Simulation and optimization of heavy oil cracking (HOC) unit using neural network and genetic algorithm

摘要

This research presents an artificial neural network (ANN) model to investigate optimum operating condition of heavy oil catalytic cracking (HOC) to reach maximum gasoline yield. In this case, American petroleum institute index (AP!) , weight percentage of sulfur, Conradson carbon residue content (CCR), gas, coke, and liquid volume percent conversion (%L V) of reaction were considered as ANN model inputs while the percentage of normal butane (N-C4), iso-butane (I-C4), butene (C4=), propane (C3), propene (C3=), heavy cycle oil (HCO), and light cycle oil (LCO) and gasoline (GAS 0) were considered as network outputs. 70% of all industrial collected data set were utilized to train and find the best neural network. Among the different networks, feed-forward multi-layer perceptron network with Levenberg Marquardt (LM) training algorithm with 10 neurons in hidden layer was found as the best network. The trained network showed good capability in anticipating the results of the unseen data (30% of the aIJ data) of catalytic cracking unit with high accuracy. In the next step of study sensitivity analysis was carried out to find the effect of the operating condition on gasoline and products yields. FinaIJy genetic algorithm (GA) was used to optirnize neural model of the plant. It was found that gasoline yield can be increased to 73.6429 % by adjusting operating conditions. 2 •