A research team at the Korea Institute of Energy Research (KIER) has developed a groundbreaking technology to analyze the microstructure of carbon fibre paper, a vital material in hydrogen fuel cell stacks. By leveraging X-ray diagnostics and an AI-based image learning model, the team achieved a speed 100 times faster than existing methods. This innovation enables precise analysis using only X-ray tomography, eliminating the need for an electron microscope and allowing for near real-time condition diagnosis. Through training a machine learning algorithm with 5,000 images from 200 carbon fibre paper samples, the model accurately predicted the 3D distribution and arrangement of key components like carbon fibers, binders, and coatings with an impressive accuracy of over 98%. Dr. Chi-Young Jung highlighted the study's significance in enhancing analysis technology by integrating AI with virtual space utilization, showcasing the clear relationship between structure and properties of energy materials. The research, published in Applied Energy, holds promise for future applications in fields like secondary batteries and water electrolysis, indicating its practical applicability in advancing energy materials technology.