Universität zu Köln

Eslamibidgoli, Mohammad J., Tipp, Fabian P., Jitsev, Jenia ORCID: 0000-0002-1221-7851, Jankovic, Jasna, Eikerling, Michael H. and Malek, Kourosh (2021). Convolutional neural networks for high throughput screening of catalyst layer inks for polymer electrolyte fuel cells. RSC Adv., 11 (51). S. 32126 - 32135. CAMBRIDGE: ROYAL SOC CHEMISTRY. ISSN 2046-2069

Full text not available from this repository.

Abstract

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.

Item Type:	Journal Article
Creators:	Creators Email ORCID ORCID Put Code Eslamibidgoli, Mohammad J. UNSPECIFIED UNSPECIFIED UNSPECIFIED Tipp, Fabian P. UNSPECIFIED UNSPECIFIED UNSPECIFIED Jitsev, Jenia UNSPECIFIED orcid.org/0000-0002-1221-7851 UNSPECIFIED Jankovic, Jasna UNSPECIFIED UNSPECIFIED UNSPECIFIED Eikerling, Michael H. UNSPECIFIED UNSPECIFIED UNSPECIFIED Malek, Kourosh UNSPECIFIED UNSPECIFIED UNSPECIFIED
URN:	urn:nbn:de:hbz:38-587480
DOI:	10.1039/d1ra05324h
Journal or Publication Title:	RSC Adv.
Volume:	11
Number:	51
Page Range:	S. 32126 - 32135
Date:	2021
Publisher:	ROYAL SOC CHEMISTRY
Place of Publication:	CAMBRIDGE
ISSN:	2046-2069
Language:	English
Faculty:	Unspecified
Divisions:	Unspecified
Subjects:	no entry
Uncontrolled Keywords:	Keywords Language OXYGEN REDUCTION; NEXT-GENERATION; IONOMER; WATER; MODEL; MICROSTRUCTURE; PERFORMANCE; INSIGHTS; CARBON Multiple languages Chemistry, Multidisciplinary Multiple languages
URI:	http://kups.ub.uni-koeln.de/id/eprint/58748