Abstract
An Artificial Neural Network (ANN) estimator is designed to predict the composition values of a reactive batch distillation system inferentially. The estimator for the reactive batch distillation system, which is recently a preferred industrial operation for specialty chemicals production, is designed using temperature measurements throughout the column. The reflux ratio of the batch distillation column is also used as input to the ANN as well as temperature values. The ANN used is an Elman network with two hidden layers; having 20 neurons in the first hidden layer, three neurons in the second hidden layer, and four neurons in the output layer. The performance of the designed network is tested in open-loop and it is found that, it is possible to predict the product compositions by using the designed ANN estimator which can be used in the control of the product compositions.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
