Prediction of Oil Flow Rate Through Orifice Flow Meters: Optimized Machine-Learning Techniques

Abstract

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.