Rig Site Research Articles

Self-supervised denoising at low signal-to-noise ratios: A seismic-while-drilling application

Self-supervised blind-mask denoising networks overcome the challenge of requiring clean training targets by employing a mask on raw noisy data to form the input for training while using the unmasked version as the network's target. The application of such networks has shown considerable strength in suppressing both random and coherent noise in seismic data. However, because such networks need to figure out the target (clean signal) on their own, they struggle at low signal-to-noise ratios. Seismic-while-drilling acquisitions result in seismic data of very low quality because the drilling operation introduces significant noise propagating from the rig site. Due to its consistent and low-frequency nature, it is hard to design a noise mask to hide the rig noise from the network without also hiding useful information required for predicting the signal. However, by reframing the task from a noise suppression to a noise prediction task and utilizing a mask to hide the signal from the network, the rig noise can be predicted accurately. Therefore, the difference between the network's prediction and the raw data results in common bit (equivalent to shot, but continuous) gathers with a significantly higher signal-to-noise ratio due to the removal of rig noise. Illustrated on six common bit gathers, this reversed methodology is shown to separate the rig noise and signal, even in their shared bandwidth. The additional use of explainable artificial intelligence is investigated as a means of avoiding the manual step of creating the signal mask, providing promising results. This study lays the ground work for suppression of high-amplitude, consistent noises, such as those arising from well site operations like fluid injection procedures for carbon sequestration or geothermal energy production purposes.

Safety Behavior Analysis in the Drilling Rig Site Operations of Pertamina Hulu Mahakam

PT Pertamina Hulu Mahakam is Indonesia national oil company that produce and operate gas and oil field in Mahakam, East Kalimantan Area. It spreads from swamp delta to shallow water offshore area. In 2022, the company operates 5 drilling rigs, which are 3 Jack Up Rigs and 2 Swamp Barge Rigs. The drilling rig is used to perform the operations of well construction activities for development and explorations wells, from spud, drilling, until well completion. The operations on the drilling rig have a high-risk profile. It involves handling equipment, tools, tripping hazard, lifting operations, moving object, drop object, power system, rotation system, high pressure lines and simultaneous operations. A safety system, campaign, initiatives, and measurement are deployed on the rig site to keep the rig crew away from incident. Despite safety initiatives in place on the rig site, however, incident still happens. If incident happened, there will be lost of productivity, man hours, medical cost, administration, and dedicated investigation time. The operations need to be stopped and reevaluated again before continuing the job. Due to the most common factor of incident is human factor, hence, to understand how safety initiatives conducted and implemented by people on the rig, the research uses the theory of planned behavior. The research took sample of questionnaires and interview from personnel on the rig, which are the actors of safety initiatives. It involves direct and indirect method, and comparison between descriptive (manual method) and PLS analysist. On PLS analysis, author compares independently the result between: Direct Measurement (A), Control Belief (B) and Control belief multiply to the outcome evaluation / motivation / power, depend on the factors of the TPB (B x C). From the result, it is observed that the determinant factors of the theory of planned behavior such as: attitude, subjective norm and perceived behavioral control is confirmed to have effect on the intention and safety incident avoidance. Based on the descriptive analysis, all variable element of TPB have high to very high category, except Direct Measurement of Perceived Behavioural Control (PBC) that falls into medium category. This give indication that the level of control, ease or difficulties of rig workers in performing safety initiatives is low compare to the other factors. It is shown by the questionnaire result that despite they have control in performing safety initiatives, however, when incident happened, they state that they have less control. On the hypothesis result, the model B x C has the best output from reliability test, however, it is shown that the attitude has no effect on safety behavior intention. This finding relates to the answer on the level of worries and concern on safety of the rig crew which supposed to be undesirable when incident happened, however the answer was more on desirable. This part can be explored more on how the rig worker view the “worry or concern”, which due to their nature of their workplace, they might use this as a tool to keep vigilant and awareness on the workplace.

Techno-Economic and Environmental Analysis of Decommissioned Flowline, Umbilical, and Tubular for Breakwaters

This paper presents the application of recycled tubular, flowline, and umbilical in coastal protection structures. Flowline and tubular are found to improve the load resistance capacity of concrete beams. Embedment of flowline, umbilical, and tubular into concrete beams would be beneficial to the structural performance, which do not noticeably alter the initial cracking strength of the concrete beam but will provide good post-cracking resistance. A techno-economic analysis was performed, which revealed that coastal protection concrete structures with decommissioned components accounting for more than 25% of the concrete weight could be both economically viable and environmentally friendly options. Since global warming is the most dominant environmental impact (i.e., 63%), recycling these decommissioned components from offshore structures could impose positive environmental impacts. Given the limited supply of construction materials in the remote coastal area as well as its proximity to decommissioned oil and gas rig sites, these decommissioned components could have great potential for use as construction materials in the coastal areas adjacent to the oil exploration. This preliminary study finds no showstopper for the concept of recycling the mentioned decommissioned components as coastal protection concrete structures from structural performance, environmental impact, and economic perspectives.

Collaborative Approach Optimizes Automated-Drilling Performance Measurement

_ This article, written by JPT Technology Editor Chris Carpenter, contains highlights of paper OTC 31579, “A Successful Case Study of a Collaborative Approach in Operational Optimization Through Adoption of Automated-Drilling-Performance Measurement,” by Muhammad Afiq Arif Normin, TDE Group, and Azlesham Rosli and Meor M.H.M. Hashim, SPE, Petronas, et al. The paper has not been peer reviewed. Copyright 2022 Offshore Technology Conference. Reproduced by permission. _ This paper discusses the strategy devised, the approach implemented, and the challenges experienced in the adoption and implementation of an automated drilling-performance-measurement (ADPM) system to be used onsite and remotely. The stages of the optimization of the ADPM system are broken down into prespud operations, operations, and post-well analysis. The successful result of this deployment has seen total actual savings of 2.94 days throughout the campaign. From 2016 to 2021, the operator gained 39.03 days of actual savings for their rig fleet. The ADPM Tool The ADPM tool was introduced in 2016 as part of the operator’s digitalization effort. The tool was integrated into operations at the Wells Real-Time Center (WRTC) and was managed by a wells technical application champion (WTAC). With this integration in place, the operator aimed to deliver all wells, whether vertical, horizontal, or extended-reach, in the most consistent and efficient way without jeopardizing the operation’s safety. To ensure the investment bore dividends, this initiative required a major collaborative effort. The tool’s main input is the rig’s real-time surface data obtained by mud-logging sensors. The real-time data are transmitted to the WRTC server in Kuala Lumpur and stored. Access to the data is provided to the ADPM tool to extract the necessary data required for rig-state detection. The secondary input for the ADPM tool is the daily drilling report (DDR) prepared by drilling supervisors at the rig site. The extraction of information from the DDRs serves two purposes: to provide information on the activity performed on the surface not detected by rig-state detection and to provide a reference for ADPM personnel during data processing and quality control. Each activity code and subcode associated with the DDR also is integrated into the ADPM database. Merging both data has provided more insight to the project team because a comparison between the activity reported in the DDRs and the activity detected by the ADPM can be highlighted. During the initial phase of ADPM deployment, a list of the key performance indicators (KPIs) was defined and established by the WTAC. This set of KPIs covered the tripping, drilling, and casing and liner operations necessary to determine invisible lost time (ILT). For tripping operations, the critical KPIs are slip time, tripping-in speed, and tripping-out speed. All KPIs are differentiated as having been performed in cased hole or open hole. Next is on-bottom drilling, with five focused KPIs. Finally, three KPIs were dedicated to the casing and liner operations: slips time, average pipe moving speed, and gross running rate. As with tripping operations, all KPIs were differentiated as having been performed in cased hole or open hole except slips time. All KPIs were computed from a single data source (the real-time data).

Probabilistic assessment of equivalent fracture aperture constrained on quasi-real-time drilling mud loss data

We provide a rigorous workflow to quantify the effects of key sources of uncertainty associated with equivalent fracture aperture estimates w constrained through mud loss information acquired while drilling a well in a reservoir. A stochastic inverse modeling framework is employed to estimate the probability distribution of w. This choice is consistent with the quantity and quality of available data. The approach allows assessing the probability that values of w inferred from mud loss events exceed a given threshold. We rely on a streamlined analytical solution to model mud losses while drilling. We explicitly consider uncertainties associated with model parameters and forcing terms, including drilling fluid rheological properties and flow rates, pore fluid pressure, and dynamic drilling fluid pressure. A synthetic scenario is considered to provide a transparent reference setting against which our stochastic inverse modeling workflow can be appraised. The approach is then applied to a real-case scenario. The latter is associated with data monitored on a rig site. A direct comparison of the impact of data collected through two common techniques (respectively, relying on flow meter sensors or pump strokes) on the ensuing probability of w is provided. A detailed analysis of the uncertainty related to the level of data corruption is also performed, considering various levels of measurement errors. Results associated with the field setting suggest that the proposed workflow yields probability distribution of w that are compatible with interpretations relying on traditional analyses of image logs. Results stemming from direct and indirect flow data display similar shapes. This suggests the viability of the probabilistic inversion methodology to assist quasi-real-time identification of equivalent fracture apertures on the basis of routinely acquired information during drilling.

Drill Bit Failure Forensics Using 2D Bit Images Captured at the Rig Site

Summary Identifying the root cause of damage of a pulled bit as soon as possible will aid in preparation for future drilling operations. Today, bit damage analyses are often time-consuming, delayed, subjective, and error prone. A novel automated forensics approach is presented in this paper for polycrystalline diamond compact (PDC) bit damage root cause analysis using 2D bit photos that can be easily captured on a phone or camera at the rigsite. A labeled data set consisting of 125 actual bit images and 800 synthetic images was first created with the cutters appropriately identified and labeled. Using this data set, a convolutional neural network (CNN) along with other image processing techniques was applied to first identify the individual cutters and their positions on the bit and then to quantify the damage to the cutters. A cutter detection accuracy of over 97% and a damage quantification accuracy of 97% were achieved. A separate classifier was then trained to directly identify the root cause of failure from the bit images. This classifier utilized a separate data set that consisted of multiple bit images from 25 distinct bit runs. This data set was labeled into different types of failure mechanisms through analysis by a subject-matter expert. The trained classifier developed could properly identify the root causes of failure when the bit photo quality met certain minimum standards. One key observation was that bit images are not always captured appropriately, and this reduces the accuracy of the proposed methodology. By identifying the potential root causes of PDC damage through image processing, drilling parameters can be optimized to prolong future bit life.

Development of Digital Twins for Drilling Fluids: Local Velocities for Hole Cleaning and Rheology Monitoring

AbstractIn this work, we present our advances to develop and apply digital twins for drilling fluids and associated wellbore phenomena during drilling operations. A drilling fluid digital twin is a series of interconnected models that incorporate the learning from the past historical data in a wide range of operational settings to determine the fluids properties in real-time operations. Our specific focus is on prediction of cuttings bed thickness along the wellbore in hole cleaning and prediction of high-pressure high-temperature (HPHT) rheological properties (in downhole conditions). In both applications, we present procedures to develop accurate digital twins for prediction of drilling fluid properties in real-time drilling operations. In the hole cleaning application, we develop accurate computational fluid dynamics (CFD) models to capture the effects of rotation, eccentricity, and bed height on local fluid velocities above cuttings bed. We then run 55,000 CFD simulations for a wide range of operational settings to generate training data for machine learning. For rheology monitoring, thousands of lab experiment records are collected as training data for machine learning. In this case, the HPHT rheological properties are determined based on rheological measurement in the American Petroleum Institute (API) condition (14.7 psi and 150 °F) together with the fluid type and composition data. We compare the results of the application of several machine learning algorithms to represent CFD simulations (for hole cleaning) and lab experiments (for monitoring HPHT rheological properties). Rotating cross-validation method is applied to ensure accurate and robust results. In both cases, models from the gradient boosting and the artificial neural network algorithms provided the highest accuracy (about 0.95 in terms of R2) for test datasets. With developments presented in this paper, the hole cleaning calculations can be performed in real time, and the HPHT rheological properties of drilling fluids can be estimated at the rig site avoiding the need to wait for the laboratory experimental results.

Machine Learning Model for Monitoring Rheological Properties of Synthetic Oil-Based Mud.

The drilling fluid rheology is a critical parameter during the oil and gas drilling operation to achieve optimum drilling performance without nonproductive time or extra remedial operation cost. The close monitoring for rheological properties will help the drilling fluid crew to take quick actions to maintain the designed profiles for the drilling fluid rheology, especially when it comes to the flat rheology drilling fluid system, which is a new generation for harsh and specific drilling conditions that require flat profiles for the mud rheology regarding the temperature condition changes. The current study introduces a machine learning application toward predicting the rheology of synthetic oil-based mud (flat rheology type) for the full automation system of monitoring the mud rheological properties. Four models are developed, for the first time, to determine the rheological characteristics of flat rheology synthetic oil-based system using artificial neural networks. The developed models are capable of predicting the plastic and apparent viscosities, yield point, and flow behavior index from only the mud density and Marsh funnel as model inputs. The proposed models were trained and optimized from a real field dataset (369 measurements) with further testing the models using an unseen dataset of 153 data points. The predicted rheological properties achieved a high degree of accuracy versus the actual measurements and showed a coefficient of correlation range from 0.91 to 0.97 with an average absolute percentage error of less than 9.66% during the training and testing phases. Besides, machine learning-based correlations are proposed for estimating the rheological properties on the rig site without running the machine learning system for easy field applications.

Novel Torque and Drag Model for Drilling Two-Dimensional High-Angle Wells.

Planning high-angle wells involves diverse areas; one of the most important of these areas is torque and drag (T&D) management. Not only could uncontrolled T&D cause various drilling problems like drill string (D/S) failures, casing wear, stuck pipes, and slow rates of penetration but it could also entirely stop the drilling progress, if torque and/or drag exceed rig or string capabilities. Modeling T&D in advance would alleviate these problems by prediction of friction forces to be encountered and urging the drilling team to take the required measures to mitigate these forces or upgrade the drilling hardware (rig equipment and/or D/S). Modeling T&D is still a complex and time-consuming job to be carried out at the rig site while drilling, so that an accurate and rig-friendly model would be very useful to industry. In this work, a novel and simple model had been developed to predict T&D values while drilling both curve and tangent sections of high-angle wells based on a soft-string concept, in which the D/S is assumed to be a chain lying on the lower side of the well that can transmit torsional forces. Despite the simplicity of the calculations, the model accounts for components of drilling torque that are overlooked in most complex packages. Friction within the top drive system had been considered to predict the torque acting on the D/S only. In addition, the torque applied on the D/S by the viscous drilling fluid was accounted for by reversing the concept of viscometers. The model proved to be practical and reliable for the two-dimensional wellbore and thus is superior in terms of quick field application. The developed model was tested using data from the Western Desert, Egypt. Statistical analysis had been used to assure the accuracy of the proposed model and to assess the effect of different drilling parameters and practices on both T&D. The reliability of the model had been proven with a negligible error for drag calculations and 10% error on average for torque calculations. Also, the effect of distance between successive survey stations on T&D modeling had been proven mathematically. This research narrows the gap between theory and practice by studying the dominant factors and determining the extent of the effect of each of them on wellbore friction forces. In addition, the work sheds light on the best practices concluded from the application of the developed model on field data.

Rate of penetration prediction while drilling vertical complex lithology using an ensemble learning model

The rate of penetration (ROP) accounts for a substantial portion of the overall drilling cost. The drilling optimization process, which mostly involves the adjustment of the mechanical drilling parameters, is therefore of prime importance in ensuring efficient drilling. However, drilling formations with assorted types of lithology necessitate the involvement of more parameters to reduce uncertainty and enhance confidence when predicting the ROP. The objective of this paper is to introduce an ensemble model based on random forest (RF), in which artificial neural network (ANN), and adaptive neuro-fuzzy inference system (ANFIS) are the base learner models, to predict the ROP across different lithological formations In this study, two types of actual field data of Well-1 were employed to build the model: (i) mechanical drilling parameters collected from real-time sensors allocated at the rig site, and (ii) petrophysical properties obtained from conventional well logs. Well-2 with more than 2300 unseen data points was used to compare the capability of the base learners (i.e., ANN and ANFIS), standalone RF, and RF-meta model in predicting the ROP with two of the earliest published ROP empirical models (Maurer's and Bingham's models). The results showed that the RF-meta model outperformed the base learners and Maurer's and Bingham's empirical models in predicting the ROP in Well-2 with a low absolute average percentage error (AAPE) of 7.8 % and a high coefficient of determination (R2) of 0.94.

Improved Tracking of the Rheological Properties of Max-Bridge Oil-Based Mud Using Artificial Neural Networks.

Lab measurements for the rheological properties of mud are critical for monitoring the drilling fluid functions during the drilling operations. However, these measurements take a long time and might need more than one person to be completed. The main objectives of this research are to implement artificial intelligence for predicting the mud rheology from only Marsh funnel (μf) and measuring mud density (ρm) easily and quickly on the rig site. For the first time, an artificial neural network (ANN) was used to build different models for predicting the rheological properties of Max-bridge oil-based mud. The properties included the plastic viscosity (μp), yield point (γ), flow behavior index (η), and apparent viscosity (μa). Field measurements of 383 samples were used to build and optimize the ANN models. The obtained results showed that 32 neurons in the hidden layer and tan sigmoid function transfer function were the best parameters for all ANN models. The training and testing processes of models showed a strong prediction performance with a correlation coefficient (R) greater than 0.91 and an average absolute percentage error (AAPE) less than 5.31%. New empirical correlations were developed based on the optimized weights and biases of the ANN models. The developed empirical correlations were compared with the published correlations, and the comparison results confirmed that the ANN-developed correlations outperformed all previous work.

Using Cameras To Understand What Is Happening While Drilling

Can a camera do a better job than humans at creating a minute-by-minute record of drilling activity? Or evaluate damaged drill bits better? Based on two papers at the SPE/IADC International Drilling Conference and Exhibition, the answer might soon be yes. Schlumberger researchers showed that video from a camera on the drill floor and on the drilling cuttings shaker kept an accurate record of what the rig was doing at the time, also known as the rig state (SPE 204086). A paper from The University of Texas-Austin (UT-Austin) showed a camera phone could create images for use in their bit-evaluation program to assess the damage and offer a reasonable explanation for what caused it (SPE 204124). A year ago Teradata announced its Bit-Box, which houses cameras and lights to create 3D bit images. It is now on the market; other companies are working on competing products. Cameras have gotten small and cheap at a time when innovations like self-driving cars have driven tech companies to speed development of computer-vision tools. Schlumberger’s goal is to convert video from rig cameras into a constant record of the rig state. It is being done with data gathered by sensors while drilling, or by people if the sensors stop working or generate bad data. The system leaves gaps when sensor issues are missed or workers are otherwise occupied, which is a maddening problem for those who need to know what is going on at any moment to interpret drilling data. “We need to understand what the rig was doing when we look at and try to solve problems” using digital analysis, said Crispin Chatar, a drilling subject matter expert for Schlumberger, who presented the paper at the virtual conference. The bit-evaluation program used phone camera images as a lower-cost substitute for 3D imaging, like the system sold by Teradata. Mobile phone images come with the risk of bad lighting and varying angles, which the authors said affected the analysis. But those devices are small, and there are plenty of backups available. “Everybody has a mobile phone at a rig site,” said Pradeep Ashok, a research scientist in the petroleum engineering department at UT-Austin. He believes cameras on mobile devices are the future because “if you could build something that requires no added equipment it will allow more rapid adoption.” Mobile phone owners also worry about breaking their phone. They may not be so concerned about rig equipment, which is a concern to those selling more-complex imaging devices. Both projects were early efforts to test what can be done with camera data, which is likely to expand over time. Schlumberger’s goal of tracking the rig state more reliably and cheaper than when using sensors may not be enough to convince users to change their ways at a time when sensors are proliferating to support more digitally controlled activities. The Schlumberger data were gathered at a test well for an automated rig.

Technology Focus: Extended-Reach and Complex Wells (May 2021)

In selecting papers for this feature, reviewer Stéphane Menand of Helmerich and Payne has identified a trio of papers that investigates new approaches toward familiar issues encountered when drilling complex well types. Whether considering the customization of drilling approaches in Middle Eastern carbonate reservoirs, implementing a collaborative work flow in tackling high-tortuosity wells offshore Western Australia, or researching the ability of a fibrous material to effect hole cleaning as opposed to polymeric sweeps, the authors of these papers understand that technical expertise may not be completely realized if it is not applied to problems in original ways. In carbonate reservoirs, the goal of drilling extended-reach wells is set against the geological makeup of such formations, the complexity of which adds significant uncertainty to geosteering and well placement. The authors of paper SPE 203335 develop a work flow that makes possible the customization of drilling scenarios through an emphasis on mechanical specific energy, as well as the use of an optimized borehole-assembly design. The work flow helped deliver what the authors write is the longest well in the Middle East offshore Abu Dhabi. In a similar vein, the authors of paper SPE 202251 describe a challenging scenario involving an ultraextended-reach well in a mature field offshore Western Australia. The project overcame shallow water depth and a high tortuosity requirement by implementing an integrated plan that used a reservoir-mapping-while-drilling service. The authors stress that this technology, coupled with active collaboration between specialists, town, and rig site, allowed the project to achieve the desired oil-column thickness with zero collision incidents. Highly deviated wells often face problems resulting from ineffective hole cleaning. Paper SPE 203147 studies the properties of a fibrous material when compared with the hole-cleaning performance of common polymeric pills. The authors write that the fibrous material proved effective, in part because of a unique characteristic in which a spiderweb-like network of fibers is created that does not allow cuttings to settle easily in complex wells. In addition, the material is environmentally friendly. All three papers approach well- established problems in the critical industry sector of extended-reach drilling with innovation and confidence. Enjoy the papers and be sure to search SPE’s OnePetro online library for more fresh approaches to the technical challenges posed by these well types. Recommended additional reading at OnePetro: www.onepetro.org. SPE 196410 - Analysis of Friction-Reduction System During Drilling Operation at a High-Inclination Well on Field X by Rizqiana Mudhoffar, Tanri Abeng University, et al. SPE 197257 - Successful Management of Collision Risk in an Extended-Reach Well by Manchukarn Naknaka, Mubadala Petroleum, et al. SPE 202730 - Challenges in Drilling and Completion of Extended-Reach-Drilling Wells With Landing Point Departure of More Than 10,000 ft in Light/Slim Casing Design by Nitheesh Kumar Unnikrishnan, Abu Dhabi National Oil Company, et al.

Collaboration and Optimization Processes Contribute to Ultra-ERD Offshore Well Success

This article, written by JPT Technology Editor Judy Feder, contains highlights of paper SPE 202251, “Transforming the Mindset To Drill Ultra-ERD Wells With High Tortuosity,” by Barry Goodin, SPE, Duane Selman, and Andy Wroth, Vermilion Oil and Gas, et al., prepared for the 2020 SPE Asia Pacific Oil and Gas Conference and Exhibition, originally scheduled to be held in Perth, Australia, 20–22 October. The paper has not been peer reviewed. The complete paper describes the extensive integrated engineering collaboration and optimization process that allowed an operator to push the drilling and completion envelope to drill a pair of complex, ultra-extended-reach-drilling (ERD) wells in the mature Wandoo field in the Carnarvon Basin offshore Western Australia. The shallow reservoir depth, extreme ERD profile, and high tortuosity requirement for the wells posed significant challenges. These were overcome with extensive planning; integrated engineering designs; application of new technology; good-quality, real-time data interpretation; and strong execution support from both rig site and town. Introduction The Wandoo field, in 56 m of water off-shore Western Australia, was discovered in 1991 and subsequently developed and placed on production in 1993. The shallow unconsolidated sandstone reservoir consists of a heavily biodegraded oil column overlain by a gas cap and supported by a strong aquifer drive. Field infrastructure consists of a 15-well-slot manned production facility, Wandoo B, and a five-slot monopod, Wandoo A, which is tied back to Wandoo B by subsea in-field pipelines. In late 2018, the operator planned and executed a two-well drilling campaign consisting of two complex, ultra-ERD wells, Wandoo B15 and B16. Both wells were planned to be batch drilled for the top hole and intermediate hole sections, with the production hole sections to be drilled and completed sequentially. The primary objective for the B15 well was to recover unswept oil along the western flank of the field and track the well along the main Wandoo fault to the north to assess the structure and reserves from the northern tip of the field. The B16 well objective was to access unswept reserves through the center and down to the south of the field, essentially twinning the B11ST1 well, another ERD well drilled on an earlier campaign, to its eastern flank. To maximize recovery, both wells needed to be placed approximately 1 m below the top of the reservoir, except where overlain by the gas cap, in which case the wells were to be placed approximately 2 m below the gas/oil contact to avoid gas coning. Drilling Challenges and Solutions The first half of the complete paper presents a detailed discussion of the drilling challenges and solutions, illustrated with schematics, maps, charts, and graphs. Both Wells B15 and B16 were classified as ultra-ERD wells because the shallow true vertical depth (TVD) of the reservoir resulted in extreme stepout ratios and required highly complex well paths to access the remaining reserves. The complete paper lists various specific drilling- and systems-related challenges.

Deep Learning and Time-Series Analysis for the Early Detection of Lost Circulation Incidents During Drilling Operations

Drilling operations consist of breaking the rock to deepen a wellbore for oil or gas extraction. A drilling fluid, circulating from the surface through the drill pipe and from the annulus to the surface, is used to remove rock cuttings and maintain hydrostatic pressure. Drilling fluid lost circulation incidents (LCIs) are major sources of non-productive time (NPT) in drilling operations. These incidents occur due to preexisting natural fractures (vugs, caverns, etc.) and/or drilling-induced hydraulic fractures. The initiation of an LCI could lead to other hazardous drilling phenomena, such as formation influx or kick/blowout, stuck pipe incidents, among others. LCIs are typically monitored at the rig site by observing drilling fluid levels in the fluid tanks. This manual process incurs missing the occurrence or late detection of LCIs. Machine learning (ML) and deep learning (DL) classification algorithms are powerful in processing time-series data and achieving early detection of such temporal phenomena. In this study, we performed a large-scale analysis of the surface drilling and rheology data obtained from historical wells with LCIs. This analysis includes primary and secondary preprocessing steps including, aggressive sampling, feature engineering, and window normalization to derive generalizable DL models for real-time operations. Focal loss was utilized to account for data class imbalance and train robust and generalizable models. The results obtained from different ML/DL algorithms showed that one-dimensional convolutional neural network models resulted in the best performance with state-of-the-art precision, recall, and F <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> scores of 87.34%, 73.40%, and 79.77%, respectively, on unseen test drilling data.

Transient response of near-wellbore supercharging during filter cake growth

Supercharging in the vicinity of a borehole is an important factor that affects formation damage and drilling safety, and the filter cake growth process has a significant impact on supercharging in the vicinity of the borehole. However, existing models that predict pore pressure distribution overlook dynamic filter cake growth. Thus, an analytical supercharging model was developed that considers time-dependent filter cake effects, and this model was verified using a two-dimensional numerical model. The influences of filter cake, formation, and filtrate properties on supercharging were investigated systematically. The results indicate that time-dependent filter cake effects have significant influence on supercharging. Supercharging increases in the early stage but decreases over time because of the dynamic growth of filter cake, and the supercharging magnitude decreases along the radial direction. Because of filter cake growth, the magnitude of supercharging falls quickly across the filter cake, and the decreased magnitude of pore pressure caused by the filter cake increases. Supercharging in low-permeability formations is more obvious and the faster rate of filter cake growth, a lower filtrate viscosity and faster reduction rate of filter cake permeability can help to weaken supercharging. The order of importance of influencing factors on supercharging is overbalance pressure &gt; formation permeability &gt; formation porosity ≈ filtrate viscosity &gt; filter cake permeability attenuation coefficient &gt; initial filter cake permeability control ratio &gt; filter cake growth coefficient &gt; filter cake porosity. To alleviate supercharging in the vicinity of the borehole, adopting drilling fluids that allow a filter cake to form quickly, optimizing drilling fluid with a lower filtrate viscosity, keeping a smaller overbalance pressure, and precise operation at the rig site are suggested for low-permeability formations during drilling.

Deep-Learning Techniques Classify Cuttings Volume of Shale Shakers

This article, written by JPT Technology Editor Chris Carpenter, contains highlights of paper SPE 194084, “Classifying Cutting Volume at Shale Shakers in Real Time by Video Streaming Using Deep-Learning Techniques,” by Xunsheng Du, Yuchen Jin, and Xuqing Wu, University of Houston, et al., prepared for the 2019 SPE/IADC International Drilling Conference and Exhibition, The Hague, 5–7 March. The paper has been peer approved and is scheduled for publication in SPE Drilling &amp; Completion. A real-time deep-learning model is proposed to classify the volume of cuttings from a shale shaker on an offshore drilling rig by analyzing the real-time monitoring video stream. As opposed to the traditional, time-consuming video-analytics method, the proposed model can implement a real-time classification and achieve remarkable accuracy. The approach is composed of three modules. Compared with results manually labeled by engineers, the model can achieve highly accurate results in real time without dropping frames. Introduction A complete work flow already exists to guide the maintenance and cleaning of the borehole for many oil and gas companies. A well-formulated work flow helps support well integrity and reduce drilling risks and costs. One traditional method needs human observation of cuttings at the shale shaker and a hydraulic and torque-and-drag model; the operation includes a number of cleanup cycles. This continuous manual monitoring of the cuttings volume at the shale shaker becomes the bottleneck of the traditional work flow and is unable to provide a consistent evaluation of the hole-cleaning condition because the human labor cannot be available consistently, and the torque-and-drag operation is discrete, containing a break between two cycles. Most of the previous work used image-analysis techniques to perform quantitative analyses on the cuttings volume. The traditional image-processing approach requires significant work on feature engineering. Because the raw data are usually noisy with missing components, pre- processing and augmenting the data play an important role in making the learning model more efficient and productive. The deep-learning framework, on the other hand, automatically discovers the representations needed for feature detection or classification from raw data. It can help overcome the difficulties in setting up and monitoring devices in a harsh environment, and the data-acquisition requirement for a cuttings-volume-monitoring system at the offshore rig might be relaxed. The objective of this study is to verify the feasibility of building a real-time, automatic cuttings-volume-monitoring sys-tem on a remote site with a limited data-transmission bandwidth. The minimum data-acquisition hardware requirement includes the following: Single uncalibrated charged-coupled-device camera Inconsistent lighting sources Low-bit-rate transmission Image-processing unit without graphics-processing-unit support (e.g., a laptop) A deep neural network (DNN) is adopted to perform the image processing and classification on cuttings volumes from a shale shaker at a remote rig site. Specifically, the convolutional neural networks are implemented as feature extractors and classifiers in the described model. The main contributions of this study can be summarized as follows: A deep-learning framework that can classify the volume of cuttings in real time A real-time video analysis system that requires minimum hardware setup efforts, capable of processing low-resolution images An object-detection work flow to detect automatically the region covered by cuttings A multithread video encoder/decoder implemented to improve real-time video-streaming processing

RADIOLOGICAL EVALUATION OF THE CONCENTRATION AND IMPACT OF OIL AND GAS ACTIVITIES IN ERUEMUKOHWARIEN AREA OF SOUTHERN NIGERIA

The study was carried out in-situ using a Radalert 100 nuclear radiation monitor and a geographical positioning system (GPS). Five facilities were investigated at the rig site which included the rig site host community as well as the camp site for the oil workers at Ekapkamreh town. Ten 10 sampling locations were evaluated at a total of 60 study points. The values obtained range between 0.115±0.018 (µSv/hr) and 0.299±0.040 (µSv/hr) for the rig site environment, 0.111±0.006 (µSv/hr) and 0.337±0.031 (µSv/hr) for field logistic base (offices and workshops), 0.114±0.011 (µSv/hr) and 0.312±0.021 (µSv/hr) for components of the mud circulation section. Also, the radiological concentration of the Chemical Store ranged between 0.126±0.019 (µSv/hr) and 1.181±0.104 (µSv/hr), while the radiological values obtained from other facilities within the rig site ranged from 0.155±0.026 (µSv/hr) and 0.249±0.026 (µSv/hr). Radiation readings obtained for soil ranged from 0.149±0.05 (µSv/hr) to 0.219±0.025 (µSv/hr) and 0.114±0.039 (µSv/hr) to 0.219±0.051 (µSv/hr) respectively at the host community and camp site. Most of the results obtained showed that the general environment of the rig site is slightly above the permissible absorbed dose rate threshold of 0.15(µSv/hr) recommended by the United Nation Scientific Committee on the Effects of Atomic Radiation (UNSCEAR) in 2009. However, the exposure rates exceed the standard background level of 13µR/hr (coequal to 0.13µSv/hr). There is high tendency for the industry workers to be exposed to radiation with time.

Artificial neural network models for real-time prediction of the rheological properties of NaCl mud

Drilling fluid’s rheology is a main parameter in optimization of drilling operations and reduction of the cost of drilling a well as it contributes to elimination of many drilling problems such as stuck pipe, hole cleaning, lost circulation, and other well control problems. Rheological properties of the drilling mud including plastic viscosity (PV), yield point (YP), flow behavior index (n), and apparent viscosity (AV) must be recorded in real time to calculate rig hydraulics. In rig sites, these values are recorded only twice a day because they require long time for measuring and cleaning the equipment. Artificial neural networks (ANN) can be used to get accurate models for estimation of the rheological properties of the mud in a real time based on the frequently measured parameters such as drilling mud density (MD), and Marsh funnel viscosity or time (FT). Application of ANN rewarded the objective of this paper to predict the rheological properties of the drilling mud by more frequently measured MD and FT. Using ANN has the advantage of retrieving the empirical correlations to calculate the rheological properties by whitening the black box which is another objective of this paper. Only field measurements of almost 814 datasets were divided into training and testing sets to validate the ANN empirical correlations. Levenberg-Marquardt backpropagation training algorithm (trainlm) and tangential sigmoidal (tansig) transferring function were used with all the empirical correlations in this paper. The optimized number of neurons for the ANN models was 38 for PV and 34 for n and YP, while it was only 24 for AV. The models were validated by almost 30% of the total datasets and resulted in very low average absolute percentage error (AAPE) which was 6.26%. The correlation coefficient (R) was more than 90% and comparing the AV model results with the previous AV models showed the superiority of the developed ANN-based empirical equation.

Real-time determination of rheological properties of high over-balanced drilling fluid used for drilling ultra-deep gas wells using artificial neural network

Drilling depleted and ultra-deep gas reservoirs required special drilling fluids which should be capable of bridging along the walls of the well and withstands a high differential pressure. High-overbalanced water-based drilling fluid (HOBWBDF) is one of the most common drilling fluid used to drill the ultra-deep gas wells. Drilling fluids properties such as yield point (YP), plastic viscosity (PV), apparent viscosity (AV), flow behavior index (n) and consistency index (k) are very vital inputs in managing rig hydraulics, margins of surge and swab pressure, equivalent circulation density (ECD) and hole cleaning. There is a need to develop a new technique to estimate the rheological properties in real-time using the frequent measurements of mud density and Marsh funnel viscosity, which are carried out more frequently (every 15–20 min).The main goal beyond this work is to build novel empirical models that are capable of predicting the above-mentioned rheological properties of high over-balanced water-based drilling fluid (HOBWBDF) in real-time for the first time. The models are built based on only two inputs which are the mud weight from the mud balance test and Marsh funnel viscosity measured by the Marsh funnel test. More than 1200 field measurements of rheological properties were used to feed an artificial neural network in order to develop new novel empirical models.The developed models using the ANN technique showed high accuracy for predicting the different drilling fluid rheological properties. The obtained results showed a maximum average absolute percentage error (AAPE) less than 8% with a correlation coefficient higher than 93%. The main advantages of these models are their inexpensiveness as there is no need for additional equipment to be added to the rig site. Moreover, these models would greatly help the drilling engineers to manage the ECD, surge and swab pressure and hole cleaning which in return will be reflected positively on the drilling performance.