Prediction of oil flow rate through orifice flow meters: Optimized machine-learning techniques

Flow measurement is an essential requirement for monitoring and controlling oil movements through pipelines facilities. However, delivering reliably accurate measurements 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 flow 40 plus processing facilities in southwestern Iran evaluated hybrid machine-learning-optimizer models predict wide range rates (Qo) orifice plate meters. Distance-weighted K-nearest-neighbor (DWKNN) multi-layer perceptron (MLP) algorithms are coupled artificial-bee colony (ABC) firefly (FF) swarm-type The two-stage ABC-DWKNN Plus MLP-FF model achieved the highest prediction accuracy (root mean square errors = 8.70 stock-tank barrels per day) rate plates, thereby removing dependence on unreliable empirical formulas such calculations.