Study on Influencing Factors of Ethanol Coupling to Prepare C4 Olefins

Longlong Li; Rui Hong; Chenxia Yang; Jiaqi Tao

doi:10.54097/hset.v17i.2595

Authors

Longlong Li
Rui Hong
Chenxia Yang
Jiaqi Tao

DOI:

https://doi.org/10.54097/hset.v17i.2595

Keywords:

Regression analysis, machine learning algorithm, support vector machine regression (SVMR), C4 olefin, random forest model, BP neural network model.

Abstract

In this paper, we study the data analysis and calculation of the factors influencing the preparation of C4 olefins by ethanol coupling. Specifically, by combining each catalyst, the relationship between temperature and ethanol conversion and C4 olefin selectivity was analyzed by regression analysis and correlation analysis, respectively. In addition, the grey relational degree analysis was used to solve the grey relational degree between the influencing factors of the experiment. The nonlinear correspondence between ethanol conversion and C4 olefin selectivity with different catalyst combinations and temperatures was evaluated by means of random forest model and BP neural network model. Finally, we build a support vector machine regression (SVMR) model and optimize the cost and gamma parameters of this model using a genetic algorithm.

Downloads

Download data is not yet available.

References

L. S. Pei, Preparation of butanol and C_4 alkenes by ethanol coupling, Dalian University of Technology, 2018.

Z. M. Lin, Applied statistics. Second Edition, Tsinghua University Press, 2015.

P. S. Chu, Econometrics (Third Edition), Renmin University of China Press, 2009.

L. Tao, W. S. Yu, Research on my country's electricity market transaction evaluation system based on gray correlation degree and fuzzy comprehensive evaluation method, Industrial Technology and Economics, 2018, 37(09): 130-137.

G. Xuan, Research on movie box office prediction based on random forest, China University of Petroleum (Beijing), 2018.

Y. D. Ju, Y. Jing, Z. X. Juan, Feature selection algorithm based on random forest, Journal of Jilin University (Engineering Edition), 2014 (01); 142-146.

L. X. Hai, Application of random forest model in classification and regression analysis, Journal of Applied Entomology (Insect Knowledge), 2013, 50(004): 001190-1197.

L. Y. Sheng, X. Xin, et al., Data Mining Principles and Application of Algorithms, Beijing: Machinery Industry Press, 2014.

Y. J. Qi, L. Jia, S. S. Qian, Influencing factor analysis model and empirical research on the impact factor of sci-tech journals based on BP neural network, China Market, 2008(26): 103-104.

L. Ning, Analysis of influencing factors of the impact factors of management journals based on BP neural network, Journal of Shaanxi Institute of Education, 2007(03):83-86.

L. G. Zhou, The idea of osmotic control variables to cultivate chemical experimental ability, New Education, 2021(14):77-78.