Projecting Petrophysical Logs at the Bit through Multi-Well Data Analysis with Machine Learning
A. Sharma,
T. Burak,
R. Nygaard
et al.
Abstract:The vertical distance from logging while drilling (LWD) sensors to the bit is often more than 30m (98 ft), which leads to difficulty in performing real-time comparison of LWD and drilling data. This study aims to predict the petrophysical data at the drill bit with the objective of determining the best supervised machine learning algorithm to incorporate to reduce the sensor offset problem. The bulk density and porosity logs are predicted at the bit in this paper using petrophysical and drilling parameters. Th… Show more
“…The workflow is visually represented in Figure 3, which illustrates the comprehensive steps involved: data collection, data processing, model training and testing, followed by efficient model selection. The comparative analysis of all regression models is performed based on the R-squared and error metrics as mentioned in [19][20][21] for efficient model selection.…”
Artificial lift systems, such as electrical submersible pumps and sucker rod pumps, frequently encounter operational challenges due to high gas–oil ratios, leading to premature tool failure and increased downtime. Effective upstream gas separation is critical to maintain continuous operation. This study aims to predict the efficiency of downhole gas separator using machine learning models trained on data from a centrifugal separator and tested on data from a gravity separator (blind test). A comprehensive experimental setup included a multiphase flow system with horizontal (31 ft. (9.4 m)) and vertical (27 ft. (8.2 m)) sections to facilitate the tests. Seven regression models—multilinear regression, random forest, support vector machine, ridge, lasso, k-nearest neighbor, and XGBoost—were evaluated using performance metrics like RMSE, MAPE, and R-squared. In-depth exploratory data analysis and data preprocessing identified inlet liquid and gas volume flows as key predictors for gas volume flow per minute at the outlet (GVFO). Among the models, random forest was most effective, exhibiting an R-squared of 96% and an RMSE of 112. This model, followed by KNN, showed great promise in accurately predicting gas separation efficiency, aided by rigorous hyperparameter tuning and cross-validation to prevent overfitting. This research offers a robust machine learning workflow for predicting gas separation efficiency across different types of downhole gas separators, providing valuable insights for optimizing the performance of artificial lift systems.
“…The workflow is visually represented in Figure 3, which illustrates the comprehensive steps involved: data collection, data processing, model training and testing, followed by efficient model selection. The comparative analysis of all regression models is performed based on the R-squared and error metrics as mentioned in [19][20][21] for efficient model selection.…”
Artificial lift systems, such as electrical submersible pumps and sucker rod pumps, frequently encounter operational challenges due to high gas–oil ratios, leading to premature tool failure and increased downtime. Effective upstream gas separation is critical to maintain continuous operation. This study aims to predict the efficiency of downhole gas separator using machine learning models trained on data from a centrifugal separator and tested on data from a gravity separator (blind test). A comprehensive experimental setup included a multiphase flow system with horizontal (31 ft. (9.4 m)) and vertical (27 ft. (8.2 m)) sections to facilitate the tests. Seven regression models—multilinear regression, random forest, support vector machine, ridge, lasso, k-nearest neighbor, and XGBoost—were evaluated using performance metrics like RMSE, MAPE, and R-squared. In-depth exploratory data analysis and data preprocessing identified inlet liquid and gas volume flows as key predictors for gas volume flow per minute at the outlet (GVFO). Among the models, random forest was most effective, exhibiting an R-squared of 96% and an RMSE of 112. This model, followed by KNN, showed great promise in accurately predicting gas separation efficiency, aided by rigorous hyperparameter tuning and cross-validation to prevent overfitting. This research offers a robust machine learning workflow for predicting gas separation efficiency across different types of downhole gas separators, providing valuable insights for optimizing the performance of artificial lift systems.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.