Forward prediction of column breakthrough using a neural network model to interpret thermal signals

Abstract

A neural network trained with data sets where a time off-set is introduced between input and target signals has been used for forward prediction of breakthrough in an ion-exchange adsorption column. The interval used for the time scale shift was determined using a linear correlation between the relative elution volume and the position of the. Once trained the network proved capable of accurately predicting the forthcoming breakthrough curve using signals derived from a sensor mounted in the top third of the column.