A Maximum Yield Model for Coupled Ethanol to C4 Alkenes Based on BP Neural Network and Genetic Algorithm
- https://doi.org/10.2991/assehr.k.220504.214How to use a DOI?
- Correlation analysis; Grey correlation model; BP neural network; Genetic algorithm
The preparation of C4 alkenes using ethanol coupling is an important reaction in chemical production, and the catalyst combination and temperature have a significant impact on the extent and efficiency of the reaction. This paper provides a model for seeking the maximum C4 alkenes yield by designing the catalyst combination and setting the temperature. Firstly, we investigated the relationship of ethanol conversion and C4 alkenes selectivity with temperature. The correlation analysis and regression analysis were conducted. We obtained that temperature is positively correlated with ethanol conversion and C4 alkenes selectivity in a certain temperature range, and the most drastic effect point was obtained lies within the interval [350,400] °C. Moreover, we analyzed results from the perspective of the chemical reaction mechanism. Then, we analyzed the effect of different catalyst combinations and temperatures on ethanol conversion and C4 alkenes selectivity by the grey correlation model. We obtain the correlation ranking: temperature > Co loading > Co/SiO2 and HAP loading ratio > drop acceleration rate of ethanol. Finally, we set the maximum C4 alkenes yield as the objective function and established a BP neural network to solve this optimization problem with the genetic algorithm used for extreme value finding. The maximum C4 alkenes yield of 0.4580 was obtained with the catalyst combination of 200 mg 1wt% Co/SiO2, 200 mg HAP, and ethanol concentration 0.9 mL/min without temperature limitation. With a limiting temperature of less than 350°C, the maximum C4 alkenes yield is 0.1982 at a reaction temperature of 348.60°C with the catalyst combination of 200 mg 1wt% Co/SiO2, 200 mg HAP, and ethanol concentration 0.9 mL/min.
- © 2022 The Authors. Published by Atlantis Press SARL.
- Open Access
- This is an open access article distributed under the CC BY-NC 4.0 license.
Cite this article
TY - CONF AU - Baiyang Xiao AU - Yiran Chen AU - Mingyuan Li AU - JingBo Ma AU - Xinyao Zhang PY - 2022 DA - 2022/06/01 TI - A Maximum Yield Model for Coupled Ethanol to C4 Alkenes Based on BP Neural Network and Genetic Algorithm BT - Proceedings of the 2022 8th International Conference on Humanities and Social Science Research (ICHSSR 2022) PB - Atlantis Press SP - 1172 EP - 1178 SN - 2352-5398 UR - https://doi.org/10.2991/assehr.k.220504.214 DO - https://doi.org/10.2991/assehr.k.220504.214 ID - Xiao2022 ER -