Prediction Model and Optimization of Coupling Reaction Yield Based on BP Neural Network

Abstract

The preparation of C4 olefins from ethanol has become a research hotspot in the field of chemical product production. Based on the test data of given catalyst combination at different temperatures, a neural network prediction model for the effect of different catalyst combination and temperature on C4 olefin yield is proposed in this paper. Firstly, taking the catalyst combination and temperature as independent variables, the C4 olefin yield is analyzed by multiple regression analysis and evaluated by R-square index. Secondly, on the basis of this experiment, the BP neural network model for predicting the yield of coupling reaction is reconstructed, and the adaptive genetic operator is added to the BP neural network to optimize its threshold, weight, and convergence speed, so as to improve the accuracy of yield prediction. Finally, the prediction results of BP and GA-BP models are compared from five aspects: SSE, MAE, MSE, RMSE, and MAPE. The experimental results show that the improved model has good global optimization ability and high yield prediction accuracy in the prediction of coupling reaction yield. Therefore, the multiple control variable model proposed in this paper has a certain positive significance for predicting the effect of catalyst combination on yield in coupling reaction.

Construction of distribution transformer operation reliability prediction model based on big data

“…In Formula 1, T represents the load value, λ represents the rated current, v represents the alternating current, and b represents the mutual inductance time. According to the difference between the actual load value and the characteristic value, the operation of the distribution transformer is adjusted to ensure the stable dispatch of the power, and at the same time, the overall reliability prediction effect can be improved [8][9].…”