Olefin is widely used in chemical and pharmaceutical production. In the process of producing C4 olefin, catalyst combination and temperature will affect the formation of C4 olefin. As one of the most important high value-added raw materials in the chemical industry, the synthesis of C4 Olefin by ethanol coupling was of great significance in the field of the chemical industry. Different catalysts and various conditions have different effects on the chemical reaction ^[1]. This paper mainly explores the relationship between selectivity of C4 olefin and catalyst combination and temperature, and how to optimize catalyst combination and temperature to make the yield of C4 olefin as high as possible. This article is based on relevant data sets. This article explores the relationship between variables such as the amount of Co loading, Co/SiO2 ratio, HAP loading ratio, ethanol concentration, catalyst loading method, temperature, and the selectivity of C4 olefins and the conversion rate of ethanol. It is based on relevant datasets and utilizes the method of controlling variables. Pearson coefficient is used to test the correlation between variables, and a multiple linear regression model is established. Finally, experiments are designed to verify the optimal conditions for achieving the highest yield of C4 olefins. Based on analysis and validity testing, the findings suggest that the proposed model is well-suited for chemical reactions in a wide range of industrial production contexts, facilitating efficient extraction of the desired product during actual manufacturing processes. Future improvements will focus on optimizing the model with a larger dataset, incorporating advanced deep learning techniques, and enhancing both its accuracy and precision.

Aijia Chen. The Regression Analysis Model of C4 Olefin Yield Optimization Study. Academic Journal of Materials & Chemistry (2023) Vol. 4, Issue 5: 36-43. https://doi.org/10.25236/AJMC.2023.040506.

[1] Shaopei Lv. Preparation of butanol and C_4 olefin by coupling ethanol [D]. Dalian University of Technology, 2018. 

[2] Jianfei Leng, Xu Gao, Jiaping Zhu. Application of multivariate linear regression statistics to predictive models [J]. Statistics and decision-making, 2016, 07:82-85. 

[3] Liang Dai, Hongke Xu, Ting Chen, Chao Qian, Dianpeng Liang. Multiple linear regression prediction Model based on Map Reduce [J]. Computer application, 2014, 07:1862- 1866. 

[4] Feng Ye. Application of multiple linear regression in forecasting economic and technical output [J]. China and Foreign Energy, 2015, 02:45-48

[5] Xingren Jin. Analysis of influence factors of institutional investors' shareholding preference in pharmaceutical industry [D]. Yunnan University of Finance and Economics, 2021. 

[6] Li Shaowei, Wang Yujie, Xiong Lang, Huang Shengqi. Optimization model for the preparation of C4 olefins by ethanol coupling [J]. Journal of Taizhou University, 2021, 43(06): 26-32+77. DOI: 10. 13853/j. cnki. issn. 1672-3708. 2021. 06. 004. 

[7] Wu Shaojun. Development Status and Optimization Measures of Chemical Engineering Technology [J]. Chemical Design Communication, 2021, 47(07):122-123.