Machine-Learning Predictive Model for Semiautomated Monitoring of Solid Content in Water-Based Drilling Fluids; Arabian Journal for Science and Engineering; Vol. 50, no. 7

Бібліографічні деталі
Parent link:Arabian Journal for Science and Engineering.— .— Berlin: Springer Nature
Vol. 50, no. 7.— 2025.— P. 5175–5194
Співавтор: National Research Tomsk Polytechnic University (570)
Інші автори: Davoodi Sh. Shadfar, Muravyov (Murav’ev) S. V. Sergey Vasilyevich, Wood D. A. David, Mehrad M. Mohammad, Rukavishnikov V. S. Valery Sergeevich
Резюме:Title screen
Accurate and frequent monitoring of the solid content (SC) of drilling fluids is necessary to avoid the issues associated with improper solid particle concentrations. Conventional methods for determining SC, such as retort analysis, lack immediacy and are labor-intensive. This study applies machine learning (ML) techniques to develop SC predictive models using readily available data—Marsh funnel viscosity and fluid density. A dataset of 1290 data records was collected from 17 wells drilled in two oil fields located in southwest Iran. Four ML models—least squares support vector machine (LSSVM), multilayered perceptron neural network, extreme learning machine, and generalized regression neural network—were developed to predict SC from the compiled dataset. Multiple assessment techniques were applied to attentively evaluate the models’ prediction performances and select the best-performing, SC prediction model. The LSSVM model generated the least errors, exhibiting the lowest root-mean-square error values for the training (1.80%) and testing (1.84%) subsets. The narrowest confidence interval, 0.18, achieved by the LSSVM model confirmed its reliability for SC prediction. Leverage analysis revealed minimal influence of outlier data on the LSSVM model's SC prediction performance. The trained LSSVM model was further validated on unseen data from another well drilled in one of the studied oil fields, demonstrating the model’s generalizability for providing credible close-to-real-time SC predictions in the studied fields
Текстовый файл
AM_Agreement
Мова:Англійська
Опубліковано: 2025
Предмети:
Онлайн доступ:https://doi.org/10.1007/s13369-024-09689-w
Формат: MixedMaterials Електронний ресурс Частина з книги
KOHA link:https://koha.lib.tpu.ru/cgi-bin/koha/opac-detail.pl?biblionumber=676984

MARC

LEADER 00000naa0a2200000 4500
001 676984
005 20250917090848.0
090 |a 676984 
100 |a 20241127a2025 k||y0rusy50 ba 
101 0 |a eng 
102 |a DE 
135 |a drcn ---uucaa 
181 0 |a i   |b  e  
182 0 |a b 
183 0 |a cr  |2 RDAcarrier 
200 1 |a Machine-Learning Predictive Model for Semiautomated Monitoring of Solid Content in Water-Based Drilling Fluids  |f Shadfar Davoodi, Sergey V. Muravyov, David A. Wood [et al.] 
203 |a Текст  |c электронный  |b визуальный 
283 |a online_resource  |2 RDAcarrier 
300 |a Title screen 
320 |a References: 102 tit 
330 |a Accurate and frequent monitoring of the solid content (SC) of drilling fluids is necessary to avoid the issues associated with improper solid particle concentrations. Conventional methods for determining SC, such as retort analysis, lack immediacy and are labor-intensive. This study applies machine learning (ML) techniques to develop SC predictive models using readily available data—Marsh funnel viscosity and fluid density. A dataset of 1290 data records was collected from 17 wells drilled in two oil fields located in southwest Iran. Four ML models—least squares support vector machine (LSSVM), multilayered perceptron neural network, extreme learning machine, and generalized regression neural network—were developed to predict SC from the compiled dataset. Multiple assessment techniques were applied to attentively evaluate the models’ prediction performances and select the best-performing, SC prediction model. The LSSVM model generated the least errors, exhibiting the lowest root-mean-square error values for the training (1.80%) and testing (1.84%) subsets. The narrowest confidence interval, 0.18, achieved by the LSSVM model confirmed its reliability for SC prediction. Leverage analysis revealed minimal influence of outlier data on the LSSVM model's SC prediction performance. The trained LSSVM model was further validated on unseen data from another well drilled in one of the studied oil fields, demonstrating the model’s generalizability for providing credible close-to-real-time SC predictions in the studied fields 
336 |a Текстовый файл 
371 0 |a AM_Agreement 
461 1 |t Arabian Journal for Science and Engineering  |c Berlin  |n Springer Nature 
463 1 |t Vol. 50, no. 7  |v P. 5175–5194  |d 2025 
610 1 |a Drilling fluid 
610 1 |a Least-squares support vector machine 
610 1 |a Semi-automated monitoring 
610 1 |a Machine learning modeling 
610 1 |a Solid content 
610 1 |a электронный ресурс 
610 1 |a труды учёных ТПУ 
701 1 |a Davoodi  |b Sh.  |c specialist in the field of petroleum engineering  |c Research Engineer of Tomsk Polytechnic University  |f 1990-  |g Shadfar  |9 22200 
701 1 |a Muravyov (Murav’ev)  |b S. V.  |c specialist in the field of control and measurement equipment  |c Professor of Tomsk Polytechnic University,Doctor of technical sciences  |f 1954-  |g Sergey Vasilyevich  |9 15440 
701 1 |a Wood  |b D. A.  |g David 
701 1 |a Mehrad  |b M.  |g Mohammad 
701 1 |a Rukavishnikov  |b V. S.  |c Director of the Center for Training and Retraining of Oil and Gas Specialists, Associate Professor of Tomsk Polytechnic University, Candidate of Technical Sciences  |c Engineer of Tomsk Polytechnic University  |f 1984-  |g Valery Sergeevich  |9 17614 
712 0 2 |a National Research Tomsk Polytechnic University  |c (2009- )  |9 27197  |4 570 
801 0 |a RU  |b 63413507  |c 20241127  |g RCR 
856 4 |u https://doi.org/10.1007/s13369-024-09689-w  |z https://doi.org/10.1007/s13369-024-09689-w 
942 |c CF