A staff of researchers has developed a novel solution to analyse the microstructure of carbon fibre paper, a key materials in hydrogen gasoline cells, at a velocity 100 occasions quicker than current strategies, due to digital twin expertise and synthetic intelligence (AI).
Carbon fibre paper is a key materials in hydrogen gasoline cell stacks, taking part in an important position in facilitating water discharge and gasoline provide. It’s composed of supplies resembling carbon fibres, binders (adhesives) and coatings.
Dr Chi-Younger Jung’s analysis staff from the Hydrogen Analysis and Demonstration Heart on the Korea Institute of Vitality Analysis (KIER) developed a expertise that analyses the microstructure of carbon fibre paper utilizing X-ray diagnostics and an AI-based picture studying mannequin.
Notably, this expertise permits exact evaluation utilizing solely X-ray tomography, eliminating the necessity for an electron microscope. Because of this, it permits for close to real-time situation prognosis, in keeping with the examine printed in journal Utilized Vitality.
The analysis staff extracted 5,000 pictures from over 200 samples of carbon fibre paper and educated a machine studying algorithm with this information.
Because of this, the educated mannequin was in a position to predict the 3D distribution and association of the important thing elements of carbon fibre paper – together with carbon fibers, binders, and coatings – with an accuracy of over 98.
“This examine is important in that it enhances evaluation expertise by combining AI with digital area utilisation, and clearly identifies the connection between the construction and properties of vitality supplies, thereby demonstrating its sensible applicability,” stated Dr Jung.
“We count on it to play a big position in associated fields resembling secondary batteries and water electrolysis sooner or later,” he added.
