Optimization of process conditions for catalytic preparation of C4 olefins from ethanol based on Stochastic Forest algorithm

C4 olefin is an essential production raw material in the field of chemical industry and medicine. This paper primarily establishes a mathematical model based on the existing experimental data in order to investigate the optimal catalyst combination and temperature for Ethanol Catalysed preparation of C4 olefin. Firstly, we pretreated the variables and analysed the effects of catalyst loading mode with the addition of quartz sand on the selectivity of C4 olefins. Then the remaining four variables, as well as two dependent variables, are analysed by multiple linear regression and nonlinear regression. In the nonlinear regression method, we make use of the three different neural network algorithms: BP, RBF, and random forest. After considering the prediction results, the goodness of fit, and model stability, we believe that the effect of the random forest algorithm is better. On ethanol conversion and C4 olefin selectivity, the effects of different catalyst combinations and temperatures were acquired.