Fig. 1: Our workflow for the application of the simple Transfer Learning (TL) approach. | npj Advanced Manufacturing

Fig. 1: Our workflow for the application of the simple Transfer Learning (TL) approach.

From: Transfer learning assessment of small datasets relating manufacturing parameters with electrochemical energy cell component properties

Fig. 1

In the upper part of the diagram, we have the case of applying it to an experimental dataset to predict electrode density and mass loading using the Graphite dataset as the vast one and transferring it through the TL approach to the Silicon-Graphite (Si-Gra) and the NMC smaller datasets. In the lower part of the diagram, we have the case of applying the TL approach to the stochastically generated dataset (GDL200 as a source dataset and GDL1000 as a target dataset, explained in the Methods section) to predict the GDL geometric tortuosity.

Back to article page