TY  - JOUR
AU  - Eslamibidgoli, Mohammad Javad
AU  - Tipp, Fabian
AU  - Jitsev, Jenia
AU  - Jankovic, Jasna
AU  - Eikerling, Michael H.
AU  - Malek, Kourosh
TI  - Convolutional neural networks for high throughput screening of catalyst layer inks for polymer electrolyte fuel cells
JO  - RSC Advances
VL  - 11
IS  - 51
SN  - 2046-2069
CY  - London
PB  - RSC Publishing
M1  - FZJ-2021-03819
SP  - 32126 - 32134
PY  - 2021
AB  - The performance of polymer electrolyte fuel cells decisively depends on the structure and processes in membrane electrode assemblies and their components, particularly the catalyst layers. The structural building blocks of catalyst layers are formed during the processing and application of catalyst inks. Accelerating the structural characterization at the ink stage is thus crucial to expedite further advances in catalyst layer design and fabrication. In this context, deep learning algorithms based on deep convolutional neural networks (ConvNets) can automate the processing of the complex and multi-scale structural features of ink imaging data. This article presents the first application of ConvNets for the high throughput screening of transmission electron microscopy images at the ink stage. Results indicate the importance of model pre-training and data augmentation that works on multiple scales in training robust and accurate classification pipelines.
LB  - PUB:(DE-HGF)16
UR  - <Go to ISI:>//WOS:000716076100001
DO  - DOI:10.1039/D1RA05324H
UR  - https://juser.fz-juelich.de/record/897486
ER  -