Honorina L. Lacar | Servillano Sb Olano Jr. | Elmer P. Dadios
Discipline: Engineering
Artificial Neural Network (ANN) was used as an alternative in predicting the separation performance of a ternary distillation process in a packed column with structured packing of a wire-gauze type. In the absence of an actual prototype, the neural network model predicted the effects of reflux ratio, external heat flux through the wall of the distillation column, and feed location with respect to the concentrations of the products. The liquid stream concentration profile within the column was also predicted. Results showed that the ANN approach was capable of modeling complex distillation operations with acceptable accuracy.