Javascript must be enabled to continue!
Leveraging Machine Learning for Predicting Gas Separation Efficiency of a Downhole Separator
View through CrossRef
AbstractArtificial lift systems, specifically Electrical Submersible Pumps and Sucker Rod Pumps, often face operational challenges due to high Gas-Oil Ratio, leading to premature tool failure and increased non-productive time. These issues underscore the necessity for efficient gas separation at upstream of the artificial lift pump to ensure uninterrupted operations. Downhole gas separators, situated upstream of the artificial lift pump, are designed to segregate gas from the fluid, reducing downtime. This study aims to predict the gas separation efficiency of the downhole gas separator using experimental data from a centrifugal separator and testing the generated models on experimental data for a gravity separator.To predict the separation efficiency of the downhole separator, multiple machine learning models were evaluated, and a comparative analysis was performed. The experimental test data obtained for the centrifugal packer-type separator was used for model training and experimental test data for the gravity separator was used for model testing (blind test). To conduct experiments, multiphase flow setup (31ft. (9.4m) long horizontal and 27ft. (8.2m) tall vertical section of multiphase flow setup) was used. In this study, seven regression methods, including multilinear (MLR), random forest (RF), support vector machine (SVM), ridge, lasso, k-nearest neighbor (KNN) and XGBoost, were examined to assess their ability to effectively predict the gas separation efficiency. Several performance metrics, including Root mean square error (RMSE), Mean absolute percentage error (MAPE) and R-squared were evaluated to select the efficient model.In-depth exploratory data analysis and feature engineering were performed to identify significant input parameters for model training. The scatterplot and correlation plot indicated the response variable were mostly affected by inlet liquid and gas volume flow. Therefore, liquid and gas volume flow at inlet were selected as two independent parameters to predict gas volume flow per minute at the outlet (GVFO) as the response variable. After data scaling, a comparative analysis of the seven incorporated regression models revealed that, the Random Forest model to be the most efficient for predicting GVFO, closely followed by the KNN model. The Random Forest model exhibits R-squared values of 96% and RMSE value of 112. Hyperparameter tuning and tenfold cross-validation ensured optimal values for tuning parameters and prevented oveffitting, respectively.This developed machine learning workflow enables the prediction of the gas separation efficiency of different type of downhole gas separator by using experimental test data from a centrifugal downhole separator. It provides critical findings through a comparative analysis of seven regression models. This research offers valuable insights that can aid in optimizing the performance of artificial lift systems.
Title: Leveraging Machine Learning for Predicting Gas Separation Efficiency of a Downhole Separator
Description:
AbstractArtificial lift systems, specifically Electrical Submersible Pumps and Sucker Rod Pumps, often face operational challenges due to high Gas-Oil Ratio, leading to premature tool failure and increased non-productive time.
These issues underscore the necessity for efficient gas separation at upstream of the artificial lift pump to ensure uninterrupted operations.
Downhole gas separators, situated upstream of the artificial lift pump, are designed to segregate gas from the fluid, reducing downtime.
This study aims to predict the gas separation efficiency of the downhole gas separator using experimental data from a centrifugal separator and testing the generated models on experimental data for a gravity separator.
To predict the separation efficiency of the downhole separator, multiple machine learning models were evaluated, and a comparative analysis was performed.
The experimental test data obtained for the centrifugal packer-type separator was used for model training and experimental test data for the gravity separator was used for model testing (blind test).
To conduct experiments, multiphase flow setup (31ft.
(9.
4m) long horizontal and 27ft.
(8.
2m) tall vertical section of multiphase flow setup) was used.
In this study, seven regression methods, including multilinear (MLR), random forest (RF), support vector machine (SVM), ridge, lasso, k-nearest neighbor (KNN) and XGBoost, were examined to assess their ability to effectively predict the gas separation efficiency.
Several performance metrics, including Root mean square error (RMSE), Mean absolute percentage error (MAPE) and R-squared were evaluated to select the efficient model.
In-depth exploratory data analysis and feature engineering were performed to identify significant input parameters for model training.
The scatterplot and correlation plot indicated the response variable were mostly affected by inlet liquid and gas volume flow.
Therefore, liquid and gas volume flow at inlet were selected as two independent parameters to predict gas volume flow per minute at the outlet (GVFO) as the response variable.
After data scaling, a comparative analysis of the seven incorporated regression models revealed that, the Random Forest model to be the most efficient for predicting GVFO, closely followed by the KNN model.
The Random Forest model exhibits R-squared values of 96% and RMSE value of 112.
Hyperparameter tuning and tenfold cross-validation ensured optimal values for tuning parameters and prevented oveffitting, respectively.
This developed machine learning workflow enables the prediction of the gas separation efficiency of different type of downhole gas separator by using experimental test data from a centrifugal downhole separator.
It provides critical findings through a comparative analysis of seven regression models.
This research offers valuable insights that can aid in optimizing the performance of artificial lift systems.
Related Results
The Hot Test of Primary Separation Equipment of Steam Generator for CAP1400 Nuclear Power Plant
The Hot Test of Primary Separation Equipment of Steam Generator for CAP1400 Nuclear Power Plant
A new type of Steam separator for CAP1400 Steam Generator is introduced. The result of characteristic experiment, the variables of which contain steam load, saturated water flow an...
Downhole Gas Separation and Injection Powered by a Downhole Turbo Expander
Downhole Gas Separation and Injection Powered by a Downhole Turbo Expander
Abstract
A downhole gas compressor and turbine expander are being developed to inject excess gas into North Slope fields. North Slope oil fields and some oil and con...
Smart Facility Advanced Separator
Smart Facility Advanced Separator
Abstract
The objective of this work was to develop the prototype unit of Advanced Production Separator (APS) for simultaneous removal of sand, out from production se...
Quantifying Separator Oil Shrinkage
Quantifying Separator Oil Shrinkage
In tight unconventionals, oil and gas rates are often measured daily at separator conditions. Consequently, it is necessary to reliably convert these rates to volumes at standard c...
Troll Pilot Control System: Advanced Control System for a Subsea Separator
Troll Pilot Control System: Advanced Control System for a Subsea Separator
ABSTRACT
This paper describes the design of a subsea control system for control and monitoring of a subsea water separator, for use by Norsk Hydro in the Troll fi...
REDUCTION OF THE AMOUNT OF CONDENSATE ENTERING THE COMPRESSOR BY IMPLEMENTING DESIGN MODIFICATIONS IN THE GAS COMPRESSOR SEPARATOR
REDUCTION OF THE AMOUNT OF CONDENSATE ENTERING THE COMPRESSOR BY IMPLEMENTING DESIGN MODIFICATIONS IN THE GAS COMPRESSOR SEPARATOR
Reliable and long-term operation of gas compressors largely depends on the effective prevention of liquid phase ingress, particularly condensate, into the compressor flow path. Liq...
Numerical Simulation on Steam-Water Separator Performance Based on Population Balance Model
Numerical Simulation on Steam-Water Separator Performance Based on Population Balance Model
The performance of the moisture separator is simulated and analyzed by the Euler two fluid model with population balance model (PBM), and compared with the traditional single drop ...
Study on Non-Contact Connection Separated Layer Production Technology and Its Application Test
Study on Non-Contact Connection Separated Layer Production Technology and Its Application Test
Abstract
Separated layer production is an effective means to mitigate inter-layer problems, minimize invalid water circulation and improve oilfield production effici...

