Artificial Neural Network for Optimization of a Synthesis Process of γ-Bi_2MoO_6 Using Surface Response Methodology

摘要

In this work an artificial neural network was utilized in order to optimize the synthesis process of γ-Bi_2MoO_6 oxide by co-precipitation assisted with ultrasonic radiation. This oxide is recognized as an efficient photocatalyst for degradation of organic pollutants in aqueous media. For the synthesis of γ-Bi_2MoO_6 three variables were considered, the exposure time to ultrasonic radiation, calcination time and temperature. The efficiency of photocatalysts synthesized was evaluated in the photodegradation of rhodamine B (rhB) under sun-like irradiation. A set of experimental data were introduced into the neural network, a multilayer type perceptron with a back-propagation learning rule was used to simulate the results by modifying one of the three input variables and observing the efficiency of photocatalysts using besides a response surface methodology.