of relatively weak rocks means the field is potentially subject to stress-induced wellbore instability problems. However, observations of numerous time-dependent failures imply secondary influences must also be considered to arrive at possible remediation strategies. It was observed that the combination of weak rocks and numerous time-dependent failures using different types of mud system have contributed to wellbore stability problems. The wellbore stability is due to reactive shale, which is time sensitive as majority of the drilling problems are observed after drilling. The major contributor to the time-dependent deterioration process is mechanical and chemical imbalances between shale and drilling fluids compounded by large open-hole exposure area and contact time resulting in rising pore pressure caused by the invasion of drilling fluid into the formations, and then exacerbated by less-than-optimal drilling practices. This finding, together with improved geomechanical understanding of the field helped to evaluate the safe mud weight windows, formulate the mud designs and optimize drilling practices. All the planned wells were drilled successfully without any loss time incidents and non-productive time. This paper presents an integrated approach and workflow that combines the drilling data and formation response to identify the most likely causative mechanisms of the time-delayed wellbore instabilities in a mature field. This knowledge was then used to develop strategies for optimizing future drilling operations in the field.


2012 ◽  
Vol 535-537 ◽  
pp. 323-328 ◽  
Author(s):  
Long Li ◽  
Jin Sheng Sun ◽  
Xian Guang Xu ◽  
Cha Ma ◽  
Yu Ping Yang ◽  
...  

Due to their special properties, nanomaterials had potential application value, and they could play an essential role in improving mudcake quality, assisting in film-forming, reducing lost circulation, and enhancing wellbore stability. Some nanomaterials, such as nanocomposite filtration-reducing agent, nanocomposite viscosifier, nanosized emulsion lubricant, nanometer organoclay, and so on, were introduced, and all of them had significantly influence on the process of drilling operations. As a result, the application of nanomaterials in the field of drilling fluids are very useful for cleaning borehole, maintaining borehole stability, protecting reservoir, and enhancing oil and gas recovery. Finally, the further application of nanomaterials in drilling fluids is also prospected.


2021 ◽  
Author(s):  
Peter Batruny ◽  
Zuriel Aburto ◽  
Pete Slagel ◽  
M Razali Paimin ◽  
Mohamad Mahran ◽  
...  

Abstract Downhole vibration is the primary cause of low Rate of Penetration (ROP), and severe vibration causes Bottom Hole Assembly (BHA) tool failure; it is especially apparent during Hole Enlargement While Drilling (HEWD) due to multiple points of cutter contact with the formation at the bit and the underreamer. Electronic, high data rate sensors, embedded in the 17-1/2 in. bit and the 22 in. underreamer, generated detailed insights on the location, mechanism, and magnitude of downhole vibration. Time-based downhole vibration logs from the sensors were plotted alongside mudlogging data. Finite Element Analysis (FEA) models were run using actual drilling parameters to simulate downhole conditions and provide a baseline model for further optimization. Sensor data was isolated for each of the bit and underreamer to better understand the individual and combined vibration mechanisms during hole enlargement while drilling operations. The FEA model was then used to optimize BHA configuration and underreamer placement that result in the largest drilling parameter window for future BHAs. The data from sensors showed that whirl occurred when the bit entered sandstone bodies and the underreamer was still in shale. The data also showed that when the bit was in shale and the underreamer in sandstone, the underreamer experienced stick slip which induced stick slip at the bit. The BHA dynamics model run with actual drilling parameters showed a narrow drilling window with multiple critical vibration points at the same rotation speed (RPM). A new BHA was developed for the next well with a wider drilling window and less critical vibration points for the same RPM. The analysis identified key operational mitigations when stick slip or whirl are encountered. This work leveraged technology and insights generated from data to shorten the learning curve and improve operations after just one well. In a drilling age where operations are becoming increasingly complex, relying on surface data is no longer enough.


Sign in / Sign up

Export Citation Format

Share Document