Mathematical Modeling of Shale Swelling in Water-Based Muds

Kulkarni, Suhasini; Maghrabi, Shadaab; Teke, Kushabhau; Kulkarni, Dhanashree; Jamison, Dale E.

doi:10.2118/163352-ms

Cited by 7 publications

(3 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…4(a). It was observed that the prediction accuracy with ANN has significantly improved in comparison to earlier empirical models (Kulkarni et al 2012).…”

Section: Ann Modeling For a (Saturation Swelling Parameter)mentioning

confidence: 82%

Neural-net Modeling of Shale-swelling Behavior in Aqueous Drilling Fluids

et al. 2013

Self Cite

View full text Add to dashboard Cite

Managing shale swelling is critical when drilling with water-based muds (WBMs). Excessive swelling can lead to shale sloughing, borehole collapse, stuck pipe, and shale disintegration. The fine solids content can increase and cause difficulties controlling rheological properties. Linear swell meter (LSM) testing is a well-known laboratory procedure used to characterize shale swelling in a WBMs.A mathematical modeling tool known as the artificial neural network (ANN) was used to model shale swelling in a WBM. The ANN model establishes complex relationships between a set of inputs and an output based on computational modeling. For ANN modeling of the shale-swelling, the shale mineralogy and fluid composition constituted input parameters, while the output was represented by an experimental characteristic swelling parameter derived from the "% swelling vs. time" data from the LSM test for the respective shale-fluid combinations.Experimental data for building the ANN model was obtained by performing about 250 standard LSM tests on different shales with varying mineralogy and WBMs with varying salt concentrations. This shale swelling ANN model provided excellent correlation with R 2 > 0.9. The ANN model was then successfully validated for an independent set of shale-fluid conditions.Using the shale swelling ANN model, shale-swelling in WBM was predicted for a given shale mineralogy and fluid composition. This reduced the number of trials necessary to determine an optimized WBM formulation. Mud engineers can use this model in real-time as the shale chemistry varies with the depth of the formation drilled. The model provides a helpful measure of fluid performance to determine the optimization necessary to obtain the desired shale behavior. Using this method can help minimize drilling risks and costs associated with unpredictable shales. IntroductionUnderstanding the shale response in the presence of a drilling fluid is crucial to predict and manage borehole instabilities during drilling. Within the drilling industry, researchers have developed several experimental tests and numerical models to describe the interaction between shale and a drilling fluid (specifically, a WBM).Related to experiments, Chenevert and Osisanya (1989) provided various devices that can be used to measure swelling response of shales as they come in contact with WBMs. The effect of potassium chloride (KCl) containing fluids on smectiterich shales was investigated by Horsrud et al. (1998), under both atmospheric and simulated downhole conditions.With respect to computation, Molenaar et al. (1998) described the interaction between the drilling fluid composition and the mechanical behavior of shale based on constitutive models consisting of transport equations for the fluids and the ions. The effect of physio-chemical shale-fluid interaction on shale formation pressure and shale swelling was studied by Huang et al. (1998) using numerical simulations and modeling. In work closely related to this paper, Basma et al. (2003) attempted to implement sequent...

show abstract

“…4(a). It was observed that the prediction accuracy with ANN has significantly improved in comparison to earlier empirical models (Kulkarni et al 2012).…”

Section: Ann Modeling For a (Saturation Swelling Parameter)mentioning

confidence: 82%

Neural-net Modeling of Shale-swelling Behavior in Aqueous Drilling Fluids

et al. 2013

Self Cite

View full text Add to dashboard Cite

show abstract

“…They employed various inputs, such as clay content, applied pressures, and fluid composition, to predict swelling behavior. Similarly, Kulkarni et al 53 proposed a model to estimate the swelling of shale by including the shale's cation exchange capacity (CEC) and the concentrations of NaCl salt in the drilling fluid. Maghrabi et al 7 constructed an ANN model specifically for forecasting shale swelling in WBDFs.…”

Section: Introductionmentioning

confidence: 99%

An Experimental Study and Machine Learning Modeling of Shale Swelling in Extended Reach Wells When Exposed to Diverse Water-Based Drilling Fluids

Tariq,

Murtaza,

Alrasheed

et al. 2024

Energy Fuels

View full text Add to dashboard Cite

Shale swelling poses considerable challenges for companies involved in extended-reach well drilling, particularly when it comes to maintaining wellbore stability. Despite the incorporation of swelling inhibitors in water-based drilling fluids (WBDFs), shale swelling can persist as an issue. Currently, the assessment of WBDFs' ability to prevent swelling usually involves costly, timeconsuming, and labor-intensive laboratory experiments. Therefore, this study leverages machine learning techniques (ML) to forecast the dynamic linear swelling behavior of sodium bentonite-based shale wafers. These shale wafers were subjected to different WBDFs containing diverse inorganic salts such as sodium chloride (NaCl), potassium chloride (KCl), magnesium chloride (MgCl 2 ), and calcium chloride (CaCl 2 ). To gather sufficient data to train the ML models, an extensive experimental study was conducted using various WBDF formulations. The experiments were conducted on wafers, wherein each wafer treated with an inorganic salt underwent a linear swell test for 120 h until the swelling reached a plateau. Moreover, the conductivities and zeta potential of WBDFs, which were prepared using varying concentrations of salts, were recorded. Several ML techniques, namely gradient boosting, decision trees, adaptive gradient boosting (AdaBoost), K-nearest neighbors, random forest, extreme gradient boosting, and stacked generalized regression (SGR) were used to forecast shale swelling. The ML models were trained using input features such as salt types, salt concentrations, salt conductivities, salt zeta potential, and elapsed time. The results revealed that the SGR model outperformed other techniques by effectively predicting linear swelling in terms of coefficient of determination (R 2 ) above 0.95. The developed ML model offers an efficient approach to assess the maximum swelling potential of various WBDFs that can help in effectively mitigating the wellbore instability concerns by continuously evaluating the interaction between shale and the drilling fluid for drilling for extended reach or maximum contact wells.

show abstract

“…The ANN approach has also been used to characterize other properties of the drilling fluids (e.g., filtration properties [Jeirani and Mohebbi 2006]). Recent work has demonstrated shale swelling modeling based on the ANN approach ) as well as using other numerical models (Kulkarni et al 2012;.…”

Section: Introductionmentioning

confidence: 99%

Modeling of Shale-Erosion Behavior in Aqueous Drilling Fluids

Maghrabi

Kulkarni

Teke

et al. 2014

Day 1 Tue, February 25, 2014

Self Cite

View full text Add to dashboard Cite

Numerous shale-stability issues can occur while drilling with water-based muds (WBMs), including shale sloughing and cutting disintegration. These issues can be detrimental to the formation and pose difficulties with respect to rheology control, possibly reducing the rate of penetration (ROP). A "shale-erosion test" is a well-known laboratory test used to characterize the erosion of cuttings in WBMs.This paper documents a mathematical modeling tool known as an artificial neural network (ANN) used to model the erosion behavior of shale cutting in WBM. The ANN model establishes complex relationships between a set of inputs and an output based on computational modeling. For ANN modeling of shale-erosion behavior, the shale mineralogy and fluid composition constitute a set of inputs, while experimentally obtained "% erosion or % recovery" of the cuttings from the shale-erosion test represent the output.Experimental data for building the ANN model was obtained by performing approximately 150 standard shale-erosion tests using five different shales with varying mineralogy and WBMs with varying salt concentrations/types, shale stabilizers, and mud weights. For every test conducted, the input data (shale and fluid characteristics) and the output data (% recovery) was incorporated into the ANN model. The ANN model was then run to establish relationships between inputs and the output, which exhibited excellent correlation with R2 ≈ 0.85-0.90. The ANN model was successfully validated for an independent set of shale-fluid interactions.With the novel ANN model in place, erosion behavior of cuttings could be predicted in advance, thereby reducing the number of trials necessary in technical service labs. Mud engineers can use this model on a real-time basis as the shale chemistry varies with the depth of the formation drilling. The model could provide convenient measurement of fluid performance, enabling fluid optimization necessary to obtain desired shale behavior in advance, thereby minimizing drilling risks and costs associated with these oftentimes unpredictable shales.

show abstract

Mathematical Modeling of Shale Swelling in Water-Based Muds

Cited by 7 publications

References 6 publications

Neural-net Modeling of Shale-swelling Behavior in Aqueous Drilling Fluids

Neural-net Modeling of Shale-swelling Behavior in Aqueous Drilling Fluids

An Experimental Study and Machine Learning Modeling of Shale Swelling in Extended Reach Wells When Exposed to Diverse Water-Based Drilling Fluids

Modeling of Shale-Erosion Behavior in Aqueous Drilling Fluids

Contact Info

Product

Resources

About