scholarly journals Reaction condition optimization for non-oxidative conversion of methane using artificial intelligence

Author(s):  
Hyun Woo Kim ◽  
Sungwoo Lee ◽  
Gyoung S. Na ◽  
Seung Ju Han ◽  
Seok Ki Kim ◽  
...  

Chemical reactions typically have numerous controllable factors that need to be optimized to yield the desired products. Although traditional experimental methods are limited to explore possible combinations of these factors,...

2020 ◽  
Author(s):  
Hyun Woo Kim ◽  
Sung Woo Lee ◽  
Gyoung S. Na ◽  
Seung Ju Han ◽  
Seok Ki Kim ◽  
...  

Chemical reactions typically have numerous controllable factors that need to be optimized to yield the desired products. Although traditional experimental methods are limited to explore possible combinations of these factors, artificial intelligence (AI) can provide the optimal solution based on chemical reaction data. In this study, we optimize the non-oxidative conversion of methane to C<sub>2</sub> compounds using AI, such as machine learning (ML) to predict experimental results and metaheuristics to optimize reaction conditions. A decision tree-based machine learning method can reasonably predict the reaction outcomes (CH<sub>4</sub> conversion, C<sub>2</sub> yield, and selectivities for C<sub>2</sub> and coke) with an error of < 5%. Trained ML models are applied to maximize the C<sub>2</sub> yield by optimizing the reaction parameters with metaheuristics. We can simultaneously enhance the C<sub>2</sub> yield and suppress the coke formation by improving the multi-objective function for the optimization. We believe that our method will be helpful to optimize the chemical reaction conditions with multiple targets.<br>


2020 ◽  
Author(s):  
Hyun Woo Kim ◽  
Sung Woo Lee ◽  
Gyoung S. Na ◽  
Seung Ju Han ◽  
Seok Ki Kim ◽  
...  

Chemical reactions typically have numerous controllable factors that need to be optimized to yield the desired products. Although traditional experimental methods are limited to explore possible combinations of these factors, artificial intelligence (AI) can provide the optimal solution based on chemical reaction data. In this study, we optimize the non-oxidative conversion of methane to C<sub>2</sub> compounds using AI, such as machine learning (ML) to predict experimental results and metaheuristics to optimize reaction conditions. A decision tree-based machine learning method can reasonably predict the reaction outcomes (CH<sub>4</sub> conversion, C<sub>2</sub> yield, and selectivities for C<sub>2</sub> and coke) with an error of < 5%. Trained ML models are applied to maximize the C<sub>2</sub> yield by optimizing the reaction parameters with metaheuristics. We can simultaneously enhance the C<sub>2</sub> yield and suppress the coke formation by improving the multi-objective function for the optimization. We believe that our method will be helpful to optimize the chemical reaction conditions with multiple targets.<br>


1992 ◽  
Vol 15 (4) ◽  
pp. 363-370 ◽  
Author(s):  
V. R. Choudhary ◽  
A. M. Rajput ◽  
B. Prabhakar

2017 ◽  
Vol 60 (9-11) ◽  
pp. 735-742 ◽  
Author(s):  
Sunyoung Park ◽  
Maeum Lee ◽  
Jongyoon Bae ◽  
Do-Young Hong ◽  
Yong-Ki Park ◽  
...  

Fuel ◽  
1998 ◽  
Vol 77 (13) ◽  
pp. 1477-1481 ◽  
Author(s):  
Vasant R. Choudhary ◽  
Bathula Prabhakar ◽  
Amarjeet M. Rajput ◽  
Ajit S. Mamman

Sign in / Sign up

Export Citation Format

Share Document