A robust predictive technique for the pressure drop during condensation in inclined smooth tubes

摘要: Abstract The pressure drop during condensation in inclined tubes at different saturation temperatures is one of the most important design parameters many applications. Due to need huge investments for providing a highly equipped laboratory and difficulties data collection over challenging situations, developing high performance predictive model helpful optimize condensers with lower pumping costs as result accurate estimation drops. In this communication, potential four universal intelligent models, particle swam optimization-artificial neural network (PSO-ANN), genetic algorithm-least square support vector machine (GA-LSSVM), hybrid approach-adaptive neuro fuzzy inference system (Hybrid-ANFIS), algorithm-power law committee systems (GA-PLCIS) are evaluated precise estimating (ΔP) frictional (ΔPfric). comparative results demonstrated that developed GA-LSSVM, Hybrid-ANFIS, GA-PLCIS models could be implemented establish favorable predictions application interest. Nevertheless, by combining merits single indicate higher introducing R2 = 0.9990752581, MSE = 0.0140, RRMSE = 2.4983 ΔP R2 = 0.9990960793, MSE = 0.0126, RRMSE = 2.2414 ΔPfric. Based on results, can taken into account practical easy-to-use accuracy predicting performance, which engineers monitor under conditions, even situations such low mass fluxes qualities.