Hybridized machine-learning for prompt prediction of rheology and filtration properties of water-based drilling fluids

Davoodi, Shadfar; Mehrad, Mohammad; Wood, David A.; Ghorbani, Hamzeh; Rukavishnikov, Valeriy S.

doi:10.1016/j.engappai.2023.106459

Cited by 27 publications

(3 citation statements)

References 67 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Generally, in classification problems with nonlinearly separable data, kernel functions are used to transform the data into a higher-dimensional feature space, enabling linear separation. In regression scenarios, kernelization is applied for nonlinear SVR [ 51 , 52 , 53 , 54 ]. Figure 3 shows the execution of an SVM classifier on a dataset containing two classes and two features (linear SVR).…”

Section: Methodsmentioning

confidence: 99%

A Developed Robust Model and Artificial Intelligence Techniques to Predict Drilling Fluid Density and Equivalent Circulation Density in Real Time

Al-Rubaii,

Al-Shargabi,

Aldahlawi

et al. 2023

Sensors

View full text Add to dashboard Cite

When drilling deep wells, it is important to regulate the formation pressure and prevent kicks. This is achieved by controlling the equivalent circulation density (ECD), which becomes crucial in high-pressure and high-temperature wells. ECD is particularly important in formations where the pore pressure and fracture pressure are close to each other (narrow windows). However, the current methods for measuring ECD using downhole sensors can be expensive and limited by operational constraints such as high pressure and temperature. Therefore, to overcome this challenge, two novel models named ECDeffc.m and MWeffc.m were developed to predict ECD and mud weight (MW) from surface-drilling parameters, including standpipe pressure, rate of penetration, drill string rotation, and mud properties. In addition, by utilizing an artificial neural network (ANN) and a support vector machine (SVM), ECD was estimated with a correlation coefficient of 0.9947 and an average absolute percentage error of 0.23%. Meanwhile, a decision tree (DT) was employed to estimate MW with a correlation coefficient of 0.9353 and an average absolute percentage error of 1.66%. The two novel models were compared with artificial intelligence (AI) techniques to evaluate the developed models. The results proved that the two novel models were more accurate with the value obtained from pressure-while-drilling (PWD) tools. These models can be utilized during well design and while drilling operations are in progress to evaluate and monitor the appropriate mud weight and equivalent circulation density to save time and money, by eliminating the need for expensive downhole equipment and commercial software.

show abstract

Section: Methodsmentioning

confidence: 99%

A Developed Robust Model and Artificial Intelligence Techniques to Predict Drilling Fluid Density and Equivalent Circulation Density in Real Time

Al-Rubaii,

Al-Shargabi,

Aldahlawi

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…In the same year, Afandi et al (2022) used Artificial Neural Network (ANN) model to predict probe temperature 31 . Davoodi and Vo Thanh (2023) proposed the LSSVM machine learning model for predicting the residual captive index of carbon dioxide solubility at global geologic sequestration sites, hydrogen uptake values of porous carbon materials, and combined machine learning with optimization to propose the LSSVM-COA model to improve the prediction accuracy while reducing the Associated uncertainties 32 – 34 ; Davoodi and Mehrad (2023) proposed hybrid machine learning for rapid prediction of rheological and filtration properties of water-based drilling fluids, achieving accurate and reliable prediction of filtration properties of drilling fluids and applying hybrid machine learning to assist in prediction of uniaxial compressive strength using drilling variables 35 , 36 .…”

Section: Introductionmentioning

confidence: 99%

Reservoir temperature prediction based on characterization of water chemistry data—case study of western Anatolia, Turkey

Shi,

Zhang,

et al. 2024

Sci Rep

View full text Add to dashboard Cite

Reservoir temperature estimation is crucial for geothermal studies, but traditional methods are complex and uncertain. To address this, we collected 83 sets of water chemistry and reservoir temperature data and applied four machine learning algorithms. These models considered various input factors and underwent data preprocessing steps like null value imputation, normalization, and Pearson coefficient calculation. Cross-validation addressed data volume issues, and performance metrics were used for model evaluation. The results revealed that our machine learning models outperformed traditional fluid geothermometers. All machine learning models surpassed traditional methods. The XGBoost model, based on the F-3 combination, demonstrated the best prediction accuracy with an R2 of 0.9732, while the Bayesian ridge regression model using the F-4 combination had the lowest performance with an R2 of 0.8302. This study highlights the potential of machine learning for accurate reservoir temperature prediction, offering geothermal professionals a reliable tool for model selection and advancing our understanding of geothermal resources.

show abstract

“…The combination of the cuckoo optimization algorithm with a multilayer extreme learning machine is used to predict the unexpected change in viscosity in drilling operations. This model predicts March funnel viscosity, plastic viscosity, yield point, filtrate volume, utilizing fluid density, and solid percentage …”

Section: Introductionmentioning

confidence: 99%

Enhancing Fracturing Fluid Viscosity in High Salinity Water: A Data-Driven Approach for Prediction and Optimization

Othman,

Tariq,

Aljawad

et al. 2023

Energy Fuels

View full text Add to dashboard Cite

Optimizing fracture fluid viscosity in a high salinity medium (i.e., seawater and produced water) is challenging. Hence, we conducted numerous rheology experiments utilizing an Anton Paar rheometer to generate viscosity data. We have experimented with different types and concentrations of polymers, crosslinkers, and chelating agents in different water salinities at different shear rates, temperatures, pressures, and mixing orders. After data cleaning, the study generated 645 data from 86 experiments, which were fed to the machine learning (ML) models such as fully connected neural networks (FCNN), gradient boosting (GB), adaptive gradient boosting (AdaBoost), extreme GB (XGB), random forest (RF), and decision trees (DT). The hyper-parameters of these models were optimized using a grid search optimization approach during the training phase. Additionally, the K-fold crossvalidation technique was utilized to enhance the models' performance of the ML. The performance of the ML models was assessed through various assessment tests, such as root mean square error (RMSE), coefficient of determination (R 2 ), average absolute percentage error (AAPE), and cross-plots. The outcomes of the predictions indicated that the feedforward neural network (FCNN) outperformed the DT, RF, GB, AdaBoost, and XGB models. These techniques yielded remarkably low error rates. With the optimal settings, the fracturing fluid viscosity was predicted with 95% accuracy. In addition, the fracturing fluid viscosity was maximized using the particle swarm optimization algorithm by optimizing the input parameters where the FCNN model was trained. The proposed methodology of predicting the fracturing fluid viscosity could minimize the experimental cost of measuring fracturing fluid rheology.

show abstract

Hybridized machine-learning for prompt prediction of rheology and filtration properties of water-based drilling fluids

Cited by 27 publications

References 67 publications

A Developed Robust Model and Artificial Intelligence Techniques to Predict Drilling Fluid Density and Equivalent Circulation Density in Real Time

A Developed Robust Model and Artificial Intelligence Techniques to Predict Drilling Fluid Density and Equivalent Circulation Density in Real Time

Reservoir temperature prediction based on characterization of water chemistry data—case study of western Anatolia, Turkey

Enhancing Fracturing Fluid Viscosity in High Salinity Water: A Data-Driven Approach for Prediction and Optimization

Contact Info

Product

Resources

About