DETERMINATION OF SYNERGISTICALLY GENERATED ACID STRENGTH BY NEURAL NETWORK COMBINED WITH EXPERIMENT

Abstract

Artificial neural network was applied for the estimation of strength of acid sites synergistically generated on binary mixed oxides. The acid strength of a series of mixed oxides with one component fixed could be estimated within a reasonable error. when two corresponding mixed oxides are included in the training set. It was shown that the neural network can be a powerful tool to reduce the number of experimental runs required to evaluate the synergistic effect over a wide range of possible combinations of components.