Recent Developments of the International Future Lab of Hydrogen Economy: Using Artificial Intelligence (AI) Based Machine Learning (ML) in r-SOC Development

Abstract

The International Future Laboratory for Hydrogen Economy at the Technical University of Munich (TUM) has established a research-network model researching in the field of electrically assisted gasification, reversible solid oxide cells, and biocatalytic synthesis of hydrogen. Using experimental and numerical data, the current study elucidates the progress on reversible solid oxide cell technologies. Advanced artificial intelligence (AI)-based machine learning approaches are utilized to evaluate and optimize SOC-relevant processes. The SOC research is giving particular attention to the integrated approach of traditional numerical methods such as CFD and accelerated modern AI methods. The complex thermochemistry of syngas-containing auxiliary components has been assessed using experimentally validated numerical models. The approach is utilized to create data for the successful construction and training of AI-based machine-learning models. Multi-regression studies shed light on the interactions between process variables to improve and prepare SOC-ready fuel which is essential for successful operation. A recently developed ML model is effectively employed to forecast and optimize the reforming procedures with different fuel constellations including oxygen-containing syngas compositions. Consequently, the results contribute to better knowledge and qualitative benefits of the preparation of high-quality, pure syngas, improved fuel utilisation furthering sustainable research and r-SOC operation in a safe, consistent manner. Hence, the availability of valuable information early in the process is achieved. Moreover, the approach reduced prohibitive experiments contributing to the sustainable use of resources.