Prediction of Optimal Experimental Conditions for The Preparation of C4 Alkenes by Ethanol Coupling Based on Machine Learning Algorithm

DOI

10.2991/978-94-6463-040-4_64How to use a DOI?

Keywords

Machine learning; Process conditions; XGBoost algorithm; Computer-aided experimental design; Ethanol-coupled to prepare C4 alkenes

Abstract

The paper aims to combine computers with chemical experiments, using known experimental data to predict the optimal experimental conditions for the preparation of C4 alkenes by ethanol coupling. In this paper, the known data are predicted by using four machine learning algorithms of random forest, XGBoost, SVR and LightGBM, and by comparing the degree of fitting of the predicted value and the true value, the XGBoost algorithm is selected as the most suitable model to establish the algorithm and the degree of fit is 91.61%, and the best experimental condition prediction model based on the XGBoost algorithm is established. Temperature and catalyst combinations that yielded the best results were:400℃, 200mg 1wt%Co/SiO2-200mg HAP-ethanol concentration of 0.9ml/min. Temperatures under 350℃, and the optimal catalyst combination and temperature were: 325℃, 200mg 2wt%Co/SiO2- 200mg HAP-ethanol concentration of 1.68ml/min. Through machine learning algorithms, the most suitable ratio of chemical experiments is solved, it is to obtain the most efficient experimental ratio, reduce unnecessary experiments, save experiment time, and consume the least amount of chemical materials. Moreover, the model in this paper can also be used for designing auxiliary experiments in other chemical and physical fields with some applicability.

Copyright

© 2023 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Zihao Deng
AU  - Qiuliang Lin
AU  - Junjie Chen
AU  - Shixian Zhang
PY  - 2022
DA  - 2022/12/27
TI  - Prediction of Optimal Experimental Conditions for The Preparation of C4 Alkenes by Ethanol Coupling Based on Machine Learning Algorithm
BT  - Proceedings of the 2022 3rd International Conference on Artificial Intelligence and Education (IC-ICAIE 2022)
PB  - Atlantis Press
SP  - 421

EP  - 427

SN  - 2589-4900
UR  - https://doi.org/10.2991/978-94-6463-040-4_64
DO  - 10.2991/978-94-6463-040-4_64
ID  - Deng2022
ER  -