Standpipe Pressure Research Articles

Predicting Rate of Penetration and optimization Weight on bit using Artificial Neural Networks

Obtaining the maximum Rate of Penetration (ROP) by optimization drilling parameters is the aim of every drilling engineer. This is because it could save time, reduce cost and minimize drilling problems. However, ROP depends on a lot of parameters which lead to difficulties in its prediction. Therefore, it is necessary and important to investigate a solution predicting ROP with high accuracy to determine the suitable drilling parameters. In this study, a new approach using Artificial Neural Network (ANN) has been proposed to predict ROP from real – time drilling data of several wells in Nam Rong - Doi Moi field with more than 900 datasets included important parameters such as the weight on bit (WOB), weight of mud (MW), rotary speed (RPM), standpipe pressure (SPP), flow rate (FR), torque (TQ). In the process of training the network, algorithms and the number of neurons in the hidden layer were varied to find the optimal model. The ANN model shows high accuracy when compared to actual ROP, therefore it can be recommended as an effective and suitable method to predict the ROP of other wells in the research area. Besides, base on the proposed ANN model, authors carried out experiments and determind the optimal weight on bit value for the drilling interval from 1800 to 2300 m of wells in Nam Rong Doi Moi field

Real-time prediction of formation pressure gradient while drilling

Accurate real-time pore pressure prediction is crucial especially in drilling operations technically and economically. Its prediction will save costs, time and even the right decisions can be taken before problems occur. The available correlations for pore pressure prediction depend on logging data, formation characteristics, and combination of logging and drilling parameters. The objective of this work is to apply artificial neural networks (ANN) and adaptive neuro-fuzzy inference system (ANFIS) to introduce two models to estimate the formation pressure gradient in real-time through the available drilling data. The used parameters include rate of penetration (ROP), mud flow rate (Q), standpipe pressure (SPP), and rotary speed (RS). A data set obtained from some vertical wells was utilized to develop the predictive model. A different set of data was utilized for validating the proposed artificial intelligence (AI) models. Both models forecasted the output with a good correlation coefficient (R) for training and testing. Moreover, the average absolute percentage error (AAPE) did not exceed 2.1%. For validation stage, the developed models estimated the pressure gradient with a good accuracy. This study proves the reliability of the proposed models to estimate the pressure gradient while drilling using drilling data. Moreover, an ANN-based correlation is provided and can be directly used by introducing the optimized weights and biases, whenever the drilling parameters are available, instead of running the ANN model.

Combining physics-based and data-driven modeling in well construction: Hybrid fluid dynamics modeling

This study presents a hybrid modeling approach combining physics-based and data-driven models for improved standpipe pressure prediction during well constructing. The proposed approach provides a more robust and accurate model that mitigates some of the disadvantages of using purely physics-based or data-driven models.We start with purely physics-based modeling of standpipe pressure, both steady-state and transient. The steady-state model can predict the magnitude of pressure during drilling and circulation, while the transient model can simulate dynamic behavior such as pressure spikes when flow is initiated and fluid gels in the wellbore are broken. We then evaluate several machine learning techniques including neural network, deep learning, Gaussian process, support vector machine, and random forest, which were trained with drilling time-series datasets. Finally, machine learning techniques are combined with physics-based models via a hidden Markov model, which involves a rule-based, stochastic decision-making algorithm.The results of the hybrid modeling exercise show that the proposed hybrid model can more accurately predict standpipe pressure and capture the transient events when compared to either physics-based or machine learning models used by themselves. The hybrid model also provides better interpretability of results compared to a purely data-driven black-box model. This is because purely data-driven models lack a connection to the underlying physics.Being able to accurately model and manage the pressure response during drilling operations is essential, especially for wells drilled in narrow-margin drilling environments. We demonstrate how pressure can be more accurately predicted through our proposed hybrid modeling, leading to safer, more optimized operations. The work is also presented as an example of the benefits of hybrid modeling in general, which can be applied to many areas of well construction beyond mere standpipe prediction.

Generation of Synthetic Sonic Slowness Logs From Real-Time Drilling Sensors Using Artificial Neural Network

Abstract The acoustic data in terms of compressional and shear wave velocity provide important petrophysical information about the rock. The sonic data are a significant input that is commonly used for deriving geomechanical parameters. Understanding the geomechanical properties of reservoir rock is essential during the drilling, development, production, and stimulation of an oil or gas reservoir. Among them, Young's modulus and Poisson's ratio are the most important elastic parameters. These properties are usually estimated from bulk density, compressional, and shear wave velocity log data. Sonic data acquisition is usually achieved through dipole sonic imager log or laboratory testing on core samples which is costly and time-consuming. Acquiring sonic data from wireline logs is not a feasible approach all the time, as the wireline log, specially shear-wave log, may not be recorded for every well. However, drilling data are available in real-time for every well using real-time drilling sensors. The main objective of this paper is to predict sonic slowness logs in real-time based on the drilling data using artificial neural network (ANN). The data used in this study were recorded during the drilling of 12¼″ hole sections from two wells. Many formations of different lithology were penetrated while drilling these sections of over 3000 ft vertical interval. The drilling and sonic data sets were recorded and preprocessed before using them for the ANN model. About 2900 data points from the first well were used for building and testing the model. The input parameters included weight on bit (WOB), torque (T), standpipe pressure (SPP), pipe speed (PS), rate of penetration (ROP), and mud flowrate (Q). Another data set of 2000 data points from the second well that was drilled in the same field was used to validate the model. The predictions were compared with sonic logs that were obtained after the drilling operation, and the results appear to be highly promising for future applications. The sonic slowness ANN models showed high accuracy for the model building (training and testing). Validation of these models was carried out using an unseen data set. The results using the validation data set for the compressional slowness model yielded a coefficient of determination (R2) of 0.983 and average absolute percentage error (AAPE) of less than 1.25%. For the shear slowness model, R2 was higher than 0.994 and AAPE less than 1.175%. The study offers empirical correlations that can be utilized to estimate the sonic slowness logs by engineers without the need to employ ANN software. The new shear slowness correlation was compared with other widely used correlations and the results showed high accuracy.

Use of Artificial Neural Networks in predicting rate of penetration and optimization weight on bit for several wells in Nam Rong - Doi Moi field, Vietnam

Obtaining the maximum Rate of Penetration (ROP) by optimization of drilling parameters is the aim of every drilling engineer. This helps to save time, reduces cost and minimizes drilling problems. Since ROP depends on a lot of parameters, it is very difficult to predict it correctly. Therefore, it is necessary and important to investigate a solution for predicting ROP with high accuracy in order to determine the suitable drilling parameters. In this study, a new approach using Artificial Neural Network (ANN) has been proposed to predict ROP from real - time drilling data of several wells in Nam Rong - Doi Moi field with more than 900 datasets included important parameters such as weight on bit (WOB), weight of mud (MW), rotary speed (RPM), stand pipe pressure (SPP), flow rate (FR), torque (TQ). In the process of training the network, algorithms and the number of neurons in the hidden layer were varied to find the optimal model. The ANN model shows high accuracy when comparing to actual ROP, therefore it can be recommended as an effective and suitable method to predict ROP of other wells in research area. Besides, base on the proposed ANN model, authors carried out experiments and determine the optimal weight on bit value for the drilling interval from 1800 to 2300 m of wells in in Nam Rong Doi Moi field.

Real-time prediction of Poisson\u2019s ratio from drilling parameters using machine learning tools

Rock 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.

Real-Time Prediction of Acoustic Velocities While Drilling Vertical Complex Lithology Using AI Technique

Mechanical rock properties are often determined using sonic log data—compressional velocity (VP) and shear velocity (VS). However, a sonic well log is not always acquired due to deteriorated hole condition (i.e., hole washout), sonic tool failures, especially in high-pressure, high-temperature (HPHT) wells, and relatively high cost. This paper introduces two data-driven models, namely artificial neural network (ANN) and random forest (RF), to estimate VP and VS across different formations that are characterized by deep burial depth and strong heterogeneity. Two types of actual field data were used to develop the models: (i) drilling surface parameters, which include flow rate, standpipe pressure, rotary speed, and surface torque, and (ii) acoustic velocities VP and VS, which were acquired by a conventional sonic log. Well-1 and Well-2 with data points of 6,846 were used to develop the models, while Well-3 with 1,016 data points was used to evaluate the capability of the developed models to generalize on an unseen data set with different statistical behavior. Furthermore, Well-3 was used to compare the accuracy of the developed models with the earliest published correlations in estimating the VS. The results showed that the RF outperformed the optimized ANN in estimating VP and VS in Well-3. The RF predicted the VP with a low average absolute percentage error (AAPE) of 0.9% and correlation of coefficient (R) of 0.87, while the AAPE and R were 6.7 % and 0.45 in the case of ANN. Similarly, the RF estimated the VS with an AAPE of 1.1% and R of 0.85, whereas the ANN predicted the VS with an AAPE of 9.5% and R of 0.40. Furthermore, the RF was the most accurate in determining VS in Well-3 compared to the earliest published correlations.

Data-Driven Modeling Approach for Pore Pressure Gradient Prediction while Drilling from Drilling Parameters.

Real-time prediction of the formation pressure gradient is critical mainly for drilling operations. It can enhance the quality of decisions taken and the economics of drilling operations. The pressure while drilling tool can be used to provide pressure data while drilling, but the tool cost and its availability limit its usage in many wells. The available models in the literature for pressure gradient prediction are based on well logging or a combination of some drilling parameters and well logging. The well-logging data are not available for all wells in all sections in most wells. The objective of this paper is to use support vector machines, functional networks, and random forest (RF) to develop three models for real-time pore pressure gradient prediction using both mechanical and hydraulic drilling parameters. The used parameters are mud flow rate (Q), standpipe pressure, rate of penetration, and rotary speed (RS). A data set of 3239 field data points was used to develop the predictive models. A different data set unseen by the model was utilized for the validation of the proposed models. The three models predicted the pore pressure gradient with a correlation coefficient (R) of 0.99 and 0.97 for training and testing, respectively. The root-mean-squared error (RMSE) ranged from 0.008 to 0.021 psi/ft for training and testing, respectively, between the predicted and the actual pore pressure data. Moreover, the average absolute percentage error (AAPE) ranged from 0.97% to 3.07% for training and testing, respectively. The RF model outperformed the other models by an R of 0.99 and RMSE of 0.01. The developed models were validated using another data set. The models predicted the pore pressure gradient for the validation data set with high accuracy (R of 0.99, RMSE around 0.01, and AAPE around 1.8%). This work shows the reliability of the developed models to predict the pressure gradient from both mechanical and hydraulic drilling parameters while drilling.

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

AbstractThe 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 2333 data points from well (A) with 70:30 training to testing ratio. The models were validated using unseen dataset (1300 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.

New model for standpipe pressure prediction while drilling using Group Method of Data Handling

The continuous evaluation of the measured Stand Pipe Pressure (SPP) against a modeled SPP value in real-time involves the automatic detection of undesirable drilling events such as drill string washouts and mud pump failures. Numerous theoretical and experimental studies have been established to calculate the friction pressure losses using different rheological models and based on an extension of pipe flow correlations to an annular geometry. However, it would not be feasible to employ these models for real-time applications since they are limited to some conditions and intervals of application and require input parameters that might not be available in real-time on each rig. In this study, The Group Method of Data Handling (GMDH) is applied to develop a trustworthy model that can predict the SPP in real-time as a function of mud flow, well depth, RPM and the Fan VG viscometer reading at 600 and 300 rpm. In order to accomplish the modeling task, 3351 data points were collected from two wells from Algerian fields. Graphical and statistical assessment criteria disclosed that the model predictions are in excellent agreement with the experimental data with a coefficient of determination of 0.9666 and an average percent relative error less than 2.401%. Furthermore, another dataset (1594 data points) from well-3 was employed to validate the developed correlation for SPP. The obtained results confirmed that the proposed GMDH-SPP model can be applied in real-time to estimate the SPP with high accuracy. Besides, it was found that the proposed GMDH correlation follows the physically expected trends with respect to the employed input parameters. Lastly, the findings of this study can help for the early detection of downhole problems such as drill string washout, pump failure, and bit balling.

Real-Time Prediction of the Dynamic Young’s Modulus from the Drilling Parameters Using the Artificial Neural Networks

The dynamic Young’s modulus (Edyn) is an important factor for evaluating the static Young’s modulus which is an important parameter influences hydraulic fracturing design, drilling performance, in situ stresses estimation, and wellbore stability evaluation. Currently, the prediction of the Edyn requires the knowledge of the shear and compressional velocities and bulk density, which may not always be available. For the first time, an equation for evaluating Edyn in real-time from the weight on bit, the rate of penetration, torque, standpipe pressure, drill pipe rotation speed, and the drilling fluid flow rate is introduced. This new correlation was developed from the artificial neural networks (ANN) which were trained on 2054 data points from Well-A. The developed correlation was tested and validated on 871 and 2912 data points from Well-B and Well-C, respectively. The results showed that the ANN model evaluated Edyn with average absolute percentage error (AAPE) of 3.09%, for the training data. The developed equation estimated the Edyn with AAPE of only 3.38% and 3.73%, for the testing and validation data, respectively.

Predicting Drilling Rate of Penetration Using Artificial Neural Networks

Oil well drilling processes are generally high-cost operations; however, these costs can be reduced by optimising drilling operations. In particular, it is vital to optimise the drilling rate of penetration during oil well drilling operations. Many parameters affect drilling penetration rate, and these have complex relationships with each other. The accurate prediction of the drilling rate of penetration has particular importance in the optimisation of all drilling parameters and the reduction of drilling costs. In this paper, a neural network model is developed to predict the rate of penetration for an Iraqi oil field as a function of well depth, drilling fluid inflow, bit rotation speed (RPM), weight on bit (WOB), standpipe pressure, and bit size. The data on which the network was trained was collected from one drilled oil well, and 3,939 data points were used to develop the new model. These were randomly divided into two parts, with 70% used for training and 30% used for testing. The results showed that the resulting neural network model offers high accuracy for predicting the drilling rate of penetration. The statistical analysis showed that the developed neural network model predicted the rate of penetration very high accuracy (correlation coefficient of 0.983 and average absolute error of just 7.78%). The new model can also be used to determine the optimum drilling parameters to obtain a desired rate of penetration.

Hydraulics analysis of the U-tubing effect in a riserless drilling system

As a newly developed marine drilling technology, riserless drilling (RD) shows obvious advantages for use in deep-water and ultra-deepwater petroleum resources exploitation. However, the available published hydraulic analysis models for RD are rare or imperfect, especially regarding the lack of accounting for the out-of-hole time. To analyse the actual flow characteristics of drilling mud in an RD system after the surface mud pumping is complete, this paper presents a new hydraulic simulation model of the U-tubing effect. The specific calculation methods of pressure loss in the drilling string and the wellbore annulus at different flow regimes (turbulent flow, transition flow, and laminar flow) are provided based on the Herschel-Bulkley (HB) rheological model. A case study shows that a critical volumetric flow rate (CVFR) exists for a specific RD system to just cause the standpipe pressure to become zero. Only when the initial pump circulation rate is greater than the CVFR can it ensure the normal operation of the RD. Otherwise, the fluid mud level inside the drilling string will drop, resulting in the u-tubing effect. In the first few seconds after the surface pump is shut down, the wellbore transient flow rate is influenced strongly by the initial circulation rate. When the initial flow rate is less than the CVFR, the transient flow rate is accelerated during the first few seconds, which is not the expected behaviour. The influence of the drilling string size, fluid density and rheological parameters of the drilling fluid on the transient flow rate and the Bottom Hole Pressure (BHP) are also considered. The results proved that the smaller values of the rheological parameters are beneficial for reducing the fluctuation of the BHP during the U-tubing process.

Prediction of properties of reservoir using Artificial Neural Network and Monte Carlo Simulation

Two methods for forecasting reservoir distribution are used: Monte Carlo Simulation and Artificial Neural Network. The data used in this research was obtained from the drilling sheet report of the Efe04 well located in the Northern Niger Delta Depobelt. The operator released the data set of the Efe field. Amukpe well data from the Amukpe field was also used as part of the test data to see how the model works on different fields. To minimize uncertainties, only the surface drilling parameters are used for the model. Mode of operation (rotation or sliding), Torque, Surface Revolution, Flow rate (gallons per minute), Stand Pipe Pressure, Revolutions per Minute, hole size. When reservoir distribution can be predicted, it is extremely beneficial since it increases exploration accuracy and lowers costs by delaying the next round of exploration. Geostatistics, on the other hand, is rarely used in areas with few wells drilled. A new technique called Geology Driven Integration Tool (GDI) has been developed to estimate reservoir parameters when just a few wells are available. Due to the lack of well data and regional geological constraints in the GDI model, several pseudo-wells are constructed by Monte Carlo Simulation to make up for the deficiency of a few real wells. They can also be used to create fake seismograms. To determine the weighting factors that link the selected seismic attributes to the given reservoir features, the appropriate seismic attributes and the given reservoir parameters are input to the Artificial Neural Network (ANN). In the end, the ANN is trained on all of the seismic data in the area and then used to estimate reservoir property distribution. In addition to the areas that have already been explored, the estimated results suggest exploring the southern portion of the Efe field and the northern portion of the Efe field as potential prospect locations. In the southern half of the Amukpe field, the gas zone's net thickness is expected to rise to 27 meters, thanks to increased porosity of 27%. North of the Efe field, a 15-25-meter-thick porosity-rich reservoir is predicted to be distributed.

Unconfined compressive strength (UCS) prediction in real-time while drilling using artificial intelligence tools

Unconfined compressive strength (UCS) is a major mechanical parameter of the rock which has an essential role in developing geomechanical models. It can be estimated directly by lab testing of retrieved core samples or from well log data. These methods are very expensive and require huge efforts and time. Therefore, there is a need to develop a new technique for predicting UCS values in real-time. In this study, three artificial intelligence (AI) models were developed using artificial intelligence tools; artificial neural networks (ANN), adaptive neuro-fuzzy inference system (ANFIS), and support vector machine (SVM) to predict UCS of the downhole formations while drilling based on real-time recording of the drilling mechanical parameters. These parameters include rate of penetration (ROP), mud pumping rate (GPM), stand-pipe pressure (SPP), rotary speed in revolution per minute (RPM), torque (T), and weight on bit (WOB). A dataset of 1771 points from a Middle Eastern field was used to build the developed models: for training and testing processes. A new UCS correlation was developed based on the optimized AI model. Another set of data (2175 data points unseen by the model) was used to validate the model and the developed UCS correlation. The developed ANN-model outperformed the ANFIS- and SVM-models with a correlation coefficient (R-value) of 0.99 and an average absolute percentage error (AAPE) of 3.48% between the predicted and actual UCS values. The new UCS correlation outperformed the available correlations for UCS prediction and it was able to predict the UCS with AAPE of 4.2% compared to the actual UCS values.

Artificial neural network model for real-time prediction of the rate of penetration while horizontally drilling natural gas-bearing sandstone formations

Rate of penetration (ROP) is a critical parameter affecting the total cost of drilling an oil well. This study introduces an empirical equation developed based on the optimized artificial neural networks (ANNs) for estimation of the rate of penetration (ROP) in real-time while horizontally drilling natural gas-bearing sandstone reservoirs based on the surface measurable drilling parameters of the mud injection rate, drillstring rotation speed (DSR), standpipe pressure, torque, and weight on bit (WOB) in combination with ROPc, which is a new parameter developed in this study based on regression analysis. The ANN model was learned and optimized using 1154 data points; the training parameters were collected while horizontally drilling natural gas-bearing sandstone formations in Well-A. An empirical equation for ROP estimation was developed based on the optimized ANN model. Moreover, 495 unseen data points from Well-A were used to test the developed ROP equation, which was finally validated on 2213 data points from Well-B. The predictability of the new ROP equation was compared with the available correlations. The results showed that, without considering ROPc, the optimized ANN model estimated the ROP for the training dataset with an average absolute percentage error (AAPE) of 42.6% and correlation coefficient (R) of 0.424, while when ROPc was considered as an input, the AAPE decreased to 5.11% and R increased to 0.991. The new empirical equation estimated the ROP for the testing data of Well-A with AAPE and R of 5.39% and 0.989 and for the validation data of Well-B with AAPE and R of 8.85% and 0.954, respectively. The new empirical equation overperformed all the available empirical correlations for ROP estimation.

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

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.

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

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%.

Dynamical Simulation of High-Pressure Gas Kick in Ultra-Deepwater Riserless Drilling

Abstract During riserless drilling for ultra-deepwater gas wells, well control challenges induced by high-pressure gas kick will be faced. A two-phase flow model with consideration of high-pressure gas invasion during riserless drilling was proposed, and the model was proved to be more accurate for predicting high-pressure gas kick during riserless drilling by reproducing field data and comparison with published models. Then, a dynamical simulation of high-pressure gas kick in ultra-deepwater riserless drilling was presented. Results showed that during ultra-deepwater riserless drilling, the bottom hole pressure will be underestimated, while pit gain will be over-estimated without considering the gas acceleration effect. With the consideration of gas acceleration effect at high-pressure well bottom, the gas influx rate increases rapidly with the kick time and tends to be stable after a period of time as negative pressure difference at well bottom increases. During riserless drilling, according to the timeliness and effectivity of kick detection methods, pit gain is prior for kick detection, following bottom hole pressure, standpipe pressure, and return rate. Moreover, if early gas kick was not detected, the rapid increase in change rate of standpipe pressure and return rate can be regarded as an indicator, showing that gas is reaching mud line. Besides, the effects of shutoff time, drilling displacement, drilling fluid density increases, geothermal gradient, and reservoir permeability on kick indicators and wellbore pressure have been discussed. The research results could provide important theoretical bases and technical guidance for well control aspects of riserless drilling.

Use of Machine Learning and Data Analytics to Detect Downhole Abnormalities While Drilling Horizontal Wells, With Real Case Study

AbstractThe standard torque and drag (T&D) modeling programs have been extensively used in the oil and gas industry to predict and monitor the T&D forces. In the majority of cases, there has been variability in the accuracy between the pre-calculated (based on a T&D model) and actual T&D values, because of the dependence of the model’s predictability on guessed inputs (matching parameters) which may not be correctly predicted. Therefore, to have a reliable model, program users must alter the model inputs and mainly the friction coefficient to match the actual T&D. This, however, can conceal downhole conditions such as cutting beds, tight holes, and sticking tendencies. The objective of this study is to develop an intelligent machine to predict the continuous profile of the surface drilling torque to enable the detection of operational problems ahead of time. This paper details the development and evaluation of an intelligent system that could promote safer operation and extend the response time limit to prevent undesired events. Actual field data of Well-1, starting from the time of drilling a 5-7/8-in. horizontal section until 1 day prior to the stuck pipe incident, were used to train and test three models: random forest, artificial neural network, and functional network, with an 80/20 training-to-testing data ratio, to predict the surface drilling torque. The independent variables for the model are the drilling surface parameters, namely: flow rate (Q), hook load (HL), rate of penetration (ROP), rotary speed (RS), standpipe pressure (SPP), and weight-on-bit (WOB). The prediction capability of the models was evaluated in terms of correlation of coefficient (R) and average absolute error percentage (AAPE). The model with the highest R and lowest AAPE was selected to continue with the analysis to detect downhole abnormalities. The best-developed model was used to predict the surface drilling torque on the last day leading up to the incident in Well-1, which represents the normal and healthy trend. Then, the model was coupled with a multivariate metric distance called “Mahalanobis” to be used as a classification tool to measure how close an actual observation is to the predictive normal and healthy trend. Based on a pre-determined threshold, each actual observation was labeled “NORMAL” or “ANOMAL.” Well-2 with a stuck pipe incident was used to assess the capability of the developed system in detecting downhole abnormalities. The results showed that in Well-1, where a stuck pipe incident was reported, a continuous alarm was detected by the developed system 9 h before the drilling crew observed any abnormality, while the alarm was detected 7 h prior to any observation by the crew in Well-2. The developed intelligent system could help the drilling crew to detect downhole abnormalities in real-time, react, and take corrective action to mitigate the problem promptly.