From Science to Practice: Improving ROP by Utilizing a Cloud-Based Machine-Learning Solution in Real-Time Drilling Operations

2021 ◽  
Author(s):  
Kriti Singh ◽  
Sai Yalamarty ◽  
Curtis Cheatham ◽  
Khoa Tran ◽  
Greg McDonald
Keyword(s):  
Machine Learning ◽  
Real Time ◽  
Situational Awareness ◽  
Field Tests ◽  
Field Trials ◽  
Permian Basin ◽  
Lateral Vibrations ◽  
Drilling Parameters ◽  
Drilling Conditions ◽  
Performance Results

Abstract This paper is a follow up to the URTeC (2019-343) publication where the training of a Machine Learning (ML) model to predict rate of penetration (ROP) is described. The ML model gathers recent drilling parameters and approximates drilling conditions downhole to predict ROP. In real time, the model is run through an optimization sweep by adjusting parameters which can be controlled by the driller. The optimal drilling parameters and modeled ROP are then displayed for the driller to utilize. The ML model was successfully deployed and tested in real time in collaboration with leading shale operators in the Permian Basin. The testing phase was split in two parts, preliminary field tests and trials of the end-product. The key learnings from preliminary field tests were used to develop an integrated driller's dashboard with optimal drilling parameters recommendations and situational awareness tools for high dysfunction and procedural compliance which was used for designed trials. The results of field trials are discussed where subject well ROP was improved between 19-33% when comparing against observation/control footage. The overall ROP on subject wells was also compared against offset wells with similar target formations, BHAs, and wellbore trajectories. In those comparisons against qualified offsets, ROP was improved by as little as 5% and as much as 33%. In addition to comparing ROP performance, results from post-run data analysis are also presented. Detailed drilling data analytics were performed to check if using the recommendations during the trial caused any detrimental effects such as divergence in directional trends or high lateral or axial vibrations. The results from this analysis indicate that the measured downhole axial and lateral vibrations were in the safe zone. Also, no significant deviations in rotary trends were observed.

Application of Machine Learning for Lithology-on-Bit Prediction using Drilling Data in Real-Time

2021 ◽  
Author(s):  
Temirlan Zhekenov ◽  
Artem Nechaev ◽  
Kamilla Chettykbayeva ◽  
Alexey Zinovyev ◽  
German Sardarov ◽  
...  
Keyword(s):  
Machine Learning ◽  
Data Quality ◽  
Real Time ◽  
Hybrid Modeling ◽  
Data Set ◽  
Drilling Parameters ◽  
Drilling Data ◽  
Stable Solutions ◽  
Mud Logging

SUMMARY Researchers base their analysis on basic drilling parameters obtained during mud logging and demonstrate impressive results. However, due to limitations imposed by data quality often present during drilling, those solutions often tend to lose their stability and high levels of predictivity. In this work, the concept of hybrid modeling was introduced which allows to integrate the analytical correlations with algorithms of machine learning for obtaining stable solutions consistent from one data set to another.

Global Landslide Hazard Assessment for Situational Awareness (LHASA) Version 2: New Activities and Future Plans

2020 ◽  
Author(s):  
Dalia Kirschbaum ◽  
Thomas Stanley ◽  
Robert Emberson ◽  
Pukar Amatya ◽  
Sana Khan ◽  
...  
Keyword(s):  
Machine Learning ◽  
Real Time ◽  
Hazard Assessment ◽  
Situational Awareness ◽  
Landslide Hazard ◽  
Susceptibility Map ◽  
Landslide Hazard Assessment ◽  
Landslide Activity ◽  
Burned Areas ◽  
Version 2.0

<p>A remote sensing-based system has been developed to characterize the potential for rainfall-triggered landslides across the globe in near real-time. The Landslide Hazard Assessment for Situational Awareness (LHASA) model uses a decision tree framework to combine a static susceptibility map derived from information on slope, rock characteristics, forest loss, distance to fault zones and distance to road networks with satellite precipitation estimates from the Global Precipitation Measurement (GPM) mission. Since 2016, the LHASA model has been providing near real-time and retrospective estimates of potential landslide activity. Results of this work are available at https://landslides.nasa.gov.</p><p>In order to advance LHASA’s capabilities to characterize landslide hazards and impacts dynamically, we have implemented a new approach that leverages machine learning, new parameters, and new inventories. LHASA 2.0 uses the XGBoost machine learning model to bring in dynamic variables as well as additional static variables to better represent landslide hazard globally. Global rainfall forecasts are also being evaluated to provide a 1-3 day forecast of potential landslide activity. Additional factors such as recent seismicity and burned areas are also being considered to represent the preconditioning or changing interactions with subsequent rainfall over affected areas. A series of parameters are being tested within this structure using NASA’s Global Landslide Catalog as well as many other event-based and multi-temporal inventories mapped by the project team or provided by project partners.</p><p>In addition to estimates of landslide hazard, LHASA Version 2 will incorporate dynamic estimates of exposure including population, roads and infrastructure to highlight the potential impacts that rainfall-triggered landslides. The ultimate goal of LHASA Version 2.0 is to approximate the relative probabilities of landslide hazard and exposure across different space and time scales to inform hazard assessment retrospectively over the past 20 years, in near real-time, and in the future. In addition to the hazard. This presentation will outline the new activities for LHASA Version 2.0 and present some next steps for this system.</p>

Leveraging on Machine Learning Solution for Pioneering Wells Augmented Stuck Pipe Indicator in Real Time Centre

2021 ◽  
Author(s):  
Mohamad Hazwan Yusoff ◽  
Meor Muhammad Hakeem Meor Hashim ◽  
Muhammad Hadi Hamzah ◽  
Muhammad Faris Arriffin ◽  
Azlan Mohamad
Keyword(s):  
Machine Learning ◽  
Real Time ◽  
Detection System ◽  
Automation System ◽  
Learning Technology ◽  
Drilling Parameters ◽  
Bottom Hole Assembly ◽  
Signature Pattern ◽  
Monitoring Software ◽  
Productive Time

Abstract Stuck pipe incidents remain as one of the major problems in the drilling industry. The incidents will lead to expensive loss time in daily spread cost, bottom hole assembly cost, sidetracking cost as well as fishing cost. The Wells Augmented Stuck Pipe (WASP) Indicator, a state-of-the-art machine learning technology that seamlessly integrates with PETRONAS existing technologies, is introduced as the stuck pipe prevention detection system for the company. Historical real-time drilling data and stuck pipe incidents reports between 2007 and 2019 are used for the development of machine learning models. The models utilize key drilling parameters such as hookload and equivalent circulating density (ECD) to predict and analyze trends to detect any signature pattern anomalies for various stuck pipe events. The prediction and alarm are displayed in real-time monitoring software to trigger the operation team for prompt intervention. The WASP solution has demonstrated proven outcomes using historical and live well with high confidence in detecting stuck pipe incidents due to differential sticking, hole cleaning, and wellbore geometry. The WASP Indicator is envisaged to provide the company with cutting edge advantages in the industry. It is expected that the system will reduce the identification period and improve the reaction time of the monitoring specialists in recognizing the stuck pipe symptoms and highlighting potential incidents. The system is also bringing value to the company via non-productive time (NPT) cost avoidance and identification of early onset of various stuck pipe events based on distinct mechanisms. With the system, the existing portfolio value can be enhanced via setting dynamic trends and models into historical experiences context. The WASP Indicator is aspired to be the forefront innovation that will leap through the norm and lead the region in a greater plan of drilling automation system.

Valuable Cuttings-Based Petrophysic Analysis Successfully Reduces Drilling Risk in HPHT Formations

2021 ◽  
Author(s):  
Jianlin Chen ◽  
Yanhua Yao ◽  
Yingbiao Liu ◽  
Zhaofei Wang ◽  
Craig Collier ◽  
...  
Keyword(s):  
Real Time ◽  
Fluid Loss ◽  
Bottom Line ◽  
Rock Density ◽  
Drilling Parameters ◽  
Drilling Operations ◽  
Analysis Application ◽  
Time Basis ◽  
Compressional Strength ◽  
Drilling Conditions

Abstract Cuttings data has always been neglected or forgotten as a source of information by many operators. In some areas, it is even common practice to throw away cuttings in order to reduce cost. However, cuttings data can yield a great amout of information to provide great value and support to drilling operations, as well as reduce potential downhole risks. This was evident in wells drilled in remote Western regions of China, where wells typically have high temperature high pressure (HTHP) formations with a true vertical depth ranging between 4000-7000 meters and target formation temperature between 150-160 degrees Celcius. Due to severe drilling conditions, the measurement tools of Logging While Drilling (LWD) and Measured While Drilling (MWD) are at high risk of running into holes. Even due to the high formations’ temperatures is over the bottom line of LWD and MWD tools, the sensors of LWD and MWD cannot work efficiently in such circumstances, increasing the drilling risk and expense. Thus, "blind" drilling is the most reasonable economical choice for local operators. Without sufficient real-time formations’ information, the drilling uncertainties dramatically increase. The fluid loss, pipe stuck, as well as drilling bit damages frequently occur. Currently, there is no successful well that accesses to the target reservoir. The data from the wireline logs and cores cannot be available, as the well is the first exploration well in the block; however, during drilling, only drill cuttings are available for peoples. The creative cutting-based petrophysics models are built for the formation analysis that is able to provide rock density, cuttings gamma, Delta Time of Compressional Acoustic (DTC), Unconfined Compressional Strength (UCS) Index, Caliper Index, Brittleness Index, and Hydrocarbon Index from the cuttings samples at the wellsite on a near-real-time basis. This data can help people quantitatively and qualitatively evaluate the downhole formations on a near-real-time basis and can help people to make a more reasonable decision, and therefore, reduce the drilling risk within a controlled level. The authors provide the several cases to study the cutting models into drilling events, and proves the models are consistent with log and core data, and match the drilling parameters and like ROP, and pumping pressure, as well as torque, and bit performance. LWD and MWD are unable to run into the hole due to high formation pressure and extreme risky hole. The field portable XRF instrument is applied, and the mineralogy and elements input into the models. The cuttings petrophysics analysis application can provide the valuable information for drilling engineers to drill the wells to TD.

Application of Machine Learning Techniques for Real Time Rate of Penetration Optimization

2021 ◽  
Author(s):  
Asad Mustafa Elmgerbi ◽  
Clemens Peter Ettinger ◽  
Peter Mbah Tekum ◽  
Gerhard Thonhauser ◽  
Andreas Nascimento
Keyword(s):  
Machine Learning ◽  
Genetic Algorithm ◽  
Real Time ◽  
Predictive Models ◽  
Data Driven ◽  
Machine Learning Techniques ◽  
Time Rate ◽  
Rate Of Penetration ◽  
Drilling Parameters ◽  
Learning Techniques

Abstract Over the past decade, several models have been generated to predict Rate of Penetration (ROP) in real-time. In general, these models can be classified into two categories, model-driven (analytical models) and data-driven models (based on machine learning techniques), which is considered as cutting-edge technology in terms of predictive accuracy and minimal human interfering. Nevertheless, most existing machine learning models are mainly used for prediction, not optimization. The ROP ahead of the bit for a certain formation layer can be predicted with such methods, but the limitation of the applications of these techniques is to find an optimum set of operating parameters for the optimization of ROP. In this regard, two data-driven models for ROP prediction have been developed and thereafter have been merged into an optimizer model. The purpose of the optimization process is to seek the ideal combinations of drilling parameters that would lead to an improvement in the ROP in real-time for a given formation. This paper is mainly focused on describing the process of development to create smart data-driven models (built on MATLAB software environment) for real-time rate of penetration prediction and optimization within a sufficient time span and without disturbing the drilling process, as it is typically required by a drill-off test. The used models here can be classified into two groups: two predictive models, Artificial Neural Network (ANN) and Random Forest (RF), in addition to one optimizer, namely genetic algorithm. The process started by developing, optimizing, and validation of the predictive models, which subsequently were linked to the genetic algorithm (GA) for real-time optimization. Automated optimization algorithms were integrated into the process of developing the productive models to improve the model efficiency and to reduce the errors. In order to validate the functionalities of the developed ROP optimization model, two different cases were studied. For the first case, historical drilling data from different wells were used, and the results confirmed that for the three known controllable surface drilling parameters, weight on bit (WOB) has the highest impact on ROP, followed by flow rate (FR) and finally rotation per minute (RPM), which has the least impact. In the second case, a laboratory scaled drilling rig "CDC miniRig" was utilized to validate the developed model, during the validation only the previous named parameters were used. Several meters were drilled through sandstone cubes at different weights on bit, rotations per minute, and flow rates to develop the productive models; then the optimizer was activated to propose the optimal set of the used parameters, which likely maximize the ROP. The proposed parameters were implemented, and the results showed that ROP improved as expected.

Using satellite soil moisture and rainfall in the Landslide Hazard Assessment for Situational Awareness system

2021 ◽  
Author(s):  
Thomas Stanley ◽  
Dalia Kirschbaum ◽  
Robert Emberson
Keyword(s):  
Machine Learning ◽  
Soil Moisture ◽  
Real Time ◽  
Hazard Assessment ◽  
Situational Awareness ◽  
Landslide Hazard ◽  
Antecedent Soil Moisture ◽  
Landslide Hazard Assessment ◽  
Landslide Occurrence ◽  
Awareness System

<p>The Landslide Hazard Assessment for Situational Awareness system (LHASA) gives a global view of landslide hazard in nearly real time. Currently, it is being upgraded from version 1 to version 2, which entails improvements along several dimensions. These include the incorporation of new predictors, machine learning, and new event-based landslide inventories. As a result, LHASA version 2 substantially improves on the prior performance and introduces a probabilistic element to the global landslide nowcast.</p><p>Data from the soil moisture active-passive (SMAP) satellite has been assimilated into a globally consistent data product with a latency less than 3 days, known as SMAP Level 4. In LHASA, these data represent the antecedent conditions prior to landslide-triggering rainfall. In some cases, soil moisture may have accumulated over a period of many months. The model behind SMAP Level 4 also estimates the amount of snow on the ground, which is an important factor in some landslide events. LHASA also incorporates this information as an antecedent condition that modulates the response to rainfall. Slope, lithology, and active faults were also used as predictor variables. These factors can have a strong influence on where landslides initiate. LHASA relies on precipitation estimates from the Global Precipitation Measurement mission to identify the locations where landslides are most probable. The low latency and consistent global coverage of these data make them ideal for real-time applications at continental to global scales. LHASA relies primarily on rainfall from the last 24 hours to spot hazardous sites, which is rescaled by the local 99<sup>th</sup> percentile rainfall. However, the multi-day latency of SMAP requires the use of a 2-day antecedent rainfall variable to represent the accumulation of rain between the antecedent soil moisture and current rainfall.</p><p>LHASA merges these predictors with XGBoost, a commonly used machine-learning tool, relying on historical landslide inventories to develop the relationship between landslide occurrence and various risk factors. The resulting model relies heavily on current daily rainfall, but other factors also play an important role. LHASA outputs the probability of landslide occurrence on a grid of roughly one kilometer over all continents from 60 North to 60 South latitude. Evaluation over the period 2019-2020 shows that LHASA version 2 doubles the accuracy of the global landslide nowcast without increasing the global false alarm rate.</p><p>LHASA also identifies the areas where the human exposure to landslide hazard is most intense. Landslide hazard is divided into 4 levels: minimal, low, moderate, and high. Next, the number of persons and the length of major roads (primary and secondary roads) within each of these areas is calculated for every second-level administrative district (county). These results can be viewed through a web portal hosted at the Goddard Space Flight Center. In addition, users can download daily hazard and exposure data.</p><p>LHASA version 2 uses machine learning and satellite data to identify areas of probable landslide hazard within hours of heavy rainfall. Its global maps are significantly more accurate, and it now includes rapid estimates of exposed populations and infrastructure. In addition, a forecast mode will be implemented soon.</p>

scholarly journals Real-time prediction of Poisson’s ratio from drilling parameters using machine learning tools

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Osama Siddig ◽  
Hany Gamal ◽  
Salaheldin Elkatatny ◽  
Abdulazeez Abdulraheem
Keyword(s):  
Machine Learning ◽  
Real Time ◽  
Poisson’S Ratio ◽  
Wellbore Stability ◽  
Additional Cost ◽  
Poisson's Ratio ◽  
Inference System ◽  
Time Prediction ◽  
Drilling Parameters ◽  
Data Points

AbstractRock elastic properties such as Poisson’s ratio influence wellbore stability, in-situ stresses estimation, drilling performance, and hydraulic fracturing design. Conventionally, Poisson’s ratio estimation requires either laboratory experiments or derived from sonic logs, the main concerns of these methods are the data and samples availability, costs, and time-consumption. In this paper, an alternative real-time technique utilizing drilling parameters and machine learning was presented. The main added value of this approach is that the drilling parameters are more likely to be available and could be collected in real-time during drilling operation without additional cost. These parameters include weight on bit, penetration rate, pump rate, standpipe pressure, and torque. Two machine learning algorithms were used, artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS). To train and test the models, 2905 data points from one well were used, while 2912 data points from a different well were used for model validation. The lithology of both wells contains carbonate, sandstone, and shale. Optimization on different tuning parameters in the algorithm was conducted to ensure the best prediction was achieved. A good match between the actual and predicted Poisson’s ratio was achieved in both methods with correlation coefficients between 0.98 and 0.99 using ANN and between 0.97 and 0.98 using ANFIS. The average absolute percentage error values were between 1 and 2% in ANN predictions and around 2% when ANFIS was used. Based on these results, the employment of drilling data and machine learning is a strong tool for real-time prediction of geomechanical properties without additional cost.

Applying Different Artificial Intelligence Techniques in Dynamic Poisson's Ratio Prediction Using Drilling Parameters

2021 ◽  
pp. 1-15
Author(s):  
Osama Sidddig ◽  
Hany Gamal ◽  
Salaheldin Elkatatny ◽  
Abdulazeez Abdulraheem
Keyword(s):  
Machine Learning ◽  
Real Time ◽  
Poisson’S Ratio ◽  
Correlation Coefficients ◽  
Wellbore Stability ◽  
Performance Estimation ◽  
Poisson's Ratio ◽  
Support Vector ◽  
Drilling Parameters ◽  
Data Points

Abstract Rock geomechanical properties impact wellbore stability, drilling performance, estimation of in-situ stresses, and design of hydraulic fracturing. One of these properties is Poisson's ratio which is measured from lab testing or derived from well logs, the former is costly, time-consuming and doesn't provide continuous information, and the latter may not be always available. An alternative prediction technique from drilling parameters in real-time is proposed in this paper. The novel contribution of this approach is that the drilling data is always available and obtained from the first encounter with the well. These parameters are easily obtainable from drilling rig sensors such as rate of penetration, weight on bit and torque. Three machine-learning methods were utilized, support vector machine (SVM), functional network (FN) and random forest (RF). Dataset (2905 data points) from one well were used to build the models, while a dataset from another well with 2912 data points was used to validate the constructed models. Both wells have diverse lithology consists of carbonate, shale and sandstone. To ensure optimal accuracy, sensitivity and optimization tests on various parameters in each algorithm were performed.The three machine learning tools provided good estimations, however, SVM and RF yielded close results, with correlation coefficients of 0.99 and the average absolute percentage error (AAPE) values were mostly less than 1%. While in FN the outcomes were less efficient with correlation coefficients of 0.92 and AAPE around 3.8%. Accordingly, the presented approach provides an effective tool for Poisson's ratio prediction on a real-time basis at no additional expense. In addition, the same approach could be used in other rock mechanical properties.

Sign in / Sign up

Export Citation Format

Share Document