Generalized correlation of refrigerant mass flow rate through adiabatic capillary tubes using artificial neural network

A capillary tube is a common expansion device widely used in small-scale refrigeration and air-conditioning systems. Generalized correlation method for refrigerant flow rate through adiabatic capillary tubes is developed by combining dimensional analysis and artificial neural network (ANN). Dimensional analysis is utilized to provide the generalized dimensionless parameters and reduce the number of input parameters, while a three-layer feedforward ANN is served as a universal approximator of the nonlinear multi-input and single-output function. For ANN training and test, measured data for R12, R134a, R22, R290, R407C, R410A, and R600a in the open literature are employed. The trained ANN with just one hidden neuron is good enough for the training data with average and standard deviations of 0.4 and 6.6%, respectively. By comparison, for two test data sets, the trained ANN gives two different results. It is well interpreted by evaluating the outlier with a homogeneous equilibrium model.