Study of annealing induced nanoscale morphology change in organic solar cells with machine learning - Details

author：

Lan, Fei (Lan, Fei.) ^[1] | Jiang, Minlin (Jiang, Minlin.) ^[2] | Wei, Fanan (Wei, Fanan.) ^[3] (Scholars：魏发南) | Tao, Quan (Tao, Quan.) ^[4] | Li, Guangyong (Li, Guangyong.) ^[5]

Indexed by：

EI Scopus

Abstract：

Nanoscale　morphology　of　the　active　layer　in　organic　solar　cells　(OSCs)　plays　a　significant　role　in　affecting　the　overall　performance　of　OSCs.　In　this　work,　by　using　the　domain　size　to　describe　the　morphology　change　with　different　annealing　temperatures,　the　influence　of　annealing　to　nanoscale　morphology　in　OSCs　is　intensively　studied.　Also,　machine　learning　is　utilized　in　investigating　the　relation　between　domain　size　and　the　annealing　temperature.　The　realization　of　mapping　the　domain　sizes　to　their　annealing　temperatures　is　significant　in　bridging　the　simulation　work　of　OSCs　to　the　actual　fabrication　process,　indicating　that　the　optimized　domain　sizes　obtained　through　simulation　could　now　be　converted　to　actual　annealing　temperature　in　device　fabrication.　©　2016　IEEE.

Keyword：

Annealing Learning systems Machine learning Morphology Nanotechnology Organic solar cells

Community：

[ 1 ] [Lan, Fei]University of Pittsburgh, Department of Electrical and Computer Engineering, Pittsburg; PA; 15213, United States
[ 2 ] [Jiang, Minlin]University of Pittsburgh, Department of Electrical and Computer Engineering, Pittsburg; PA; 15213, United States
[ 3 ] [Wei, Fanan]Fuzhou University, School of Machine Engineering and Automation, Fuzhou; 350108, China
[ 4 ] [Tao, Quan]University of Pittsburgh, Department of Electrical and Computer Engineering, Pittsburg; PA; 15213, United States
[ 5 ] [Li, Guangyong]University of Pittsburgh, Department of Electrical and Computer Engineering, Pittsburg; PA; 15213, United States