scholarly journals Prediction of the Least Principal Stresses Using Drilling Data: A Machine Learning Application

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Ahmed Gowida ◽  
Ahmed Farid Ibrahim ◽  
Salaheldin Elkatatny ◽  
Abdulwahab Ali
Keyword(s):  
Machine Learning ◽  
Middle Eastern ◽  
Field Tests ◽  
Horizontal Stress ◽  
Tectonic Stress ◽  
Average Error ◽  
Drilling Process ◽  
Principal Stresses ◽  
Drilling Data ◽  
R Value

The least principal stresses of downhole formations include minimum horizontal stress (σmin) and maximum horizontal stress (σmax). σmin and σmax are substantial parameters that significantly affect the design and optimization of the drilling process. These stresses can be estimated using theoretical equations in addition to some field tests, i.e., leak-off test to include the effect of tectonic stress. This approach is associated with many technical and financial issues. Therefore, the objective of this study is to provide a novel machine learning-based solution to estimate these stresses while drilling. First, new models were developed using artificial neural network (ANN) to directly predict σmin and σmax from the drilling data; which are injection rate (Q), standpipe pressure (SPP), weight on bit (WOB), torque (T), and rate of penetration (ROP). Such data are always available while drilling, and hence, no additional cost is required. Actual data from a Middle Eastern field were collected, statistically analyzed, and fed to the models. First, the models’ predictions showed a significant match with the actual stress values with a correlation coefficient (R-value) exceeding 0.90 and a mean absolute average error (MAPE) of 0.75% as a maximum. Second, new empirical equations were generated based on the developed ANN-based models. The new equations were then validated using another unseen dataset from the same field. The predictions had an R-value of 0.98 and 0.93 in addition to MAPE of 0.36% and 0.96% for σmin and σmax models, respectively. The results demonstrated the outperformance of the developed ANN-based equations to estimate the least principal stresses from the drilling data with high accuracy in a timely and economically effective way.

scholarly journals Seismic Anisotropy and  Stress of the Canterbury  Plains

2021 ◽  
Author(s):  
◽  
Rob Holt
Keyword(s):  
Seismic Anisotropy ◽  
Horizontal Stress ◽  
Tectonic Stress ◽  
Aftershock Sequence ◽  
S Wave ◽  
Principal Stresses ◽  
Seismic Properties ◽  
Average Value ◽  
North East ◽  
Slip Regime

<p>The Mѡ=7.1 Darfield (Canterbury) earthquake struck on 4 September 2010, approximately 45 km west of Christchurch, New Zealand. It revealed a previously unknown fault (the Greendale fault) and caused billions of dollars of damage due to high peak ground velocities and extensive liquefaction. It also triggered the Mw=6.3 Christchurch earthquake on 22 February 2011, which caused further damage and the loss of 185 lives. The objective of this research was to determine the relationship between stress and seismic properties in a seismically active region using manually-picked P and S wave arrival times from the aftershock sequence between 8 September 2010-13 January 2011 to estimate shear-wave splitting (SWS) parameters, VP =VS-ratios, anisotropy (delay-time tomography), focal mechanisms, and tectonic stress on the Canterbury plains. The maximum horizontal stress direction was highly consistent in the plains, with an average value of SHmax=116 18 . However, the estimates showed variation in SHmax near the fault, with one estimate rotating by as much as 30° counter-clockwise. This suggests heterogeneity of stress at the fault, though the cause remains unclear. Orientations of the principal stresses predominantly indicate a strike-slip regime, but there are possible thrust regimes to the west and north/east of the fault. The SWS fast directions (ø) on the plains show alignment with SHmax at the majority of stations, indicating stress controlled anisotropy. However, structural effects appear more dominant in the neighbouring regions of the Southern Alps and Banks Peninsula.</p>

scholarly journals Seismic Anisotropy and  Stress of the Canterbury  Plains

2021 ◽  
Author(s):  
◽  
Rob Holt
Keyword(s):  
Seismic Anisotropy ◽  
Horizontal Stress ◽  
Tectonic Stress ◽  
Aftershock Sequence ◽  
S Wave ◽  
Principal Stresses ◽  
Seismic Properties ◽  
Average Value ◽  
North East ◽  
Slip Regime

<p>The Mѡ=7.1 Darfield (Canterbury) earthquake struck on 4 September 2010, approximately 45 km west of Christchurch, New Zealand. It revealed a previously unknown fault (the Greendale fault) and caused billions of dollars of damage due to high peak ground velocities and extensive liquefaction. It also triggered the Mw=6.3 Christchurch earthquake on 22 February 2011, which caused further damage and the loss of 185 lives. The objective of this research was to determine the relationship between stress and seismic properties in a seismically active region using manually-picked P and S wave arrival times from the aftershock sequence between 8 September 2010-13 January 2011 to estimate shear-wave splitting (SWS) parameters, VP =VS-ratios, anisotropy (delay-time tomography), focal mechanisms, and tectonic stress on the Canterbury plains. The maximum horizontal stress direction was highly consistent in the plains, with an average value of SHmax=116 18 . However, the estimates showed variation in SHmax near the fault, with one estimate rotating by as much as 30° counter-clockwise. This suggests heterogeneity of stress at the fault, though the cause remains unclear. Orientations of the principal stresses predominantly indicate a strike-slip regime, but there are possible thrust regimes to the west and north/east of the fault. The SWS fast directions (ø) on the plains show alignment with SHmax at the majority of stations, indicating stress controlled anisotropy. However, structural effects appear more dominant in the neighbouring regions of the Southern Alps and Banks Peninsula.</p>

scholarly journals Modified Fracture Mechanics Approach for Hydraulic Fracturing Stress Measurements

Geofluids ◽  
2020 ◽  
Vol 2020 ◽  
pp. 1-11
Author(s):  
Guiyun Gao ◽  
Chenghu Wang ◽  
Hao Zhou ◽  
Pu Wang
Keyword(s):  
Fracture Mechanics ◽  
Hydraulic Fracturing ◽  
Field Tests ◽  
Horizontal Stress ◽  
In Situ Stress ◽  
Stress Determination ◽  
Confining Stress ◽  
Principal Stresses ◽  
True Triaxial ◽  
Stress Ratios

Hydraulic fracturing (HF) test has been widely used to determine in situ stress. The use of a conventional continuum method for this purpose has raised considerable controversies concerning field tests, particularly in the determination of the maximum horizontal principal stress under preexisting fractures. Fracture mechanics methods are very promising when considering preexisting cracks. However, most fracture mechanics methods do not include the effects of confinement on fracture parameters that depend on confining stress. In the present paper, we proposed a modified approach based on fracture mechanics for stress determination considering the relation between fracture toughness and confining stress based on the Rummel and Abou-Sayed methods. Then, we conducted true triaxial hydraulic fracturing tests under different stress ratios for granite and sandstone specimens to verify the proposed approach. The observed typical pressure-time curves indicate that in the conducted hydraulic fracturing tests, the steady fracture growth was attained. Moreover, we demonstrated that the stress ratios influence crack orientations. The horizontal maximum principal stresses determined using the modified Rummel method achieve the lowest relative error compared with other considered stress estimation approaches. This modified fracture mechanics method could be used as a potential alternative approach to obtain a considerably more precise estimation of the maximum horizontal stress in hydraulic fracturing stress determination.

scholarly journals Machine Learning-Based Models for the Estimation of the Energy Consumption in Metal Forming Processes

Metals ◽  
2021 ◽  
Vol 11 (5) ◽  
pp. 833
Author(s):  
Irene Mirandola ◽  
Guido A. Berti ◽  
Roberto Caracciolo ◽  
Seungro Lee ◽  
Naksoo Kim ◽  
...  
Keyword(s):  
Machine Learning ◽  
Finite Element ◽  
Energy Consumption ◽  
Metal Forming ◽  
Mutual Influence ◽  
Rolling Process ◽  
Ring Rolling ◽  
Gradient Boosting ◽  
Average Error ◽  
Ring Rolling Mill

This research provides an insight on the performances of machine learning (ML)-based algorithms for the estimation of the energy consumption in metal forming processes and is applied to the radial-axial ring rolling process. To define the mutual influence between ring geometry, process settings, and ring rolling mill geometries with the resulting energy consumption, measured in terms of the force integral over the processing time (FIOT), FEM simulations have been implemented in the commercial SW Simufact Forming 15. A total of 380 finite element simulations with rings ranging from 650 mm < DF < 2000 mm have been implemented and constitute the bulk of the training and validation datasets. Both finite element simulation settings (input), as well as the FI (output), have been utilized for the training of eight machine learning models, implemented with Python scripts. The results allow defining that the Gradient Boosting (GB) method is the most reliable for the FIOT prediction in forming processes, being its maximum and average errors equal to 9.03% and 3.18%, respectively. The trained ML models have been also applied to own and literature experimental cases, showing a maximum and average error equal to 8.00% and 5.70%, respectively, thus proving once again its reliability.

scholarly journals Unraveling city-specific signature and identifying sample origin locations for the data from CAMDA MetaSUB challenge

2021 ◽  
Vol 16 (1) ◽  
Author(s):  
Runzhi Zhang ◽  
Alejandro R. Walker ◽  
Susmita Datta
Keyword(s):  
Machine Learning ◽  
Error Rates ◽  
Average Error ◽  
Importance Score ◽  
Learning Methods ◽  
Principal Coordinates Analysis ◽  
Principal Coordinates ◽  
Total Variability ◽  
The Common ◽  
Feature Selecting

Abstract Background Composition of microbial communities can be location-specific, and the different abundance of taxon within location could help us to unravel city-specific signature and predict the sample origin locations accurately. In this study, the whole genome shotgun (WGS) metagenomics data from samples across 16 cities around the world and samples from another 8 cities were provided as the main and mystery datasets respectively as the part of the CAMDA 2019 MetaSUB “Forensic Challenge”. The feature selecting, normalization, three methods of machine learning, PCoA (Principal Coordinates Analysis) and ANCOM (Analysis of composition of microbiomes) were conducted for both the main and mystery datasets. Results Features selecting, combined with the machines learning methods, revealed that the combination of the common features was effective for predicting the origin of the samples. The average error rates of 11.93 and 30.37% of three machine learning methods were obtained for main and mystery datasets respectively. Using the samples from main dataset to predict the labels of samples from mystery dataset, nearly 89.98% of the test samples could be correctly labeled as “mystery” samples. PCoA showed that nearly 60% of the total variability of the data could be explained by the first two PCoA axes. Although many cities overlapped, the separation of some cities was found in PCoA. The results of ANCOM, combined with importance score from the Random Forest, indicated that the common “family”, “order” of the main-dataset and the common “order” of the mystery dataset provided the most efficient information for prediction respectively. Conclusions The results of the classification suggested that the composition of the microbiomes was distinctive across the cities, which could be used to identify the sample origins. This was also supported by the results from ANCOM and importance score from the RF. In addition, the accuracy of the prediction could be improved by more samples and better sequencing depth.

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.

The Use of a Sensor Modules System for Measuring Drilling Parameters in a Bit, Significantly Reduces the Construction Time of Wells in Eastern Siberia

2021 ◽  
Author(s):  
Andrey Alexandrovich Rebrikov ◽  
Anton Anatolyevich Koschenkov ◽  
Anastasiya Gennadievna Rakina ◽  
Igor Dmitrievich Kortunov ◽  
Nikita Vladimirovich Koshelev ◽  
...  
Keyword(s):  
Oil And Gas ◽  
New Technologies ◽  
Field Tests ◽  
Depth Of Cut ◽  
Drilling Process ◽  
Eastern Siberia ◽  
Construction Time ◽  
Stage Of Development ◽  
Drilling Parameters ◽  
Pdc Bit

Abstract Currently, production and exploration drilling has entered a stage of development where one of the highest priority goals is to reduce the time for well construction with new technologies and innovations. One of the key components in this aspect is the utilizing of the latest achievements in the design and manufacture of rock cutting tools – drill bits. This article presents some new ideas on methods for identifying different types of vibrations when drilling with PDC bits using a system of sensors installed directly into the bit itself. In the oil and gas fields of Eastern Siberia, one of the main reasons for ineffective drilling with PDC bits are vibrations, which lead to premature wear of the cutting structure of the bit and the achievement of low ROPs in the dolomite and dolerite intervals. For efficient drilling of wells of various trajectories with a bottom hole assembly (BHA), including a downhole motor (PDM) and a PDC bit, special attention is paid to control of the bit by limiting the depth of cut, as well as the level of vibrations that occur during drilling process. Often, the existing complex of surface and BHA equipment fails to identify vibrations that occur directly on the bit, as well as to establish the true cause of their occurrence. Therefore, as an innovative solution to this problem, a system of sensors installed directly into the bit itself is proposed. The use of such a system makes it possible to determine the drilling parameters, differentiated depending on the lithological properties of rocks, leading to an increase in vibration impact. Together with the Operators, tests have been successfully carried out, which have proven the effectiveness of the application of this technology. The data obtained during the field tests made it possible to determine the type and source of vibration very accurately during drilling. In turn, this made it possible to precisely adjust the drilling parameters according to the drilled rocks, to draw up a detailed road map of effective drilling in a specific interval. Correction of drilling parameters based on the analysis of data obtained from sensors installed in the bit made it possible to reduce the resulting wear of the PDC bit cutting structure and, if necessary, make changes to the bit design to improve the technical and economic indicators. Thus, the use of a system of sensors for measuring the drilling parameters in a bit ensured the dynamic stability of the entire BHA at the bottomhole when drilling in rocks of different hardness, significantly reduced the wear of the drilling tools and qualitatively improved the drilling performance.

Utilizing Data-Driven Models to Predict Brittleness in Tuscaloosa Marine Shale: A Machine Learning Approach

2021 ◽  
Author(s):  
Jamal Ahmadov
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Brittleness Index ◽  
Estimation Methods ◽  
Gradient Boosting ◽  
Average Error ◽  
Support Vector ◽  
Marine Shale ◽  
Effective Manner ◽  
Selection Of

Abstract The Tuscaloosa Marine Shale (TMS) formation is a clay- and liquid-rich emerging shale play across central Louisiana and southwest Mississippi with recoverable resources of 1.5 billion barrels of oil and 4.6 trillion cubic feet of gas. The formation poses numerous challenges due to its high average clay content (50 wt%) and rapidly changing mineralogy, making the selection of fracturing candidates a difficult task. While brittleness plays an important role in screening potential intervals for hydraulic fracturing, typical brittleness estimation methods require the use of geomechanical and mineralogical properties from costly laboratory tests. Machine Learning (ML) can be employed to generate synthetic brittleness logs and therefore, may serve as an inexpensive and fast alternative to the current techniques. In this paper, we propose the use of machine learning to predict the brittleness index of Tuscaloosa Marine Shale from conventional well logs. We trained ML models on a dataset containing conventional and brittleness index logs from 8 wells. The latter were estimated either from geomechanical logs or log-derived mineralogy. Moreover, to ensure mechanical data reliability, dynamic-to-static conversion ratios were applied to Young's modulus and Poisson's ratio. The predictor features included neutron porosity, density and compressional slowness logs to account for the petrophysical and mineralogical character of TMS. The brittleness index was predicted using algorithms such as Linear, Ridge and Lasso Regression, K-Nearest Neighbors, Support Vector Machine (SVM), Decision Tree, Random Forest, AdaBoost and Gradient Boosting. Models were shortlisted based on the Root Mean Square Error (RMSE) value and fine-tuned using the Grid Search method with a specific set of hyperparameters for each model. Overall, Gradient Boosting and Random Forest outperformed other algorithms and showed an average error reduction of 5 %, a normalized RMSE of 0.06 and a R-squared value of 0.89. The Gradient Boosting was chosen to evaluate the test set and successfully predicted the brittleness index with a normalized RMSE of 0.07 and R-squared value of 0.83. This paper presents the practical use of machine learning to evaluate brittleness in a cost and time effective manner and can further provide valuable insights into the optimization of completion in TMS. The proposed ML model can be used as a tool for initial screening of fracturing candidates and selection of fracturing intervals in other clay-rich and heterogeneous shale formations.

scholarly journals Application of Various Machine Learning Techniques in Predicting Total Organic Carbon from Well Logs

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Osama Siddig ◽  
Ahmed Farid Ibrahim ◽  
Salaheldin Elkatatny
Keyword(s):  
Machine Learning ◽  
Organic Carbon ◽  
Total Organic Carbon ◽  
The Other ◽  
Well Logs ◽  
Machine Learning Techniques ◽  
Percentage Error ◽  
Average Error ◽  
Support Vector ◽  
Empirical Correlations

Unconventional resources have recently gained a lot of attention, and as a consequence, there has been an increase in research interest in predicting total organic carbon (TOC) as a crucial quality indicator. TOC is commonly measured experimentally; however, due to sampling restrictions, obtaining continuous data on TOC is difficult. Therefore, different empirical correlations for TOC have been presented. However, there are concerns about the generalization and accuracy of these correlations. In this paper, different machine learning (ML) techniques were utilized to develop models that predict TOC from well logs, including formation resistivity (FR), spontaneous potential (SP), sonic transit time (Δt), bulk density (RHOB), neutron porosity (CNP), gamma ray (GR), and spectrum logs of thorium (Th), uranium (Ur), and potassium (K). Over 1250 data points from the Devonian Duvernay shale were utilized to create and validate the model. These datasets were obtained from three wells; the first was used to train the models, while the data sets from the other two wells were utilized to test and validate them. Support vector machine (SVM), random forest (RF), and decision tree (DT) were the ML approaches tested, and their predictions were contrasted with three empirical correlations. Various AI methods’ parameters were tested to assure the best possible accuracy in terms of correlation coefficient (R) and average absolute percentage error (AAPE) between the actual and predicted TOC. The three ML methods yielded good matches; however, the RF-based model has the best performance. The RF model was able to predict the TOC for the different datasets with R values range between 0.93 and 0.99 and AAPE values less than 14%. In terms of average error, the ML-based models outperformed the other three empirical correlations. This study shows the capability and robustness of ML models to predict the total organic carbon from readily available logging data without the need for core analysis or additional well interventions.

Sign in / Sign up

Export Citation Format

Share Document