Estimation of asphaltene adsorption on MgO nanoparticles using ensemble learning

Ali, Syed Imran; Haneef, Javed; Ahsan, Usama; Khan, Muhammad Arqam; Yousaf, Nimra

doi:10.1016/j.chemolab.2020.104220

Cited by 23 publications

(6 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The value of MAE, MSE and RMSE has been computed using Eqs. (5) to ( 7), ( 4) where N is the number of data points, y i is the calculated value and ŷ i is the experimental value (Ali et al 2021).…”

Section: Performance Evaluation Of Proposed Scaling Swelling Equationmentioning

confidence: 99%

“…First a cross-plot is generated, which shows the relationship between the predicted values and the actual values. This plot comprises of a unit slope line that is established as a perfect model line (Ali et al 2021). The accuracy of the predicted model can be determined if a higher percentage of the data points fall on to this perfect model line.…”

Section: Performance Evaluation Of Proposed Scaling Swelling Equationmentioning

confidence: 99%

See 1 more Smart Citation

A novel technique for the modeling of shale swelling behavior in water-based drilling fluids

Lalji

Ali

Zahoor

et al. 2021

J Petrol Explor Prod Technol

Self Cite

View full text Add to dashboard Cite

One of the most significant problems in oil and gas sector is the swelling of shale when it comes in contact with water. The migration of hydrogen ions (H+) from the water-based drilling fluid into the platelets of shale formation causes it to swell, which eventually increases the size of the shale sample and makes it structure weak. This contact results in the wellbore instability problem that ultimately reduces the integrity of a wellbore. In this study, the swelling of a shale formation was modeled using the potential of first order kinetic equation. Later, to minimize its shortcoming, a new proposed model was formulated. The new model is based on developing a third degree polynomial equation that is used to model the swelling percentages obtained through linear dynamic swell meter experiment performed on a shale formation when it comes in contact with a drilling fluid. These percentages indicate the hourly change in sample size during the contact. The variables of polynomial equation are dependent on the time of contact between the mud and the shale sample, temperature of the environment, clay content in shale and experimental swelling percentages. Furthermore, the equation also comprises of adjustable parameters that are fine-tuned in such a way that the polynomial function is best fitted to the experimental datasets. The MAE (mean absolute error) of the present model, namely Scaling swelling equation was found to be 2.75%, and the results indicate that the Scaling Swelling equation has the better performance than the first order kinetics in terms of swelling predication. Moreover, the proposed model equation is also helpful in predicting the swelling onset time when the mud and shale comes in direct contact with each other. In both the cases, the percentage deviation in predicting the swelling initiation time is close to 10%. This information will be extremely helpful in forecasting the swelling tendency of shale sample in a particular mud. Also, it helps in validating the experimental results obtained from linear dynamic swell meter.

show abstract

Section: Performance Evaluation Of Proposed Scaling Swelling Equationmentioning

confidence: 99%

Section: Performance Evaluation Of Proposed Scaling Swelling Equationmentioning

confidence: 99%

A novel technique for the modeling of shale swelling behavior in water-based drilling fluids

Lalji

Ali

Zahoor

et al. 2021

J Petrol Explor Prod Technol

Self Cite

View full text Add to dashboard Cite

show abstract

“…In recent years, significant advances in computational processing have provided a wide range of robust ML algorithms to design predictive models and to make accurate predictions for distinct physicochemical properties of materials, particularly the asphaltene adsorption capability of different sorbents. [28,[53][54][55][56][57] Some studies are reported in the literature that focus on asphaltene deposition or adsorption. [58][59][60] Nevertheless, to the best of our knowledge, using ML techniques to predict asphaltene adsorption onto clay minerals has not been the focus of previous research, specifically.…”

Section: Introductionmentioning

confidence: 99%

“…Different solid surfaces or so‐called sorbents, including metals (e.g., iron [ 23,24 ] ), clay minerals (e.g., kaolinite [ 25,26 ] ), nanoparticles (e.g., metal oxides [ 27,28 ] ), and minerals (e.g., quartz [ 29–31 ] ) have been the centre of attention to assess their asphaltene adsorption capacity. Nevertheless, among all the reported surfaces, it is important to assess the adsorption capabilities of clay minerals from the perspective of petroleum engineering or material design for ground remediation implications.…”

Section: Introductionmentioning

confidence: 99%

“…Experimental research is costly, time‐consuming, and technically challenging. [ 28 ] Introducing alternative techniques for the estimation of the adsorption capacity of clay minerals is crucial considering the limitations of common types of adsorption isotherms, including Langmuir and Freundlich. In more detail, the Freundlich isotherm equation lacks theoretical background and can be used only for low‐pressure thermodynamic conditions.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Prediction of asphaltene adsorption capacity of clay minerals using machine learning

et al. 2022

View full text Add to dashboard Cite

A thorough understanding of asphaltene adsorption on clay minerals is particularly important in oil production and contaminated soil remediation using claybased adsorbents. In this paper, we introduced a machine learning approach as a reliable alternative for commonly used adsorption isotherms that suffer from inherent limitations in the prediction of asphaltene adsorption onto clay minerals. Machine learning (ML) models, namely multilayer perceptron (MLP), support vector machine (SVM), decision tree (DT), random forest (RF), and committee machine intelligent system (CMIS) combined with two optimizers were used. Experimental data (142 data points for six different clay minerals) was used for the modelling. To improve the accuracy of the smart models, a comprehensive data preparation such as outlier removal and feature selection was carried out. The results showed that relatively all the proposed models predict asphaltene adsorption on clay minerals with acceptable precision. Nevertheless, the MLP model showed superior performance compared with other models in which the overall root mean square error (RMSE) and coefficient of determination (R 2 ) values of 6.72 and 0.93 were obtained, respectively. Finally, the developed MLP model was compared with the well-known adsorption isotherms of Langmuir and Freundlich and exhibited superior performance.

show abstract

Machine Learning in Asphaltenes Mitigation

Qasim

Lal

2023

Machine Learning and Flow Assurance in Oil and Gas Production

View full text Add to dashboard Cite

Estimation of asphaltene adsorption on MgO nanoparticles using ensemble learning

Cited by 23 publications

References 47 publications

A novel technique for the modeling of shale swelling behavior in water-based drilling fluids

A novel technique for the modeling of shale swelling behavior in water-based drilling fluids

Prediction of asphaltene adsorption capacity of clay minerals using machine learning

Machine Learning in Asphaltenes Mitigation

Contact Info

Product

Resources

About