PREDICTION OF LIQUID VISCOSITY OF PURE ORGANIC COMPOUNDS VIA ARTIFICIAL NEURAL NETWORKS
Ibrahim Sami Nashawi, Ahmed A. Elgibaly · Petroleum Science and Technology · 1999
Neural network models have been developed to estimate liquid viscosity of pure organic compounds at ambient temperature. These models employ different descriptors as characterizing parameters of the compounds. Three judgement criteria were imposed upon the proposed models: the accuracy of the obtained results, the type and number of the descriptors used as input parameters. The relative importance of the input variables was assessed. In all the cases analyzed, easily accessible properties of the organic compounds have been chosen as input parameters to train the neural network models. The number of the input properties was limited to a minimum without sacrificing the accuracy of the results A set of 110 data points covering a wide variety of organic compounds with a viscosity range of 0.197-19.9 mPa.s was employed in training the neural network models. The validity of the models was tested using 35 data points that were not included in the training set. The obtained results were compared with predictions from various published models. The neural network models have the advantage of providing accurate results for a wide spectrum of structures of organic compounds using readily available physicochemical properties.