(169cc) Development of Experimental Guidelines for Organic Field-Effect Transistors (OFETs) Using Machine Learning Based on Ofets Database | AIChE

(169cc) Development of Experimental Guidelines for Organic Field-Effect Transistors (OFETs) Using Machine Learning Based on Ofets Database

Authors 

Lee, M. - Presenter, Lehigh University
Venkatesh, R., Georgia Institute of Technology
Bonsu, J. A., Georgia Institute of Technology
Grover, M., Georgia Tech
Reichmanis, E., Lehigh University
Conjugated polymers are attractive materials for flexible and stretchable electronic device applications with cost-effective processes. Although their performance is not expected to reach that of silicon-based devices, they can be applied to large area and curved surfaces. However, the device fabrication steps include many process variables that consume abundant resources and time to optimize the process with trial-and-error experimentation. In the case of organic field-effect transistors (OFETs), trial-and-error experimentation has been employed to explore optimization in huge process space. This bottleneck can be overcome with data-driven approaches. In this study, we propose a database structure to store the process conditions and guide future experimental directions More than 600 data points poly(3-hexylthiophene) (P3HT), poly[2,5-(2-octyldodecyl)-3,6-diketopyrrolopyrrole-alt-5,5-(2,5-di(thien-2-yl)thieno [3,2-b]thiophene)] (DPP-DTT), and poly{[N,N'-bis(2-octyldodecyl)naphthalene-1,4,5,8-bis(dicarboximide)-2,6-diyl]-alt-5,5'-(2,2'-bithiophene)} (N2200) are extracted and machine learning is used to understand the relationship between each process variable and device performance. We identified which variable had a significant impact on the device performance. The study shows that experimental guidelines can be provided by machine learning to reduce resources and time for process optimization.