Study on Ethanol Coupling Reaction Based on BP Neural Network and Correlation

Butanol and C4 olefins, as important chemical raw materials, are widely used in the production of chemical products and pharmaceutical intermediates. Traditional production methods use fossil energy as raw materials, but with the shortage of fossil energy production and the aggravation of its impact on the environment, the energy supply gradually tends to be diversified, and the development of new clean energy is becoming more and more urgent. Ethanol molecules can be prepared by biomass fermentation. They have a wide range of sources and are green and clean. They are used as platform molecules to produce high value-added butanol and C_4 olefins have great application prospects and economic benefits, and have attracted extensive attention at home and abroad. However, in the current industrial production, the catalyst combination and temperature have a great impact on the conversion of ethylene and the selectivity of C4 olefins, and its selection and control greatly affect the production efficiency of C4 olefins. This paper focuses on the influence effect and degree of two factors on two dependent variables in the process of preparing C4 olefins by ethylene coupling reaction. By establishing the least square curve to fit the temperature and ethanol conversion and the temperature and C4 olefin selectivity, the fitting curve is obtained. It can be seen that the temperature has a primary or quadratic function relationship with the ethanol conversion or C4 olefin selectivity, so it is judged that it has a certain influence, Then the effects of temperature, catalyst group and loading method on ethanol conversion and C4 olefin selectivity were obtained by Spearman correlation coefficient and random forest regression algorithm. Based on this result, the model is established, optimized and analyzed, and the optimal catalyst combination and temperature are obtained, so as to obtain the highest C4 olefin yield and achieve the maximum industrial benefit