Modeling of supercritical fluid extraction by artificial neural networks

An artificial neural network that considers the system as a black box is designed for the mass transfer modeling of supercritical fluid extraction. The proposed neural network assumes a three-layer structure with a fast backpropagation learning algorithm. In addition, a hybrid model using both a neural network and the Peng-Robinson state equation is developed for supercritical fluid extraction, where the neural network is used to generate the non-linear binary interaction parameter of the Peng-Robinson state equation. Various temperatures, pressures, and solubility in literature are used to train the proposed models. The predictions of the proposed neural network models are compared to a conventional model with a Peng-Robinson equation of state in literature. Generally the results using the proposed models are better than those using the conventional model. The effectiveness of the proposed neural network approaches are demonstrated by simulation and comparison studies