Development of an artificial neural network correlation for prediction of hold-up of slurry transport in pipelines

摘要: In the literature, very few correlations have been proposed for hold-up prediction in slurry pipelines. However, these fail to predict over a wide range of conditions. Based on databank around 220 measurements collected from open correlation was derived using artificial neural network (ANN) modeling. The found be function nine parameters such as solids concentration, particle dia, velocity, pressure drop and solid liquid properties. Statistical analysis showed that has an average absolute relative error (AARE) 2.5% standard deviation 3.0%. A comparison with selected literature developed ANN noticeably improved operating conditions, physical properties pipe diameters. This also predicts properly trend effect design hold-up.