Success Story of Utilizing Real Time Drilling Data to Remotely Support Drilling Operations and Identifying the Areas of Drilling Performance Improvement

2019 ◽  
Author(s):  
Abdul Salam Mohamad ◽  
Omar Al Dhanhani ◽  
Ashish Joshi ◽  
Ahmad Hussein ◽  
Khadija Alsawwafi ◽  
...  
Keyword(s):  
Real Time ◽  
Performance Improvement ◽  
Success Story ◽  
Drilling Performance ◽  
Drilling Data ◽  
Drilling Operations

Improving Real-Time Drilling Data Quality Using Artificial Intelligence and Machine Learning Techniques

2021 ◽  
Author(s):  
S. H. Al Gharbi ◽  
A. A. Al-Majed ◽  
A. Abdulraheem ◽  
S. Patil ◽  
S. M. Elkatatny
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Data Quality ◽  
Real Time ◽  
Input Data ◽  
Support Vector ◽  
The Real ◽  
Drilling Data ◽  
Drilling Operations

Abstract Due to high demand for energy, oil and gas companies started to drill wells in remote areas and unconventional environments. This raised the complexity of drilling operations, which were already challenging and complex. To adapt, drilling companies expanded their use of the real-time operation center (RTOC) concept, in which real-time drilling data are transmitted from remote sites to companies’ headquarters. In RTOC, groups of subject matter experts monitor the drilling live and provide real-time advice to improve operations. With the increase of drilling operations, processing the volume of generated data is beyond a human's capability, limiting the RTOC impact on certain components of drilling operations. To overcome this limitation, artificial intelligence and machine learning (AI/ML) technologies were introduced to monitor and analyze the real-time drilling data, discover hidden patterns, and provide fast decision-support responses. AI/ML technologies are data-driven technologies, and their quality relies on the quality of the input data: if the quality of the input data is good, the generated output will be good; if not, the generated output will be bad. Unfortunately, due to the harsh environments of drilling sites and the transmission setups, not all of the drilling data is good, which negatively affects the AI/ML results. The objective of this paper is to utilize AI/ML technologies to improve the quality of real-time drilling data. The paper fed a large real-time drilling dataset, consisting of over 150,000 raw data points, into Artificial Neural Network (ANN), Support Vector Machine (SVM) and Decision Tree (DT) models. The models were trained on the valid and not-valid datapoints. The confusion matrix was used to evaluate the different AI/ML models including different internal architectures. Despite the slowness of ANN, it achieved the best result with an accuracy of 78%, compared to 73% and 41% for DT and SVM, respectively. The paper concludes by presenting a process for using AI technology to improve real-time drilling data quality. To the author's knowledge based on literature in the public domain, this paper is one of the first to compare the use of multiple AI/ML techniques for quality improvement of real-time drilling data. The paper provides a guide for improving the quality of real-time drilling data.

Integrated Underreamer Technology with Real-Time Communication Helped Eliminate Rathole in Exploratory Operation Offshore Nigeria

2021 ◽  
Author(s):  
Raphael Chidiogo Ozioko ◽  
Humphrey Osita ◽  
Udochukwu Ohia
Keyword(s):  
Real Time ◽  
New Technology ◽  
Telemetry System ◽  
Operational Risks ◽  
Drilling Performance ◽  
Drilling Tools ◽  
Measurement While Drilling ◽  
Drilling Operations ◽  
Logging While Drilling ◽  
Fast Activation

Abstract This paper describes the successful deployment of integrated underreamer technology with real-time communication through mud-pulse telemetry system, to drill and eliminate rathole in 17 1/2-in × 20-in successfully in one run and helped set casing as close as possible to the depth of suspected pressure ramp on an exploratory well offshore Nigeria. This technology uses the same communication system (actuator bypass) as Measurement While Drilling tools (MWD), Logging While Drilling tools (LWD) and Rotary Steerable System (RSS). Integrated underreamers broadly used in the drilling operations support optimized casing and completion programs and helps reduce operational risks such as wellbore instability. The ball drop and hydraulically activated reamer technologies available today comes with limitations and HSE risks. The distinctive functionalities of the integrated underreamer technology described here, such as unlimited and fast activation and deactivation via downlinking and real time downhole feedback, reduce uncertainties and operational costs in the complex and challenging deep offshore drilling operations. The real-time communication through mud-pulse telemetry system enabled the placement of integrated underreamer 6 meters from the bit thereby reducing rathole length to approximately 9 meters compared to 80 meters for conventional underreamer application. The integrated underreamer is compatible with existing RSS and provide unlimited activation cycles. The integrated underreamer offers flexibility in placement in the bottom hole assembly (BHA) and it can be used as a near bit reamer, or as main reamer or as both. In this case, the integrated near bit underreamer eliminated the need for a dedicated rathole removal run. It also offered a feedback confirmation of the cutter blades activation status and provided hole opening log thereby reducing the operational uncertainties for the under reaming, saving rig time up to 16 hours for shoulder test. The underreamer was successfully deployed to drill and ream the challenging 14 ¾" × 17 ½" and ream 17 ½" × 20" section offshore Nigeria. Both sections were drilled and reamed to section Total Depth (TD) in one run with all directional reuirements and Measuring While Drilling (MWD)/Logging While Drilling (LWD) met saving client approximately 4 days of rig spread cost. The reamer appeared to provide an in-gauge borehole allowing for successful running and cementing of liners without any issues, demonstrating superior borehole quality. The new Technology proved to be a reliable and flexible hole enlargement while drilling solution that help to improve drilling performance, reduce operational risks and save cost.

Bi-Directional Long Short-Term Memory Variational Autoencoder for Real-Time Bit-Wear Estimation

2021 ◽  
Author(s):  
Trieu Phat Luu ◽  
John A.R. Bomidi ◽  
Arturo Magana-Mora ◽  
Alawi Alalsayednassir ◽  
Guodong David Zhan
Keyword(s):  
Real Time ◽  
Short Term Memory ◽  
Supervised Machine Learning ◽  
Short Term ◽  
Term Memory ◽  
Drilling Performance ◽  
Bit Wear ◽  
Variational Autoencoder ◽  
Drilling Data ◽  
Long Short Term Memory

Abstract Drilling operations rely on learned expertise in monitoring the drilling performance data and the rock data to assess the dull condition of the drill bit. While human learning can subjectively pick up the indicators based on rig surface data streams, this information is highly convoluted with changes in rock and drilling data. Recent approaches for bit wear estimation also include model-based and traditional supervised machine learning methods, which are usually costly and time-consuming. In this study, we developed a bi-directional long short-term memory-based variational autoencoder (biLSTM-VAE) to project raw drilling data into a latent space in which the real-time bit-wear can be estimated. The proposed deep neural network was trained in an unsupervised manner, and the bit-wear estimation is demonstrated as an end-to-end process.

Predicting Dysfunction Vibration Events while Drilling Using LSTM Recurrent Neural Networks

2021 ◽  
Author(s):  
Narendra Vishnumolakala ◽  
Dean Michael Murphy ◽  
Thu Nguyen ◽  
Enrique Zarate Losoya ◽  
Vivekvardhan Reddy Kesireddy ◽  
...  
Keyword(s):  
Real Time ◽  
Short Term Memory ◽  
Warning System ◽  
Complex Problem ◽  
Drill String ◽  
Sequential Data ◽  
Look Ahead ◽  
Drilling Data ◽  
The Future ◽  
Drilling Operations

Abstract The objective of the study is to build a robust Recurrent Neural Network system using Long-Short-Term-Memory (LSTM) to predict future vibrations during drilling operations. This provides a reliable solution to the complex problem of modeling several forms of vibrations encountered downhole. This accurate prediction system can be readily integrated into advisory/warning systems giving drillers the potential to save time, improve safety, and increase efficiency in drilling operations. High-frequency downhole drilling data onshore fields, obtained from a major O&G service provider, was used to train and validate the models. First, multiple classification algorithms such as Logistic Regression, KNN, Decision Trees, Random Forest were utilized to identify the presence and severity of Stickslip, Whirl, and other drill-string vibrations. LSTM-RNN was then used instead of traditional RNN intended for sequential data, to resolve the vanishing gradient problem. LSTM-RNN architecture was built to predict vibrations a)10 seconds and b) 30 seconds into the future. Results of the traditional classification models confirmed the hypothesis that dysfunctions can be successfully identified based on real-time downhole drilling data. 98% accuracy was obtained in successfully identifying torsional vibrations during drilling. A total of 101 parameters including measured and derived variables are available in the dataset. Modeling was performed with 14 features and vibrations were predicted. The RNN model was trained on data from multiple wells that encountered vibrations during drilling. The models were able to predict vibrations 10 seconds into the future with an MSE of 0.02 and 30 seconds into the future with reasonable accuracy and MSE of 0.10. Avoiding excessive vibrations will result in fewer trips by increasing longevity and reducing malfunctions of downhole electronics, the drill-string, and the BHA. Reduced NPT means drilling complex wells efficiently in less time which in turn directly translates to lower costs for the company. In addition to significant cost benefits, automated technology predicting anomalies and reacting in real-time translates to improved safety because it would now require fewer operators at risk on the rig floor. The work opens up avenues for a sophisticated advisory/warning system and effective ‘look-ahead’ drilling processes in the future.

Managing Drilling Real-Time Center Remotely Amid Covid-19 Pandemic in Compliance to 100% HSE

2021 ◽  
Author(s):  
Fernando Jose Landaeta Rivas ◽  
Michael Bradley Cotten ◽  
Paulinus Abhyudaya Bimastianto ◽  
Shreepad Purushottam Khambete ◽  
Suhail Mohammed Al Ameri ◽  
...  
Keyword(s):  
Real Time ◽  
Data Aggregation ◽  
Standard Procedure ◽  
Data Access ◽  
Productivity Level ◽  
Drilling Performance ◽  
Continuous Quality ◽  
Work From Home ◽  
Chain Of Command ◽  
Drilling Operations

Abstract COVID-19 pandemic shifted the conventional working paradigms, forcing an accelerated adaptability to remote working, ensuring the wellbeing of the employees without sacrificing the effectiveness, in compliance to 100% HSE. To overcome this challenge, Drilling Real Time Operations Center (RTOC) transformed the conventional Monitoring Onsite Hub into a full virtual collaborative remote center operated from each individual's place. This paper describes how RTOC successfully, continued to support drilling operations off-site through secure portal during work-from-home period. RTOC ensured to have the sufficient connectivity resources and security protocols to access the IT company environment and execute the tasks at the same productivity level, as operating from the hub. The platform design involved virtual machine remoting in an integrated communication environment, in synergy with the conventional ways of communication. Several data access points were developed to ensure an unstoppable link between operational teams and the data deliverables. To grantee productivity, KPIs were established and closely monitored, e.g. active rigs count, connectivity issues, software support, real-time drilling performance reporting, engineering computations, with continuous quality audits. Despite several challenges at start due to change in the nature of the work, RTOC successfully overcame the difficulties by having proper procedures and infrastructure in place. The virtual collaborative environment allowed the team to operate the center remotely and meet the targets for deliverables. Defining a clear communication protocol created efficiency when addressing data aggregation problems. As a result, RTOC was able to maintain the resolution time for data aggregation issues and continue to produce drilling performance reports within time. RTOC launched a mobile application for drilling real-time monitoring to support user mobility prior to the mandate of work-from-home policy. RTOC continued to support drilling operations during work-from-home period by providing real-time computations for drilling operations, doing real-time interactions for drilling events and introducing data analytics platform for users to analyze drilling performance. In summary, systematic implementation of the workflows and following clear chain of command have proven to be effective in ensuring business continuity of RTOC. Building trust and respect helped boost the morale and productivity of the team while ensuring their safety and wellbeing. The pandemic has been, indeed, a tough period for the world but the shift of working lifestyle was indeed a unique experience. It broadened the horizon for RTOC to develop advanced collaboration tools and upgrade the infrastructure to be future-ready for higher mobility. This novelty can also be adopted as standard procedure for Emergency Response Plan.

Real Time Automation of Cutting Carrying Capacity Index to Predict Hole Cleaning Efficiency and Thereby Improve Well Drilling Performance

2021 ◽  
Author(s):  
Mohammed M Al-Rubaii ◽  
Dhafer Al-Shehri ◽  
Mohamed N Mahmoud ◽  
Saleh M Al-Harbi ◽  
Khaled A Al-Qahtani
Keyword(s):  
Real Time ◽  
Carrying Capacity ◽  
Drilling Fluid ◽  
Model Development ◽  
Cleaning Efficiency ◽  
Time Model ◽  
Well Drilling ◽  
Hole Cleaning ◽  
Drilling Performance ◽  
Drilling Operations

Abstract Hole cleaning efficiency is one of the major factors that affects well drilling performance. Rate of penetration (ROP) is highly dependent on hole cleaning efficiency. Hole cleaning performance can be monitored in real-time in order to make sure drilled cuttings generated are efficiently transported to surface. The objective of this paper to present a real time automated model to obtain hole cleaning efficiency and thus effectively adjust parameters as required to improve drilling performance. The process adopts a modified real time carrying capacity indicator. There are many hole cleaning models, methodologies, chemicals and correlations, but majority of these models do not simulate drilling operations sequences and are not dependent on practicality of drilling operations. The developed real time hole cleaning indicator can ensure continuous monitoring and evaluation of hole cleaning performance during drilling operations. The methodology of real time model development is by selecting offset mechanical drilling parameters and drilling fluid parameters where collected, analyzed, tested and validated to model strong hole cleaning efficiency indicator that can extremely participate and facilitate a position in drilling automations and fourth industry revolution. The automated hole cleaning model is utilizing real time sensors of drilling and validate the strongest relationships among the variables. The study, analysis, test and validation of the relationships will reveal the significant parameters that will contribute massively for model development procedures. The model can be run as well by using the real time sensors readings and their inputs to be fed into the developed automated model. The developed model of real time carrying capacity indicator profile will be shown as function of depth, drilling fluid density, flow rate of mud pump or mud pump output, and other important factors will be illustrated by details. The model has been developed and validated in the field of drilling operations to empower the drilling teams for better and understandable monitoring and evaluation of hole cleaning efficiency while performing drilling operations. The real time model can provide a vision for better control of mud additives and that will contribute to mud cost effectiveness. The automated model of hole cleaning efficiency optimized the rate of penetration (ROP) by 50% in well drilling performance as a noticeable and valuable improvement. This optimum improvement saved cost and time of rig and drilling of wells and contributed to accelerate wells’ delivery. The innovative real time model was developed to optimize drilling and operations efficiency by using the surface rig sensors and interpret the downhole measurements and that can lead innovatively to other important hole cleaning indicators and other tactics for better development of downhole measurements models that can participate for optimized drilling efficiency.

A Real-Time Probabilistic Slide Drilling Dysfunction Advisory to Assist Remote Directional Drilling Operations

2021 ◽  
Author(s):  
Dawson Ramos ◽  
Pradeepkumar Ashok ◽  
Michael Yi ◽  
John D’ Angelo ◽  
Ian Rostagno ◽  
...  
Keyword(s):  
Bayesian Network ◽  
Real Time ◽  
Complex Analysis ◽  
Directional Drilling ◽  
Rotary Drilling ◽  
Stick Slip ◽  
Well Drilling ◽  
Drilling Data ◽  
Drilling Operations ◽  
Corrective Actions

Abstract Current slide drilling practices rely heavily on the intuition of the directional drillers to identify and correct drilling dysfunctions. Monitoring numerous dysfunctions simultaneously requires more complex analysis than can be done manually in real-time. There is also currently a big shift towards remote directional drilling. And as such, there is the need for a tool that can, in real-time, diagnose slide drilling dysfunctions accurately and provide advisory to both the remote directional drillers and rig crew. This paper proposes a method for a real-time slide drilling advisory system consisting of a probabilistic model which computes the likelihood that various slide drilling dysfunctions are occurring and an algorithm that determines what corrective action, if any, should be taken as a result. The dysfunction types monitored include buckling, high friction, poor toolface control, stick slip, and bit bounce. The model employs a Bayesian network which uses evidence derived from transient drilling data trends to infer the probability that any of the five considered dysfunctions are taking place. Data trends known to correlate with each dysfunction type are considered simultaneously to ensure that all dysfunction types are monitored continuously. As dysfunction probabilities are calculated, the algorithm cross references them with current drilling parameters and contextual data to determine necessary corrective actions. Corrective actions are output in the form of simple drilling parameter changes shown on a customizable graphical display. The dysfunction beliefs calculated were validated using historical data gathered from North America land drilling operations. For high friction and poor toolface control, known instances of dysfunction were identified using information in drilling logs and expert opinion and used for validation. The validation process resulted in a further refinement of the model. The proposed model along with graphical advisory displays were deployed on rigs in several North American land well drilling operations, as well as in the remote directional drilling center. While there is a lot of prior work that enables identification of rotary drilling dysfunctions in real-time, this is the first method that diagnoses slide drilling dysfunctions in real-time. The approach combines physics based models with a Bayesian network to improve accuracy and robustness in dysfunction detection. Additionally, it considers both real-time drilling data as well as drilling data from the past when diagnosing dysfunctions and facilitates remote directional drilling.

Sign in / Sign up

Export Citation Format

Share Document