Modeling and optimization of catalytic performance of SAPO-34 nanocatalysts synthesized sonochemically using a new hybrid of non-dominated sorting genetic algorithm-II based artificial neural networks (NSGA-II-ANNs)

摘要: The effects of ultrasound-related variables on the catalytic properties sonochemically prepared SAPO-34 nanocatalysts in methanol to olefins (MTO) reactions were investigated. Different behaviors are observed which can be explained by differences catalysts’ physicochemical affected ultrasonic (US) power intensity, sonication temperature, irradiation time and sonotrode size. This result confirms that activity catalysts improves with rise US power, temperature. In order find a catalyst maximum conversion methanol, light content lifetime, hybrid non-dominated sorting genetic algorithm-II based artificial neural networks (NSGA-II-ANNs) was used. multilayer feed forward back-propagation structures implemented using different training rules approach relate performance catalysts. A comparison between experimental network (ANN) values indicates ANN model 3–10–3 structure Bayesian regulation rule has best fit used as fitness evaluation inside (NSGA-II). Also, multiple linear regression (MLR) predict these objective functions. results indicate poor for functions low coefficient determination. technique is more effective than traditional statistical-based prediction models. Finally, this linked NSGA-II Pareto-optimal solutions determined NSGA-II.