In this paper, two artificial neural network (ANN) models for simulation of an industrial catalytic-reforming unit (CRU), platforming unit, are presented. The proposed models predict the volume flow rate of hydrogen, gasoline, and liquid petroleum gas (LPG), outlet temperature of reactors, gasoline specific gravity, Reid vapor pressure (RVP), and research octane number (RON) of gasoline. In this case, 90 data sets were collected from Tabriz Refinery CRU. A total of 70% of these data sets were used to build and train suitable ANN architecture. Various training algorithms and network architectures were examined, and finally, suitable network were found. Results show excellent ANN capability to predict the unseen plant data. Prediction error of the networks is 1.07%. Using ANN model, a set of optimized operation conditions leading to a maximized volume flow rate of produced gasoline were obtained. Applying optimal conditions, the gasoline production yield will increase from 80 to 82.38%.