TY - JOUR
T1 - Prediction of oil flow rate through orifice flow meters
T2 - Optimized machine-learning techniques
AU - Farsi, Mohammad
AU - Shojaei Barjouei, Hossein
AU - Wood, David A.
AU - Ghorbani, Hamzeh
AU - Mohamadian, Nima
AU - Davoodi, Shadfar
AU - Reza Nasriani, Hamid
AU - Ahmadi Alvar, Mehdi
N1 - Funding Information:
The authors are grateful to Ms. Kalaei for the technical support and effort in collecting the data needed for this study. This research was supported by Tomsk Polytechnic University under grant number VIU-CPPSND- 214/2020 .
Publisher Copyright:
© 2021 Elsevier Ltd
Copyright:
Copyright 2021 Elsevier B.V., All rights reserved.
PY - 2021/4
Y1 - 2021/4
N2 - Flow measurement is an essential requirement for monitoring and controlling oil movements through pipelines and facilities. However, delivering reliably accurate measurements through certain meters requires cumbersome calculations that can be simplified by using supervised machine learning techniques exploiting optimizers. In this study, a dataset of 6292 data records with seven input variables relating to oil flow through 40 pipelines plus processing facilities in southwestern Iran is evaluated with hybrid machine-learning-optimizer models to predict a wide range of oil flow rates (Qo) through orifice plate meters. Distance-weighted K-nearest-neighbor (DWKNN) and multi-layer perceptron (MLP) algorithms are coupled with artificial-bee colony (ABC) and firefly (FF) swarm-type optimizers. The two-stage ABC-DWKNN Plus MLP-FF model achieved the highest prediction accuracy (root mean square errors = 8.70 stock-tank barrels of oil per day) for oil flow rate through the orifice plates, thereby removing dependence on unreliable empirical formulas in such flow calculations.
AB - Flow measurement is an essential requirement for monitoring and controlling oil movements through pipelines and facilities. However, delivering reliably accurate measurements through certain meters requires cumbersome calculations that can be simplified by using supervised machine learning techniques exploiting optimizers. In this study, a dataset of 6292 data records with seven input variables relating to oil flow through 40 pipelines plus processing facilities in southwestern Iran is evaluated with hybrid machine-learning-optimizer models to predict a wide range of oil flow rates (Qo) through orifice plate meters. Distance-weighted K-nearest-neighbor (DWKNN) and multi-layer perceptron (MLP) algorithms are coupled with artificial-bee colony (ABC) and firefly (FF) swarm-type optimizers. The two-stage ABC-DWKNN Plus MLP-FF model achieved the highest prediction accuracy (root mean square errors = 8.70 stock-tank barrels of oil per day) for oil flow rate through the orifice plates, thereby removing dependence on unreliable empirical formulas in such flow calculations.
KW - Beta ratios
KW - Differential pressure
KW - Discharge coefficients
KW - Machine-learning-optimizer algorithms
KW - Oil flow rate measurement
KW - Optimized variable weights
KW - Orifice plate meters
UR - http://www.scopus.com/inward/record.url?scp=85099520192&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85099520192&partnerID=8YFLogxK
U2 - 10.1016/j.measurement.2020.108943
DO - 10.1016/j.measurement.2020.108943
M3 - Article
AN - SCOPUS:85099520192
VL - 174
JO - Industrial Metrology
JF - Industrial Metrology
SN - 1536-6367
M1 - 108943
ER -