Application of machine learning to determine the shear stress and filtration loss properties of nano-based drilling fluid

Publikationen: Beitrag in FachzeitschriftArtikelForschung(peer-reviewed)

Standard

Application of machine learning to determine the shear stress and filtration loss properties of nano-based drilling fluid. / Cai Ning, Yee; Ridha, Syahrir ; Umer Ilyas, Suhaib et al.
in: Journal of Petroleum Exploration and Production Technology, Jahrgang 13.2023, Nr. April, 04.2023, S. 1031-1052.

Publikationen: Beitrag in FachzeitschriftArtikelForschung(peer-reviewed)

Vancouver

Cai Ning Y, Ridha S, Umer Ilyas S, Krishna S, Dzulkarnain I, Abdurraham M. Application of machine learning to determine the shear stress and filtration loss properties of nano-based drilling fluid. Journal of Petroleum Exploration and Production Technology. 2023 Apr;13.2023(April):1031-1052. Epub 2022 Dez 16. doi: 10.1007/s13202-022-01589-9

Author

Bibtex - Download

@article{41443bca09bd4aad9a8e1083d85f1abc,
title = "Application of machine learning to determine the shear stress and filtration loss properties of nano-based drilling fluid",
abstract = "A detailed understanding of the drilling fluid rheology and filtration properties is essential to assuring reduced fluid loss during the transport process. As per literature review, silica nanoparticle is an exceptional additive to enhance drilling fluid rheology and filtration properties enhancement. However, a correlation based on nano-SiO2-water-based drilling fluid that can quantify the rheology and filtration properties of nanofluids is not available. Thus, two data-driven machine learning approaches are proposed for prediction, i.e. artificial-neural-network and least-square-support-vector-machine (LSSVM). Parameters involved for the prediction of shear stress are SiO2 concentration, temperature, and shear rate, whereas SiO2 nanoparticle concentration, temperature, and time are the inputs to simulate filtration volume. A feed-forward multilayer perceptron is constructed and optimised using the Levenberg–Marquardt learning algorithm. The parameters for the LSSVM are optimised using Couple Simulated Annealing. The performance of each model is evaluated based on several statistical parameters. The predicted results achieved R2 (coefficient of determination) value higher than 0.99 and MAE (mean absolute error) and MAPE (mean absolute percentage error) value below 7% for both the models. The developed models are further validated with experimental data that reveals an excellent agreement between predicted and experimental data.",
author = "{Cai Ning}, Yee and Syahrir Ridha and {Umer Ilyas}, Suhaib and Shwetank Krishna and Iskandar Dzulkarnain and Muslim Abdurraham",
note = "Publisher Copyright: {\textcopyright} 2022, The Author(s).",
year = "2023",
month = apr,
doi = "10.1007/s13202-022-01589-9",
language = "English",
volume = "13.2023",
pages = "1031--1052",
journal = "Journal of Petroleum Exploration and Production Technology",
issn = "2190-0558",
publisher = "Springer Heidelberg",
number = "April",

}

RIS (suitable for import to EndNote) - Download

TY - JOUR

T1 - Application of machine learning to determine the shear stress and filtration loss properties of nano-based drilling fluid

AU - Cai Ning, Yee

AU - Ridha, Syahrir

AU - Umer Ilyas, Suhaib

AU - Krishna, Shwetank

AU - Dzulkarnain, Iskandar

AU - Abdurraham, Muslim

N1 - Publisher Copyright: © 2022, The Author(s).

PY - 2023/4

Y1 - 2023/4

N2 - A detailed understanding of the drilling fluid rheology and filtration properties is essential to assuring reduced fluid loss during the transport process. As per literature review, silica nanoparticle is an exceptional additive to enhance drilling fluid rheology and filtration properties enhancement. However, a correlation based on nano-SiO2-water-based drilling fluid that can quantify the rheology and filtration properties of nanofluids is not available. Thus, two data-driven machine learning approaches are proposed for prediction, i.e. artificial-neural-network and least-square-support-vector-machine (LSSVM). Parameters involved for the prediction of shear stress are SiO2 concentration, temperature, and shear rate, whereas SiO2 nanoparticle concentration, temperature, and time are the inputs to simulate filtration volume. A feed-forward multilayer perceptron is constructed and optimised using the Levenberg–Marquardt learning algorithm. The parameters for the LSSVM are optimised using Couple Simulated Annealing. The performance of each model is evaluated based on several statistical parameters. The predicted results achieved R2 (coefficient of determination) value higher than 0.99 and MAE (mean absolute error) and MAPE (mean absolute percentage error) value below 7% for both the models. The developed models are further validated with experimental data that reveals an excellent agreement between predicted and experimental data.

AB - A detailed understanding of the drilling fluid rheology and filtration properties is essential to assuring reduced fluid loss during the transport process. As per literature review, silica nanoparticle is an exceptional additive to enhance drilling fluid rheology and filtration properties enhancement. However, a correlation based on nano-SiO2-water-based drilling fluid that can quantify the rheology and filtration properties of nanofluids is not available. Thus, two data-driven machine learning approaches are proposed for prediction, i.e. artificial-neural-network and least-square-support-vector-machine (LSSVM). Parameters involved for the prediction of shear stress are SiO2 concentration, temperature, and shear rate, whereas SiO2 nanoparticle concentration, temperature, and time are the inputs to simulate filtration volume. A feed-forward multilayer perceptron is constructed and optimised using the Levenberg–Marquardt learning algorithm. The parameters for the LSSVM are optimised using Couple Simulated Annealing. The performance of each model is evaluated based on several statistical parameters. The predicted results achieved R2 (coefficient of determination) value higher than 0.99 and MAE (mean absolute error) and MAPE (mean absolute percentage error) value below 7% for both the models. The developed models are further validated with experimental data that reveals an excellent agreement between predicted and experimental data.

UR - http://www.scopus.com/inward/record.url?scp=85144155278&partnerID=8YFLogxK

U2 - 10.1007/s13202-022-01589-9

DO - 10.1007/s13202-022-01589-9

M3 - Article

VL - 13.2023

SP - 1031

EP - 1052

JO - Journal of Petroleum Exploration and Production Technology

JF - Journal of Petroleum Exploration and Production Technology

SN - 2190-0558

IS - April

ER -