scholarly journals Intelligent Prediction for Rock Porosity While Drilling Complex Lithology in Real Time

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Hany Gamal ◽  
Salaheldin Elkatatny ◽  
Ahmed Alsaihati ◽  
Abdulazeez Abdulraheem
Keyword(s):  
Real Time ◽  
Drill String ◽  
Coefficient Of Determination ◽  
Reservoir Modeling ◽  
Percentage Error ◽  
Reserve Estimation ◽  
Well Drilling ◽  
Rock Porosity ◽  
Weight On Bit ◽  
Data Points

Rock porosity is an important parameter for the formation evaluation, reservoir modeling, and petroleum reserve estimation. The conventional methods for determining the rock porosity are considered costly and time-consuming operations during the well drilling. This paper aims to predict the rock porosity in real time while drilling complex lithology using machine learning. In this paper, two intelligent models were developed utilizing the random forest (RF) and decision tree (DT) techniques. The drilling parameters include weight on bit, torque, standpipe pressure, drill string rotation speed, rate of penetration, and pump rate. Two datasets were employed for building the models (3767 data points) and for validating the developed models (1676 data points). Both collected datasets have complex lithology of carbonate, sandstone, and shale. Sensitivity and optimization on different parameters for each technique were conducted to ensure optimum prediction. The models’ performance was checked by four performance indices which are coefficient of determination (R2), average absolute percentage error (AAPE), variance account for (VAF), and a20 index. The results indicated the strong porosity prediction capability for the two models. DT model showed R2 of 0.94 and 0.87 between the predicted and actual porosity values with AAPE of 6.07 and 9% for training and testing, respectively. Generally, RF provided a higher level of strong prediction than DT as RF achieved R2 of 0.99 and 0.90 with AAPE of 1.5 and 7% for training and testing, respectively. The models’ validation proved a high prediction performance as DT achieved R2 of 0.88 and AAPE of 8.58%, while RF has R2 of 0.92 and AAPE of 6.5%.

Generation of a Complete Profile for Porosity Log While Drilling Complex Lithology by Employing the Artificial Intelligence

2021 ◽  
Author(s):  
Ahmed Al-Sabaa ◽  
Hany Gamal ◽  
Salaheldin Elkatatny
Keyword(s):  
Artificial Intelligence ◽  
Prediction Model ◽  
Real Time ◽  
Storage Capacity ◽  
Data Set ◽  
Drilling Parameters ◽  
Unseen Data ◽  
Rock Porosity ◽  
Data Points ◽  
Logging Tool

Abstract The formation porosity of drilled rock is an important parameter that determines the formation storage capacity. The common industrial technique for rock porosity acquisition is through the downhole logging tool. Usually logging while drilling, or wireline porosity logging provides a complete porosity log for the section of interest, however, the operational constraints for the logging tool might preclude the logging job, in addition to the job cost. The objective of this study is to provide an intelligent prediction model to predict the porosity from the drilling parameters. Artificial neural network (ANN) is a tool of artificial intelligence (AI) and it was employed in this study to build the porosity prediction model based on the drilling parameters as the weight on bit (WOB), drill string rotating-speed (RS), drilling torque (T), stand-pipe pressure (SPP), mud pumping rate (Q). The novel contribution of this study is to provide a rock porosity model for complex lithology formations using drilling parameters in real-time. The model was built using 2,700 data points from well (A) with 74:26 training to testing ratio. Many sensitivity analyses were performed to optimize the ANN model. The model was validated using unseen data set (1,000 data points) of Well (B), which is located in the same field and drilled across the same complex lithology. The results showed the high performance for the model either for training and testing or validation processes. The overall accuracy for the model was determined in terms of correlation coefficient (R) and average absolute percentage error (AAPE). Overall, R was higher than 0.91 and AAPE was less than 6.1 % for the model building and validation. Predicting the rock porosity while drilling in real-time will save the logging cost, and besides, will provide a guide for the formation storage capacity and interpretation analysis.

Rock Strength Prediction in Real-Time while Drilling Employing Random Forest and Functional Network Techniques

2021 ◽  
pp. 1-21
Author(s):  
Hany Gamal ◽  
Ahmed Alsaihati ◽  
Salaheldin Elkatatny ◽  
Saleh Haidary ◽  
Abdulazeez Abdulraheem
Keyword(s):  
Random Forest ◽  
Real Time ◽  
Rock Strength ◽  
Prediction Models ◽  
Functional Network ◽  
Percentage Error ◽  
Data Set ◽  
Unseen Data ◽  
Drilling Data ◽  
Data Points

Abstract The rock unconfined compressive strength (UCS) is one of the key parameters for geomechanical and reservoir modeling in the petroleum industry. Obtaining the UCS by conventional methods such as experimental work or empirical correlation from logging data are time consuming and highly cost. To overcome these drawbacks, this paper utilized the help of artificial intelligence (AI) to predict (in a real-time) the rock strength from the drilling parameters using two AI tools. Random forest (RF) based on principal component analysis (PCA), and functional network (FN) techniques were employed to build two UCS prediction models based on the drilling data such as weight on bit (WOB), drill string rotating-speed (RS), drilling torque (T), stand-pipe pressure (SPP), mud pumping rate (Q), and the rate of penetration (ROP). The models were built using 2,333 data points from well (A) with 70:30 training to testing ratio. The models were validated using unseen data set (1,300 data points) of Well (B) which is located in the same field and drilled across the same complex lithology. The results of the PCA-based RF model outperformed the FN in terms of correlation coefficient (R) and average absolute percentage error (AAPE). The overall accuracy for PCA-based RF was R of 0.99 and AAPE of 4.3 %, and for FN yielded R of 0.97 and AAPE of 8.5%. The validation results showed that R was 0.99 for RF and 0.96 for FN, while the AAPE was 4 and 7.9 % for RF and FN models, respectively. The developed PCA-based RF and FN models provide an accurate UCS estimation in real-time from the drilling data, saving time and cost and enhancing the well stability by generating UCS log from the rig drilling data.

Real-Time Software to Estimate Friction Coefficient and Downhole Weight on Bit During Drilling of Horizontal Wells

2014 ◽  
Author(s):  
Mazeda Tahmeen ◽  
Geir Hareland ◽  
Bernt S. Aadnoy
Keyword(s):  
Friction Coefficient ◽  
Real Time ◽  
Information Transfer ◽  
Horizontal Wells ◽  
Drill String ◽  
Surface Measurement ◽  
Drilling Process ◽  
Drilling Data ◽  
Weight On Bit ◽  
Drag Analysis

The increasing complexity and higher drilling cost of horizontal wells demand extensive research on software development for the analysis of drilling data in real-time. In extended reach drilling, the downhole weight on bit (WOB) differs from the surface seen WOB (obtained from on an off bottom hookload difference reading) due to the friction caused by drill string movement and rotation in the wellbore. The torque and drag analysis module of a user-friendly real-time software, Intelligent Drilling Advisory system (IDAs) can estimate friction coefficient and the effective downhole WOB while drilling. IDAs uses a 3-dimensional wellbore friction model for the analysis. Based on this model the forces applied on a drill string element are buoyed weight, axial tension, friction force and normal force perpendicular to the contact surface of the wellbore. The industry standard protocol, WITSML (Wellsite Information Transfer Standard Markup Language) is used to conduct transfer of drilling data between IDAs and the onsite or remote WITSML drilling data server. IDAs retrieves real-time drilling data such as surface hookload, pump pressure, rotary RPM and surface WOB from the data servers. The survey data measurement for azimuth and inclination versus depth along with the retrieved drilling data, are used to do the analysis in different drilling modes, such as lowering or tripping in and drilling. For extensive analysis the software can investigate the sensitivity of friction coefficient and downhole WOB on user-defined drill string element lengths. The torque and drag analysis module, as well as the real-time software, IDAs has been successfully tested and verified with field data from horizontal wells drilled in Western Canada. In the lowering mode of drilling process, the software estimates the overall friction coefficient when the drill bit is off bottom. The downhole WOB estimated by the software is less than the surface measurement that the drillers used during drilling. The study revealed verification of the software by comparing the estimated downhole WOB with the downhole WOB recorded using a downhole measuring tool.

Generation of Synthetic Photoelectric Log using Machine Learning Approach

2021 ◽  
Author(s):  
Mohammad Rasheed Khan ◽  
Zeeshan Tariq ◽  
Mohamed Mahmoud
Keyword(s):  
Machine Learning ◽  
Mean Squared Error ◽  
Coefficient Of Determination ◽  
Percentage Error ◽  
Well Log ◽  
Log Data ◽  
Hydrocarbon Reservoir ◽  
Analysis Scheme ◽  
Data Points ◽  
Error Metric

Abstract Photoelectric factor (PEF) is one of functional parameters of a hydrocarbon reservoir that could provide invaluable data for reservoir characterization. Well logs are critical to formation evaluation processes; however, they are not always readily available due to unfeasible logging conditions. In addition, with call for efficiency in hydrocarbon E&P business, it has become imperative to optimize logging programs to acquire maximum data with minimal cost impact. As a result, the present study proposes an improved strategy for generating synthetic log by making a quantitative formulation between conventional well log data, rock mineralogical content and PEF. 230 data points were utilized to implement the machine learning (ML) methodology which is initiated by implementing a statistical analysis scheme. The input logs that are used for architecture establishment include the density and sonic logs. Moreover, rock mineralogical content (carbonate, quartz, clay) has been incorporated for model development which is strongly correlated to the PEF. At the next stage of this study, architecture of artificial neural networks (ANN) was developed and optimized to predict the PEF from conventional well log data. A sub-set of data points was used for ML model construction and another unseen set was employed to assess the model performance. Furthermore, a comprehensive error metrics analysis is used to evaluate performance of the proposed model. The synthetic PEF log generated using the developed ANN correlation is compared with the actual well log data available and demonstrate an average absolute percentage error less than 0.38. In addition, a comprehensive error metric analysis is presented which depicts coefficient of determination more than 0.99 and root mean squared error of only 0.003. The numerical analysis of the error metric point towards the robustness of the ANN model and capability to link mineralogical content with the PEF.

Fracture Pressure Prediction Using Surface Drilling Parameters by Artificial Intelligence Techniques

2020 ◽  
Vol 143 (3) ◽  
Author(s):  
Abdulmalek Ahmed ◽  
Salaheldin Elkatatny ◽  
Abdulwahab Ali
Keyword(s):  
Artificial Intelligence ◽  
Real Time ◽  
Coefficient Of Determination ◽  
Percentage Error ◽  
Support Vector ◽  
Optimal Model ◽  
Time Data ◽  
Fracture Pressure ◽  
Drilling Parameters ◽  
Drilling Operations

Abstract Several correlations are available to determine the fracture pressure, a vital property of a well, which is essential in the design of the drilling operations and preventing problems. Some of these correlations are based on the rock and formation characteristics, and others are based on log data. In this study, five artificial intelligence (AI) techniques predicting fracture pressure were developed and compared with the existing empirical correlations to select the optimal model. Real-time data of surface drilling parameters from one well were obtained using real-time drilling sensors. The five employed methods of AI are functional networks (FN), artificial neural networks (ANN), support vector machine (SVM), radial basis function (RBF), and fuzzy logic (FL). More than 3990 datasets were used to build the five AI models by dividing the data into training and testing sets. A comparison between the results of the five AI techniques and the empirical fracture correlations, such as the Eaton model, Matthews and Kelly model, and Pennebaker model, was also performed. The results reveal that AI techniques outperform the three fracture pressure correlations based on their high accuracy, represented by the low average absolute percentage error (AAPE) and a high coefficient of determination (R2). Compared with empirical models, the AI techniques have the advantage of requiring less data, only surface drilling parameters, which can be conveniently obtained from any well. Additionally, a new fracture pressure correlation was developed based on ANN, which predicts the fracture pressure with high precision (R2 = 0.99 and AAPE = 0.094%).

Real-Time Downhole Weight on Bit (DWOB) Automation in Directional Drilling

2015 ◽  
Author(s):  
Andrew Wu ◽  
Geir Hareland
Keyword(s):  
Real Time ◽  
Field Tests ◽  
Directional Drilling ◽  
Well Drilling ◽  
Loop Control ◽  
Closed Loop Control System ◽  
Loop Control System ◽  
Weight On Bit ◽  
The Difference ◽  
Predicted Values

This paper introduces the functionality of a new type of Autodriller software system, which can acquire downhole weight on bit (DWOB) based on surface rig measurement. Field tests are performed, including DWOB measured by downhole measuring tools and the hookload below the top drive using a TTS (Torque and Tension Sub). Three sets of drilling data from three horizontal wells in Western Canada were utilized to verify the models of this new Autodriller system. DWOB comparisons between the model and the measuring tools were carried out. The comparisons indicate a good agreement between the downhole measured DWOB and the new Autodriller predicted values. The difference between the new Autodriller prediction and downhole measured DWOB can be quantified using rooted mean square error (RMSE) or relative error (RE). This paper also analyzes the differences in some sections, and some measures are suggested to potentially reduce these differences. The new Autodriller is a closed loop control system which can automatically in real-time adjust surface weight on bit (SWOB) so that the DWOB is accurate, which will directly improve the performance of drill bits, and decrease the cost of drilling, especially in directional well drilling applications.

A Real-Time Friction Prediction Model for in Service Drill String Based on Machine Learning Methods Coupling with Mechanical Mechanism Analysis

2021 ◽  
Author(s):  
Huijuan Guo ◽  
Huaidong Luo ◽  
Guodong Zhan ◽  
Baodong Wang ◽  
Shuo Zhu
Keyword(s):  
Neural Network ◽  
Real Time ◽  
Horizontal Wells ◽  
Drill String ◽  
Mechanism Analysis ◽  
Analysis Model ◽  
Machine Learning Methods ◽  
Weight On Bit ◽  
Friction Prediction ◽  
Independent Parameters

Abstract With highly deviated wells and horizontal wells are widely used in the oil industry. The large slope well sections and long horizontal well sections will lead to a sharp increase of the drill string torque and friction, which may reduce the drilling efficiency, and even lead to accidents. Therefore, real-time and accurate analysis of drill string’s torque and friction is an urgent problem facing by the modern drilling technology. The paper established a real-time friction prediction model that combines machine learning methods with drill string mechanical mechanism analysis model. Based on 84000 sets of field monitoring data obtained on-site, a regular data training set for weight on bit (WOB) and torque prediction was constructed with 23 types of time-series related parameters and 10 types of timing independent parameters. Relationships between time-series related parameters and timing independent parameters with the weight on bit and torque were trained to utilize long and short-term memory (LSTM) neural network and muti-layer back propagation (BP) network respectively. The new developed LSTM-BP neural network achieves high-precision prediction results of WOB and torque with a relative error of less than 14%. Based on derived WOB and torque prediction results, a theoretical mechanical analysis model of the entire drill string was adopted in this paper to develop the quantitative relation between WOB and torque with the friction coefficient of the drill string and oil casing. Suitable friction coefficients along the drill string can be finally obtained by solving the equilibrium function between predicted WOB, torque and measured hook load, rotary-table torque via an iteration algorithm. A case study was performed finally using the proposed intelligent analysis method to calculate the friction coefficients. This proposed methodology can be referenced to decrease the sticking risks and improve the drilling efficiency, which can finally increase the extension limit of horizontal wells in complex strata.

scholarly journals Application of artificial neural network (ANN-MLP) for the prediction of fouling resistance in heat exchanger to MgO-water and CuO-water nanofluids

2021 ◽  
Author(s):  
Ahmed Benyekhlef ◽  
Brahim Mohammedi ◽  
Djamel Hassani ◽  
Salah Hanini
Keyword(s):  
Neural Network ◽  
Experimental Data ◽  
Artificial Neural Network ◽  
Heat Exchanger ◽  
Coefficient Of Determination ◽  
Percentage Error ◽  
Inlet Temperature ◽  
Fouling Resistance ◽  
Data Points ◽  
Artificial Neural

Abstract In this work an artificial neural network model was developed with the aim of predicting fouling resistance for heat exchanger, the network was designed and trained by means of 375 experimental data points that were selected from the literature. This data points contains 6 inputs, including time, volumetric concentration, heat flux, mass flow rate, inlet temperature, thermal conductivity and fouling resistance as an output. The experimental data are used for training, testing and validation the ANN using multiple layer perceptron (MLP). The comparison of statistical criteria of different networks shows that the optimal structure for predicting the fouling resistance of the nanofluid is the MLP network with 20 hidden neurons, which has been trained with Levenberg–Marquardt (LM) algorithm. The accuracy of the model was assessed based on three known statistical metrics including mean square error (MSE), mean absolute percentage error (MAPE) and coefficient of determination (R2). The obtained model was found with the performance of {MSE = 6.5377 × 10−4, MAPE = 2.40% and R2 = 0.99756} for the training stage, {MSE = 3.9629 × 10−4, MAPE = 1.8922% and R2 = 0.99835} for the test stage and {MSE = 5.8303 × 10−4, MAPE = 2.57% and R2 = 0.99812} for the validation stage. In order to control the fouling procedure, and after conducting a sensitivity analysis, it found that all input variables have strong effect on the estimation of the fouling resistance.

Improved Macro-clusters generation using Top-k shared Micro-clusters in Data Streams

2017 ◽  
Vol 7 (10) ◽  
pp. 52
Author(s):  
LAKSHMI PRANEETHA
Keyword(s):  
Real Time ◽  
Data Streams ◽  
Bloom Filter ◽  
Scientific Applications ◽  
Pruning Algorithm ◽  
Density Data ◽  
Data Points ◽  
Short Time ◽  
Information Streams

Now-a-days data streams or information streams are gigantic and quick changing. The usage of information streams can fluctuate from basic logical, scientific applications to vital business and money related ones. The useful information is abstracted from the stream and represented in the form of micro-clusters in the online phase. In offline phase micro-clusters are merged to form the macro clusters. DBSTREAM technique captures the density between micro-clusters by means of a shared density graph in the online phase. The density data in this graph is then used in reclustering for improving the formation of clusters but DBSTREAM takes more time in handling the corrupted data points In this paper an early pruning algorithm is used before pre-processing of information and a bloom filter is used for recognizing the corrupted information. Our experiments on real time datasets shows that using this approach improves the efficiency of macro-clusters by 90% and increases the generation of more number of micro-clusters within in a short time.

Sign in / Sign up

Export Citation Format

Share Document