Application of Machine Learning to Fischer−Tropsch Synthesis for Cobalt Catalysts | Sciact - CRIS-система Института катализа

Application of Machine Learning to Fischer−Tropsch Synthesis for Cobalt Catalysts Научная публикация

Журнал

Industrial and Engineering Chemistry Research
ISSN: 0888-5885 , E-ISSN: 1520-5045

Вых. Данные

Год: 2023, Том: 62, Номер: 48, Номер статьи : 20658-20666, Страниц : 9 DOI: 10.1021/acs.iecr.3c03147

Авторы

Motaev Kirill ¹ , Molokeev Maxim ¹ , Sultanov Bulat ² , Kharitonsev Vladimir ¹ , Matigorov Alexey ¹ , Palianov Mikhail ¹ , Azarapin Nikita ^1,3

Организации

1	Laboratory of Theory and Optimization of Chemical and Technological Processes, University of Tyumen, 625003 Tyumen, Russia
2	Laboratory of Digital Catalysis of Centre for Nature-Inspired Engineering, University of Tyumen, 625003 Tyumen, Russia
3	Institute of Chemistry, University of Tyumen, 625003 Tyumen, Russia

Machine Learning was used to make a prediction model for six property parameters (COconv (%); CH4 (%); CO2 (%); C2–C4 (%); C5+ (%); and COconv*C5+ (%)) from 16 feature parameters of 169 Fischer–Tropsch synthesis experiments for cobalt catalyst. The Random Forest method was chosen as the “black-box” prediction tool, and cross-validation tests revealed small mean average errors: 10.9 ± 1.8; 3.7 ± 0.7, 1.5 ± 0.6, 3.6 ± 0.8, 7.4 ± 1.4 and 9.0 ± 1.3, respectively. The most important feature parameters were Brunauer–Emmett–Teller (BET) surface area, pressure (P), and temperature (T). The Decision Tree was chosen to build an explainable model, which revealed that BET in the range of [199.5, 529] leads to small COconv (%); C5+(%); and COcon*C5+(%) values. Outside this range, the samples tend to have large conversion and selectivity values. Most importantly, the BET effect is not linear or monotonic; it can be extracted using machine learning methods, and current work has shown how to use it. The resulting rules can be used for further experiments to maximize the efficiency and develop a new catalyst system. Particularly, porous Co3O4 with a small admixture of Al2O3 particles, Co2O3 by classical calcination of quartz sand impregnated with a cobalt nitrate solution, and a catalyst using a hydroxyapatite support were identified as good candidates for further deep screening of the best catalysts.

Motaev K. , Molokeev M. , Sultanov B. , Kharitonsev V. , Matigorov A. , Palianov M. , Azarapin N.
Application of Machine Learning to Fischer−Tropsch Synthesis for Cobalt Catalysts
Industrial and Engineering Chemistry Research. 2023. V.62. N48. 20658-20666 :1-9. DOI: 10.1021/acs.iecr.3c03147 WOS Scopus OpenAlex

Поступила в редакцию:	6 сент. 2023 г.
Принята к публикации:	1 нояб. 2023 г.
Опубликована online:	20 нояб. 2023 г.
Опубликована в печати:	6 дек. 2023 г.

Web of science:	WOS:001142906600001
Scopus:	2-s2.0-85179108977
OpenAlex:	W4388826011

БД	Цитирований
Web of science	7
Scopus	8
OpenAlex	7