Real-time rate of penetration prediction for motorized bottom hole assembly using machine learning methods.

Drilling rate of penetration (ROP) is one of the most important factors that have their significant effect on the drilling operation economically and efficiently. Motorized bottom hole assembly (BHA) has different applications that are not limited to achieve the required directional work but also it could be used for drilling optimization to enhance the ROP and mitigate the downhole vibration. Previous work has been done to predict ROP for rotary BHA and for rotary steerable system BHA; however, limited studies considered to predict the ROP for motorized BHA. In the present study, two artificial intelligence techniques were applied including artificial neural network and adaptive neurofuzzy inference system for ROP prediction for motorized assembly in the rotary mode based on surface drilling parameters, motor downhole output parameters besides mud parameters. This new robust model was trained and tested to accurately predict the ROP with more than 5800 data set with a 70/30 data ratio for training and testing respectively. The accuracy of developed models was evaluated in terms of average absolute percentage error, root mean square error, and correlation coefficient (R). The obtained results confirmed that both models were capable of predicting the motorized BHA ROP on Real-time. Based on the proposed model, the drilling parameters could be optimized to achieve maximum motorized BHA ROP. Achieving maximum ROP will help to reduce the overall drilling cost and as well minimize the open hole exposure time. The proposed model could be considered as a robust tool for evaluating the motorized BHA performance against the different BHA driving mechanisms which have their well-established models.

Machine learning accelerated approach to infer nuclear magnetic resonance porosity for a middle eastern carbonate reservoir.

Carbonate rocks present a complicated pore system owing to the existence of intra-particle and interparticle porosities. Therefore, characterization of carbonate rocks using petrophysical data is a challenging task. Conventional neutron, sonic, and neutron-density porosities are proven to be less accurate as compared to the NMR porosity. This study aims to predict the NMR porosity by implementing three different machine learning (ML) algorithms using conventional well logs including neutron-porosity, sonic, resistivity, gamma ray, and photoelectric factor. Data, comprising 3500 data points, was acquired from a vast carbonate petroleum reservoir in the Middle East. The input parameters were selected based on their relative importance with respect to output parameter. Three ML techniques such as adaptive neuro-fuzzy inference system (ANFIS), artificial neural network (ANN), and functional network (FN) were implemented for the development of prediction models. The model's accuracy was evaluated by correlation coefficient (R), root mean square error (RMSE), and average absolute percentage error (AAPE). The results demonstrated that all three prediction models are reliable and consistent exhibiting low errors and high 'R' values for both training and testing prediction when related to actual dataset. However, the performance of ANN model was better as compared to other two studied ML techniques based on minimum AAPE and RMSE errors (5.12 and 0.39) and highest R (0.95) for testing and validation outcome. The AAPE and RMSE for the testing and validation results were found to be 5.38 and 0.41 for ANFIS and 6.06 and 0.48 for FN model, respectively. The ANFIS and FN models exhibited 'R' 0.937 and 0.942, for testing and validation dataset, respectively. Based on testing and validation results, ANFIS and FN models have been ranked second and third after ANN. Further, optimized ANN and FN models were used to extract explicit correlations to compute the NMR porosity. Hence, this study reveals the successful applications of ML techniques for the accurate prediction of NMR porosity.

Geomechanics of Organic Matters Contained in Shales: A Molecular-Level Investigation.

Petrophysical and mechanical properties of kerogen are difficult to obtain through conventional techniques due to length scale limitations. Characterization of kerogen requires the isolation of organic materials from the rock matrix, which is associated with a high probability of mechanical damage or chemical alteration of the properties. Alternatively, computational modeling and molecular representation of kerogens can be used to simulate the outcomes of the experimental work. Volumetric and thermodynamics modeling of kerogens has provided the means for recreating nanoscale structures virtually. This research implements existing three-dimensional (3D) kerogen macromolecules to form kerogen structures that can be analyzed for the mechanical behavior of type II organic matters, mainly found in shales, at different maturity levels. Additionally, the underlying factors that could control the mechanical behavior, such as the density and porosity, were investigated. The results are compared against those reported following a similar methodology or other advanced fine-scale experimental work. The results revealed an elastomer-like mechanical behavior of kerogen with comparable elastic moduli regardless of maturity level. Moreover, the mechanical behavior of kerogen was sensitive to the type of fluid contained within the structure. Such observations can help shed more light on the macroscopic mechanical properties of shales, especially for formations with high organic contents.

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.

Hyperparameter Tuning of Artificial Neural Networks for Well Production Estimation Considering the Uncertainty in Initialized Parameters.

A well production rate is an essential parameter in oil and gas field development. Traditional models have limitations for the well production rate estimation, e.g., numerical simulations are computation-expensive, and empirical models are based on oversimplified assumptions. An artificial neural network (ANN) is an artificial intelligence method commonly used in regression problems. This work aims to apply an ANN model to estimate the oil production rate (OPR), water oil ratio (WOR), and gas oil ratio (GOR). Specifically, data analysis was first performed to select the appropriate well operation parameters for OPR, WOR, and GOR. Different ANN hyperparameters (network, training function, and transfer function) were then evaluated to determine the optimal ANN setting. Transfer function groups were further analyzed to determine the best combination of transfer functions in the hidden layers. In addition, this study adopted the relative root mean square error with the statistical parameters from a stochastic point of view to select the optimal transfer functions. The optimal ANN model's average relative root mean square error reached 6.8% for OPR, 18.0% for WOR, and 1.98% for GOR, which indicated the effectiveness of the optimized ANN model for well production estimation. Furthermore, comparison with the empirical model and the inputs effect through a Monte Carlo simulation illustrated the strength and limitation of the ANN model.

A Game-Theoretic Approach to Improve Energy-Related Data.

With the increase in the energy demand, the magnitude of energy production operation increased in scale and complexity and went too far in remote areas. To manage such a big fleet, sensors were installed to send real-time data to operation centers, where subject matter experts monitor the operations and provide live support. With the expansion of installed sensors and the number of monitored operations, the operation centers were flooded with a massive amount of data beyond human capability to handle. As a result, it became essential to capitalize on the artificial intelligence (AI) capability. Unfortunately, due to the nature of operations, the data quality is an issue limiting the impact of AI in such operations. Multiple approaches were proposed, but they require lot of time and cannot be upscaled to support active real-time data streaming. This paper presents a method to improve the quality of energy-related (drilling) real-time data, such as hook load (HL), rate of penetration (ROP), revolution per minute (RPM), and others. The method is based on a game-theoretic approach, and when applied on the HL-one of the most challenging drilling parameters-it achieved a root mean square error (RMSE) of 3.3 accuracy level compared to the drilling data quality improvement subject matter expert's (SME) level. This method took few minutes to improve the drilling data quality compared to weeks in the traditional manual/semiautomated methods. This paper addresses the energy data quality issue, which is one of the biggest bottlenecks toward upscaling AI technology into active operations. To the authors' knowledge, this paper is the first attempt to employ the game-theoretic approach in the drilling data improvement process, which facilitates greater integration between AI models and the energy live data streaming, also setting the stage for more research in this challenging AI-data domain.

Impact of HCl Acidizing Treatment on Mechanical Integrity of Carbonaceous Shale.

Hydrocarbon production from unconventional resources especially shale reservoirs has tremendously increased during the past decade. Eagle Ford shale formation is one of the major sources of oil and gas in United States. However, due to extremely low permeability of this formation, stimulation treatments are implemented for hydrocarbon production. Eagle Ford shale requires a very high breakdown pressure during fracturing treatment due to high mechanical strength and low permeability. This study aims to address these challenges through applying the acidizing treatment on the shale and studying its impact. A detailed experimental investigation was carried out in this work to evaluate mechanical integrity and mineralogical and morphological changes of the shale formation when exposed to HCl acidizing treatment. Two crucial aspects of acidizing treatment, that is, impact of acid concentrations and treatment time, were given additional focus in this study. Different parameters such as porosity, nanopermeability, uniaxial compressive strength (UCS), acoustic velocities, dynamic elastic parameters, rock surface hardness (RSH) and brittleness index (BI) were analyzed before and after the acidizing treatment for different HCl concentrations. Microimaging was done through scanning electron microscopy (SEM) and whole cores were scanned using medical computed tomography (MCT) to understand the small-scale features. X-ray diffraction was used for the minerals' identification. A continuous profile of UCS was measured through the scratch test system. Post-treatment results revealed that HCl treatment has a profound impact on rock mechanical properties of Eagle Ford shale. Considerable mass loss in core plugs was recorded after treatment at each concentration. Mineralogical composition and microimaging revealed compositional changes and porosity enhancement after the treatment. Reaction rate is higher in the first 10 min for higher acid concentrations resulting in significant changes in properties in that time interval. UCS and RSH exhibited a progressive decrease with increasing concentrations. The rate of RSH reduction increased with the increase in acid concentration nonlinearly. Acoustic velocities exhibited a considerable decrease even at low acid concentrations due to the enhancement of pore spaces. Noticeable reduction was observed in dynamic rock stiffness and BI with the increase in acid concentrations. On the contrary, Poisson's ratio showed a significant increment. Experimental findings of this research can be used to optimize the acidizing treatment for Eagle Ford shale and other similar formations. Formation breakdown pressure can be reduced significantly by applying the acid treatment to improve the production of hydrocarbons. Furthermore, a better understanding of matrix acidizing can lead to savings in time and resources during production operations.

Study of the Mechanical Behavior of Organic Matters Contained in Source Rocks: New Insights into the Role of Bitumen.

Assessment of mechanical properties of organic matters contained in unconventional formations is needed to understand the geomechanics of source rocks. The organic matters are part of the source rock matrix, and they are made of kerogen and bitumen. Although the literature has some studies addressing the properties of kerogen and bitumen, no apparent attempts were made to address the mechanical behavior of organic matters as a combination of both. Isolation of organic matters from the rocks for experimental assessments has some risks of altering the original properties because of their delicate nature and their existence as micro- and nanoconstituents. Some computational approaches such as molecular simulation can serve as an alternative platform for the purpose of delineating organic matter properties including the mechanical ones. This work implements available 3D molecular modeling of kerogen and bitumen with different ratios to mimic organic matters that can be investigated for the mechanical properties. Upon the recreation of different configurations of organic matters molecularly, mechanical parameters such Young's, bulk, and shear constants, as well as the stress-strain relationship for the elastic and plastic deformations were extracted. The mechanical behavior was closely monitored before and after saturation with a number of gases that are commonly found in subsurface formations such as methane, carbon dioxide, and nitrogen. The results revealed that the organic matters had a mechanical behavior envelope similar to what were reported for organic-based materials such as polymers. Moreover, the structures containing bitumen exhibited larger values of Poisson's ratio, indicating less likelihood of them to degrade upon applied stresses. The presented data substantiate the importance of accounting for both bitumen and kerogen in modeling the petrophysics and the mechanical behavior of the organic matters.

Machine Learning-Based Propped Fracture Conductivity Correlations of Several Shale Formations.

In hydraulic fracturing operations, small rounded particles called proppants are mixed and injected with fracture fluids into the targeted formation. The proppant particles hold the fracture open against formation closure stresses, providing a conduit for the reservoir fluid flow. The fracture's capacity to transport fluids is called fracture conductivity and is the product of proppant permeability and fracture width. Prediction of the propped fracture conductivity is essential for fracture design optimization. Several theoretical and few empirical models have been developed in the literature to estimate fracture conductivity, but these models either suffer from complexity, making them impractical, or accuracy due to data limitations. In this research, and for the first time, a machine learning approach was used to generate simple and accurate propped fracture conductivity correlations in unconventional gas shale formations. Around 350 consistent data points were collected from experiments on several important shale formations, namely, Marcellus, Barnett, Fayetteville, and Eagle Ford. Several machine learning models were utilized in this research, such as artificial neural network (ANN), fuzzy logic, and functional network. The ANN model provided the highest accuracy in fracture conductivity estimation with R 2 of 0.89 and 0.93 for training and testing data sets, respectively. We observed that a higher accuracy could be achieved by creating a correlation specific for each shale formation individually. Easily obtained input parameters were used to predict the fracture conductivity, namely, fracture orientation, closure stress, proppant mesh size, proppant load, static Young's modulus, static Poisson's ratio, and brittleness index. Exploratory data analysis showed that the features above are important where the closure stress is the most significant.

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 (R 2), 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 R 2 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 R 2 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 R 2 of 0.88 and AAPE of 8.58%, while RF has R 2 of 0.92 and AAPE of 6.5%.

Dicationic Surfactants as an Additive in Fracturing Fluids to Mitigate Clay Swelling: A Petrophysical and Rock Mechanical Assessment.

The interactions of clays with freshwater in unconventional tight sandstones can affect the mechanical properties of the rock. The hydraulic fracturing technique is the most successful technique to produce hydrocarbons from unconventional tight sandstone formations. Knowledge of clay minerals and their chemical interactions with fracturing fluids is extremely vital in the optimal design of fracturing fluids. In this study, quaternary ammonium-based dicationic surfactants are proposed as clay swelling inhibitors in fracturing fluids to reduce the fractured face skin. For this purpose, several coreflooding and breakdown pressure experiments were conducted on the Scioto sandstone samples, and the rock mechanical properties of the flooded samples after drying were assessed. Coreflooding experiments proceeded in a way that the samples were flooded with the investigated fluid and then postflooded with deionized water (DW). Rock mechanical parameters, such as compressive strength, tensile strength, and linear elastic properties, were evaluated using unconfined compressive strength test, scratch test, indirect Brazilian disc test, and breakdown pressure test. The performance of novel synthesized surfactants was compared with commercially used clay stabilizing additives such as sodium chloride (NaCl) and potassium chloride (KCl). For comparison, base case experiments were performed with untreated samples and samples treated with DW. Scioto sandstone samples with high illite contents were used in this study. Results showed that the samples treated with conventional electrolyte solutions lost permeability up to 65% when postflooded with DW. In contrast, fracturing fluid containing surfactant solutions retained the original permeability even after being postflooded with DW. Conventional clay stabilizing additives led to the swelling of clays caused by high compression and tensile strength of the rock when tested at dry conditions. Consequently, the rock fractures at a higher breakdown pressure. However, novel dicationic surfactants do not cause any swelling, and therefore, the rock fractures at the original breakdown pressure.

Real-time prediction of Poisson's 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.

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.

Real-Time Prediction of Equivalent Circulation Density for Horizontal Wells Using Intelligent Machines.

Equivalent circulation density (ECD) is an important part of drilling fluid calculations. Analytical equations based on the conservation of mass and momentum are used to determine the ECD at various depths in the wellbore. However, these equations do not incorporate important factors that have a direct impact on the ECD, such as bottom-hole temperature, pipe rotation and eccentricity, and wellbore roughness. This work introduced different intelligent machines that could provide a real-time accurate estimation of the ECD for horizontal wells, namely, the support vector machine (SVM), random forests (RF), and a functional network (FN). Also, this study sheds light on how principal component analysis (PCA) can be used to reduce the dimensionality of a data set without loss of any important information. Actual field data of Well-1, including drilling surface parameters and ECD measurements, were collected from a 5-7/8 in. horizontal section to develop the models. The performance of the models was assessed in terms of root-mean-square error (RMSE) and coefficient of determination (R 2). Then, the best model was validated using unseen data points of 1152 collected from Well-2. The results showed that the RF model outperformed the FN and SVM in predicting the ECD with an RMSE of 0.23 and R 2 of 0.99 in the training set and with an RMSE of 0.42 and R 2 of 0.99 in the testing set. Furthermore, the RF predicted the ECD in Well-2 with an RMSE of 0.35 and R 2 of 0.95. The developed models will help the drilling crew to have a comprehensive view of the ECD while drilling high-pressure high-temperature wells and detect downhole operational issues such as poor hole cleaning, kicks, and formation losses in a timely manner. Furthermore, it will promote safer operation and improve the crew response time limit to prevent undesired events.

Effect of the Filtrate Fluid of Water-Based Mud on Sandstone Rock Strength and Elastic Moduli.

During drilling operations, the filtrate fluid of the drilling mud invades the drilled rock. The invading filtrate fluid will interact with the rock and therefore alter the rock internal topography, pore system, elastic moduli, and rock strength. The objective of this study is to evaluate the effect of the mud filtrate of barite-weighted water-based mud on the geomechanical properties of four types of sandstone rocks (Berea Buff, Berea Spider, Bandera Brown, and Parker). The mud filtrate was collected to provide mud filtrate-rock exposure at a pressure of 300 psi and 200 °F temperature for 10 days. The study assessed the alteration in the rock geomechanics employing an integrated laboratory analysis of X-ray diffraction (XRD), scanning electron microscopy (SEM), nuclear magnetic resonance (NMR), and scratch testing. The ultrasonic results showed changes after exposure to the mud filtrate and an obvious reduction trend in the shear wave velocities due to the dissolution and mineralogical modifications in rock samples. The obtained results displayed a general strength reduction for the four sandstone types with different levels. The strength reduction ranged from 6% reduction for Berea Spider to a record 23% reduction for Parker. For all sandstone types, Young's modulus showed a general reduction ranging from 11 to 40%, while Poisson's ratio recorded an increase by 62-155% after the filtrate interaction. The study illustrated the role of pore-system alteration in controlling the rock strength and dynamic moduli.

Imidazolium-Based Ionic Liquids as Clay Swelling Inhibitors: Mechanism, Performance Evaluation, and Effect of Different Anions.

Clay swelling is one of the challenges faced by the oil industry. Water-based drilling fluids (WBDF) are commonly used in drilling operations. The selection of WBDF depends on its performance to improve rheology, hydration properties, and fluid loss control. However, WBDF may result in clay swelling in shale formations during drilling. In this work, the impact of imidazolium-based ionic liquids on the clay swelling was investigated. The studied ionic liquids have a common cation group, 1-allyl-3-methyllimidozium, but differ in anions (bromide, iodide, chloride, and dicyanamide). The inhibition behavior of ionic liquids was assessed by linear swell test, inhibition test, capillary suction test, rheology, filtration, contact angle measurement, scanning electron microscopy, and X-ray diffraction (XRD). It was observed that the ionic liquids with different anions reduced the clay swelling. Ionic liquids having a dicyanamide anion showed slightly better swelling inhibition performance compared to other inhibitors. Scanning electron microscopy images showed the water tendency to damage the clay structure, displaying asymmetrical cavities and sharp edges. Nevertheless, the addition of an ionic liquid to sodium bentonite (clay) exhibited fewer cavities and a smooth and dense surface. XRD results showed the increase in d-spacing, demonstrating the intercalation of ionic liquids in interlayers of clay. The results showed that the clay swelling does not strongly depend on the type of anion in imidazolium-based ILs. However, the type of anion in imidazolium-based ILs influences the rheological properties. The performance of ionic liquids was compared with that of the commonly used clay inhibitor (sodium silicate) in the oil and gas industry. ILs showed improved performance compared to sodium silicate. The studied ionic liquids can be an attractive alternative for commercial clay inhibitors as their impact on the other properties of the drilling fluids was less compared to commercial inhibitors.

Exposure Time Impact on the Geomechanical Characteristics of Sandstone Formation during Horizontal Drilling.

The rock geomechanical properties are the key parameters for designing the drilling and fracturing operations and for programing the geomechanical earth models. During drilling, the horizontal-section drilling fluids interact with the reservoir rocks in different exposure time, and to date, there is no comprehensive work performed to study the effect of the exposure time on the changes in sandstone geomechanical properties. The objective of this paper is to address the exposure time effect on sandstone failure parameters such as unconfined compressive strength, tensile strength, acoustic properties, and dynamic elastic moduli while drilling horizontal sections using barite-weighted water-based drilling fluid. To simulate the reservoir conditions, Buff Berea sandstone core samples were exposed to the drilling fluid (using filter press) under 300 psi differential pressure and 200 °F temperature for different exposure times (up to 5 days). The rock characterization and geomechanical parameters were evaluated as a function of the exposure time. Scratch test was implemented to evaluate rock strength, while ultrasonic pulse velocity was used to obtain the sonic data to estimate dynamic elastic moduli. The rock characterization was accomplished by X-ray diffraction, nuclear magnetic resonance, and scanning electron microscope. The study findings showed that the rock compression and tensile strengths reduced as a function of exposure time (18% and 19% reduction for tensile strength and unconfined compression strength, respectively, after 5 days), while the formation damage displayed an increasing trend with time. The sonic results demonstrated an increase in the compressional and shear wave velocities with increasing exposure time. All the dynamic elastic moduli showed an increasing trend when extending the exposure time except Poisson's ratio which presented a constant behavior after 1 day. Nuclear magnetic resonance results showed 41% porosity reduction during the five days of mud interaction. Scanning electron microscope images showed that the rock internal surface topography and internal integrity changed with exposure time, which supported the observed strength reduction and sonic variation. A new set of empirical correlations were developed to estimate the dynamic elastic moduli and failure parameters as a function of the exposure time and the porosity with high accuracy.

Real-Time Prediction of Rheological Properties of Invert Emulsion Mud Using Adaptive Neuro-Fuzzy Inference System.

Tracking the rheological properties of the drilling fluid is a key factor for the success of the drilling operation. The main objective of this paper is to relate the most frequent mud measurements (every 15 to 20 min) as mud weight (MWT) and Marsh funnel viscosity (MFV) to the less frequent mud rheological measurements (twice a day) as plastic viscosity (PV), yield point (YP), behavior index (n), and apparent viscosity (AV) for fully automating the process of retrieving rheological properties. The adaptive neuro-fuzzy inference system (ANFIS) was used to develop new models to determine the mud rheological properties using real field measurements of 741 data points. The data were collected from 99 different wells during drilling operations of 12 » inches section. The ANFIS clustering technique was optimized by using training to a testing ratio of 80% to 20% as 591 data points for training and 150 points, cluster radius value of 0.1, and 200 epochs. The results of the prediction models showed a correlation coefficient (R) that exceeded 0.9 between the actual and predicted values with an average absolute percentage error (AAPE) below 5.7% for the training and testing data sets. ANFIS models will help to track in real-time the rheological properties for invert emulsion mud that allows better control for the drilling operation problems.

Data-Driven Approaches to Predict Thermal Maturity Indices of Organic Matter Using Artificial Neural Networks.

Prediction of thermal maturity index parameters in organic shales plays a critical role in defining the hydrocarbon prospect and proper economic evaluation of the field. Hydrocarbon potential in shales is evaluated using the percentage of organic indices such as total organic carbon (TOC), thermal maturity temperature, source potentials, and hydrogen and oxygen indices. Direct measurement of these parameters in the laboratory is the most accurate way to obtain a representative value, but, at the same time, it is very expensive. In the absence of such facilities, other approaches such as analytical solutions and empirical correlations are used to estimate the organic indices in shale. The objective of this study is to develop data-driven machine learning-based models to predict continuous profiles of geochemical logs of organic shale formation. The machine learning models are trained using the petrophysical wireline logs as input and the corresponding laboratory-measured core data as a target for Barnett shale formations. More than 400 log data and the corresponding core data were collected for this purpose. The petrophysical wireline logs are γ-ray, bulk density, neutron porosity, sonic transient time, spontaneous potential, and shallow resistivity logs. The corresponding core data includes the experimental results from the Rock-Eval pyrolysis and Leco TOC measurements. A backpropagation artificial neural network coupled with a particle swarm optimization algorithm was used in this work. In addition to the development of optimized PSO-ANN models, explicit empirical correlations are also extracted from the fine-tuned weights and biases of the optimized models. The proposed models work with a higher accuracy within the range of the data set on which the models are trained. The proposed models can give real-time quantification of the organic matter maturity that can be linked with the real-time drilling operations and help identify the hotspots of mature organic matter in the drilled section.

Comparative Analysis of Static and Dynamic Mechanical Behavior for Dry and Saturated Cement Mortar.

Deformational and breakage behaviors of concrete and cement mortar greatly influence various engineering structures, such as dams, river bridges, ports, tunnels, and offshore rig platforms. The mechanical and petrophysical properties are very sensitive to water content and are controlled by the liquid part in pore spaces to a large extent. The objective of this paper is to investigate the water saturation effect on the strength characteristics and deformability of cement mortar under two loading conditions, static and dynamic compression. A set of cement mortar samples was prepared and tested to study the mechanical behavior in dry and saturated states. The first part of the research incorporates the study of static mechanical properties for dry and brine-saturated cement mortar through uniaxial compressive strength tests (UCS). Second, drop-weight impact experiments were carried out to study the dynamic mechanical properties (impact resistance, deformation pattern, and fracture geometry) for dry and saturated cases. The comparative analysis revealed that water saturation caused substantial changes in compressive strength and other mechanical characteristics. Under static loading, water saturation caused a reduction in strength of 36%, and cement mortar tended to behave in a more ductile manner as compared to dry samples. On the contrary, under dynamic loading conditions, water saturation resulted in higher impact resistance and fracture toughness as compared to dry conditions. In addition, fractures could propagate to smaller depths as compared to dry case. The study will help resolve many civil, mining, and petroleum engineering problems where cement structures undergo static as well as dynamic compression, especially in a hydraulic environment where these structures interact with the water frequently. To the best of our knowledge, the effect of water saturation on the dynamic mechanical properties of cement mortar has not been well understood and reported in the literature.