An integrated intelligent approach to the determination of drilling fluids’ solid content; Colloids and Surfaces A: Physicochemical and Engineering Aspects; Vol. 707
| Parent link: | Colloids and Surfaces A: Physicochemical and Engineering Aspects.— .— Amsterdam: Elsevier Science Publishing Company Inc. Vol. 707.— 2025.— Article number 135906, 16 p. |
|---|---|
| Müşterek Yazar: | |
| Diğer Yazarlar: | , , , , |
| Özet: | Title screen Effective management of solid content in drilling fluids is crucial for minimizing operational challenges and ensuring high efficiency during drilling operations. Accurate and timely quantification of solid content remains a challenge due to the lengthy laboratory measurement techniques currently in use. As a result, existing solid content measurement methods lack real-time capabilities, hindering proactive monitoring of this parameter. This study develops integrated machine learning and optimization models to predict solid content based solely on two drilling fluid properties that can be quickly measured at the well site—fluid density and Marsh funnel viscosity. A dataset of 1290 records was compiled from drilling fluid compositions used in drilling 17 wells across various lithological formations in two fields in southwest Iran. The Least Squares Support Vector Machine and Radial Basis Function Neural Network models are integrated with Particle Swarm Optimization and Grey Wolf Optimizer to create efficient and rapid solid content prediction models. Six intelligent model configurations, including four hybrid machine learning-optimizer models, were trained and evaluated for their prediction and generalization performance. The hybrid models outperformed the standalone models, with the Least Squares Support Vector Machine-Grey Wolf Optimizer model achieving the lowest prediction error (root mean square error = 1.220 % with the testing dataset). Feature importance analysis reveals that fluid density has a more significant impact on solid content predictions than Marsh funnel viscosity. These novel two-variable hybrid models can be applied in well-site drilling fluid laboratories to enable frequent control and effective management of solid content during drilling operations Текстовый файл AM_Agreement |
| Dil: | İngilizce |
| Baskı/Yayın Bilgisi: |
2025
|
| Konular: | |
| Online Erişim: | https://doi.org/10.1016/j.colsurfa.2024.135906 |
| Materyal Türü: | Elektronik Kitap Bölümü |
| KOHA link: | https://koha.lib.tpu.ru/cgi-bin/koha/opac-detail.pl?biblionumber=678023 |
MARC
| LEADER | 00000naa0a2200000 4500 | ||
|---|---|---|---|
| 001 | 678023 | ||
| 005 | 20260728131503.0 | ||
| 090 | |a 678023 | ||
| 100 | |a 20250109d2025 k||y0rusy50 ba | ||
| 101 | 0 | |a eng | |
| 102 | |a NL | ||
| 135 | |a drcn ---uucaa | ||
| 181 | 0 | |a i |b e | |
| 182 | 0 | |a b | |
| 183 | 0 | |a cr |2 RDAcarrier | |
| 200 | 1 | |a An integrated intelligent approach to the determination of drilling fluids’ solid content |f Shadfar Davoodi, Evgeny Burnaev, 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: 62 tit | ||
| 330 | |a Effective management of solid content in drilling fluids is crucial for minimizing operational challenges and ensuring high efficiency during drilling operations. Accurate and timely quantification of solid content remains a challenge due to the lengthy laboratory measurement techniques currently in use. As a result, existing solid content measurement methods lack real-time capabilities, hindering proactive monitoring of this parameter. This study develops integrated machine learning and optimization models to predict solid content based solely on two drilling fluid properties that can be quickly measured at the well site—fluid density and Marsh funnel viscosity. A dataset of 1290 records was compiled from drilling fluid compositions used in drilling 17 wells across various lithological formations in two fields in southwest Iran. The Least Squares Support Vector Machine and Radial Basis Function Neural Network models are integrated with Particle Swarm Optimization and Grey Wolf Optimizer to create efficient and rapid solid content prediction models. Six intelligent model configurations, including four hybrid machine learning-optimizer models, were trained and evaluated for their prediction and generalization performance. The hybrid models outperformed the standalone models, with the Least Squares Support Vector Machine-Grey Wolf Optimizer model achieving the lowest prediction error (root mean square error = 1.220 % with the testing dataset). Feature importance analysis reveals that fluid density has a more significant impact on solid content predictions than Marsh funnel viscosity. These novel two-variable hybrid models can be applied in well-site drilling fluid laboratories to enable frequent control and effective management of solid content during drilling operations | ||
| 336 | |a Текстовый файл | ||
| 371 | 0 | |a AM_Agreement | |
| 461 | 1 | |t Colloids and Surfaces A: Physicochemical and Engineering Aspects |c Amsterdam |n Elsevier Science Publishing Company Inc. | |
| 463 | 1 | |t Vol. 707 |v Article number 135906, 16 p. |d 2025 | |
| 610 | 1 | |a Solid content monitoring | |
| 610 | 1 | |a Water-based drilling fluids | |
| 610 | 1 | |a Drilling issuesIntegrated modeling | |
| 610 | 1 | |a Least-square support vector machine | |
| 610 | 1 | |a Optimization | |
| 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 Burnaev |b E. |g Evgeny | |
| 701 | 1 | |a Wood |b D. A. |g David | |
| 701 | 1 | |a Al-Shargabi |b M. A. T. S. |c specialist in the field of petroleum engineering |c Engineer of Tomsk Polytechnic University |f 1993- |g Mokhammed Abdulsalam Takha Sallam |9 22768 | |
| 701 | 1 | |a Mehrad |b M. |g Mohammad | |
| 712 | 0 | 2 | |a Томский политехнический университет |c 1991- |9 26305 |4 570 |
| 801 | 0 | |a RU |b 63413507 |c 20250109 |g RCR | |
| 856 | 4 | |u https://doi.org/10.1016/j.colsurfa.2024.135906 |z https://doi.org/10.1016/j.colsurfa.2024.135906 | |
| 942 | |c CF | ||