Application of Evolutionary Algorithms for Modelling and Optimisation of Ultrasound-Related Parameters on Synthesised SAPO-34 Catalysts: Crystallinity and Particle Size

Abstract

First, the effects of ultrasound-related variables on the crystallinity and particle size of synthesised SAPO-34 catalysts were modelled using a genetic programming (GP) method. The results confirm that GP has good predictive power. Secondly, optimisation of the ultrasound parameters was considered using a genetic algorithm (GA) to obtain SAPO-34 catalysts with high crystallinity and minimum particle size for the best performance in the methanol to light olefins process. The GP models were used as the fitness functions inside the GA. Finally, the optimum solution was validated experimentally and the results indicate that there is a good agreement between experimental and predicted values.