Analysis of local head losses in microirrigation lateral connectors based on machine learning approaches

Abstract The presence of emitters along the lateral, as well connectors manifold, causes additional local head losses other than friction losses. An accurate estimation is crucial importance for a correct design microirrigation systems. This paper presents procedure to assess caused by 6 lateral start 32- and 40-mm nominal diameter each under actual hydraulic working conditions based on artificial neural networks (ANN) gene expression programming (GEP) modelling approaches. Different input–output combinations data partitions were assessed analyse performance system optimum training strategy models, respectively. range in manifold (hs M ) considerable lower L ). hs increases with protrusion ratio (s/S). does not decrease decreasing s/S. There correlation between Reynolds number (Re However, this might also be dependent flow before derivation. value loss component due influenced DN32 present more estimates. Crucial input parameters are velocity ratio. inclusion improves estimating accuracy models. indicators considerably worse DN40 DN32. models trained all patterns lead estimations 7 12 exclusively patterns. On hand, including process did involve any improvement connectors. ANN GEP In less , but they while both presented similar combined . equations obtained using easily estimate two components loss. equation that should used practice depends availability inputs.