Work

The Applicability of Machine Learning Methods to the Characterization of Fibrous Gas Diffusion Layers

Year: 2023

Type: article

Abstract: Porous materials can be characterized by well-trained neural networks. In this study, fibrous paper-type gas diffusion layers were trained with artificial data created by a stochastic geometry model. The features of the data were calculated by means of transport simulations using the Lattice–Boltzmann method based on stochastic micro-structures. A convolutional neural network was developed that can predict the permeability and tortuosity of the material, through-plane and in-plane. The characteristics of real data, both uncompressed and compressed, were predicted. The data was represented by reconstructed images of different sizes and image resolutions. Image artifacts are also a source of potential errors in the prediction. The Kozeny–Carman trend was used to evaluate the prediction of permeability and tortuosity of compressed real data. Using this method, it was possible to decide if the predictions on compressed data were appropriate.

Source: Applied Sciences

DOI: 10.3390/app13126981

Authors: Dieter Froning, Eugen Hoppe, Ralf Peters

Institution: Forschungszentrum Jülich

Language: English

Topic: Machine Learning in Materials Science

Subfield: Materials Chemistry

Field: Materials Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $2,558

Funders: Deutsche Forschungsgemeinschaft, Bundesministerium für Bildung und Forschung, Forschungszentrum Jülich, RWTH Aachen University