The determination of thermophysical properties of hydrofluorocarbons (HFC S) isvery important,especially the thermal conductivity. The present work, investigated the potential of an artificial neural network (ANN) model to correlate the thermal conductivity of (HFC S) at (169.87-533.02) K, (0.047-68.201) MPa and (0.0089-0.1984) W.m.-1 K-1 temperature, pressure and thermal conductivity ranges respectively, of 11systems from 3 different categories including five pure systems(R32, R125, R134a,R152a,R143a),four binary mixtures systems(R32+R125, R32+R134a, R125+ R134a,R125+R143a), and two ternary mixtures systems (R32+R125+ R134a, R125+ R134a+ R143a).Each one received 1817,794and 616 data points, respectively.The application of this model forthese3227 data points of liquid and vapor at several temperatures and pressures allowed to train, validate and test the model. This A c c e p t e d M a n u s c r i p t 2 study showed that ANN models represent a good alternative to estimate the thermal conductivity of different refrigerant systems with a good accuracy. The squared correlation coefficients of thermal conductivity predicted by ANN were R 2 = 0.998with an acceptable level of accuracy of RMSE = 0.0035 and AAD= 0.002 %.The results of applying the trained neural network model to the test data indicate that the method has a highly significant prediction capability.