Begin typing your search...

AI Helps Identify Causes Of Fuel Cell Malfunctions: Study

This technology enables precise analysis using only X-ray tomography, eliminating the need for an electron microscope

AI Helps Identify Causes Of Fuel Cell Malfunctions: Study

AI Helps Identify Causes Of Fuel Cell Malfunctions: Study
X

1 Jan 2025 7:58 AM IST

The trained model was able to predict the 3D distribution and arrangement of the key components of carbon fibre paper — including carbon fibers, binders, and coatings — with an accuracy of over 98 per cent

Seoul: A team of researchers has developed a novel way to analyse the microstructure of carbon fibre paper, a key material in hydrogen fuel cells, at a speed 100 times faster than existing methods, thanks to digital twin technology and artificial intelligence (AI).

Carbon fibre paper is a key material in hydrogen fuel cell stacks, playing a crucial role in facilitating water discharge and fuel supply. It is composed of materials such as carbon fibres, binders (adhesives) and coatings.

Dr Chi-Young Jung's research team from the Hydrogen Research and Demonstration Center at the Korea Institute of Energy Research (KIER) developed a technology that analyses the microstructure of carbon fibre paper using X-ray diagnostics and an AI-based image learning model.

Notably, this technology enables precise analysis using only X-ray tomography, eliminating the need for an electron microscope. As a result, it allows for near real-time condition diagnosis, according to the study published in journal Applied Energy.

The research team extracted 5,000 images from over 200 samples of carbon fibre paper and trained a machine learning algorithm with this data. As a result, the trained model was able to predict the 3D distribution and arrangement of the key components of carbon fibre paper — including carbon fibers, binders, and coatings — with an accuracy of over 98 per cent. “This study is significant in that it enhances analysis technology by combining AI with virtual space utilisation, and clearly identifies the relationship between the structure and properties of energy materials, thereby demonstrating its practical applicability,” said Dr Jung.

AI-based analysis carbon fibre paper hydrogen fuel cells digital twin technology microstructure analysis X-ray tomography machine learning model KIER research 
Next Story
Share it