Predicting water-based drilling fluid filtrate volume in close to real time from routine fluid property measurements; Petroleum; Vol. 11, iss. 2

Predicting water-based drilling fluid filtrate volume in close to real time from routine fluid property measurements; Petroleum; Vol. 11, iss. 2

Xehetasun bibliografikoak
Parent link:Petroleum.— .— Amsterdam: Elsevier Science Publishing Company Inc.
Vol. 11, iss. 2.— 2025.— P. 174-187
Beste egile batzuk: Davoodi Sh. Shadfar, Ba Gery M. Mohammed, Wood D. A. David, Al-Shargabi M. A. T. S. Mokhammed Abdulsalam Takha Sallam, Mehrad M. Mohammad, Soleimanian A. Alireza
Gaia:Title screen
Drilling operations depend on precisely controlling drilling fluid filtration volume (FV), which affects formation integrity, costs, and borehole stability. Maintaining optimal FV is essential to prevent well control issues, yet forecasting it is challenging due to process complexity and measurement limitations. This study adapts machine and deep learning (ML/DL) models to predict FV in almost real-time based on more easily measured fluid properties. Radial-basis-function neural network (RBFNN), generalized regression neural network (GRNN), multilayer perceptron (MLP), convolutional neural network (CNN), and Gaussian process regression (GPR) ML models are applied to 1186 records of density, viscosity, and solids content in water-based drilling fluids deployed in fourteen wellbores. CNN outperformed other models with the lowest root mean square error (RMSE) of 0.5381 mL and demonstrated resilience to overfitting and noisy data, unlike RBFNN and GRNN. The proposed method provides reliable near-real-time FV predictions, which could be beneficial in optimizing drilling operations by helping prevent potential drilling-fluid-related issues. Fast and accurate FV forecasting from routine fluid properties represents a crucial advancement for drilling operations, highlighting the need for future dataset expansion to encompass a wider range of conditions and fluid types
Текстовый файл
Hizkuntza:ingelesa
Argitaratua: 2025
Gaiak:
электронный ресурс
труды учёных ТПУ
Water-based drilling fluid
Near-real-time filtration estimation
Key fluid properties
Predictive machine-learning model
Convolutional neural network (CNN)
Sarrera elektronikoa:https://doi.org/10.1016/j.petlm.2025.03.002
Formatua: Baliabide elektronikoa Liburu kapitulua
KOHA link:https://koha.lib.tpu.ru/cgi-bin/koha/opac-detail.pl?biblionumber=680038

Antzeko izenburuak

Antzeko izenburuak