New at HZB: Tomography lab for AI-assisted battery research
X-ray tomography of a battery cathode, virtually disassembled into its components. © M. Osenberg, I. Manke/ HZB / Binder/ KIT
At HZB, a laboratory for automated X-ray tomography on solid-state batteries is being set up. The special feature: 3D data during charge/discharge processes (operando) can be evaluated quickly and in a more versatile way using artificial intelligence (AI) methods. The Federal Ministry of Research and Education is funding the "TomoFestBattLab" project with 1.86 million euros.
X-ray tomography allows a direct glimpse into a battery's inner structures during discharging and charging. "For example, when the lithium moves back and forth between the anode and cathode during charging and discharging, the lithium storage material may expand or chemical transformation processes may take place," explains tomography expert Dr Ingo Manke. The three-dimensional imaging of these structural changes can reveal weak points in terms of performance and durability, for example ageing processes. X-ray tomography can map these structural changes and has therefore also become an indispensable measurement technique in battery research - similar to medicine.
HZB is now setting up an automated tomography laboratory that is specifically geared to the needs of solid-state batteries. The evaluation of tomographic measurements is extremely time-consuming because the data volumes are huge and require complex 3D algorithms. Therefore, large parts of the 3D evaluations are to be fully automated with the help of artificial intelligence (or machine learning) methods. This is supported by a special high-performance computer with which so-called "digital twins" of the real batteries can be generated.
This combination of artificial intelligence methods and tomography measurement techniques is an innovative approach with a pilot function for equipping future laboratories. "The project helps us to digitalise battery research with regard to the requirements of Industry 4.0 and to accelerate the development of batteries," says project coordinator Manke.
The new laboratory will support working groups at university and non-university research institutions as well as industrial companies in developing and improving new battery technologies.
Funded until 2024
The project "Machine Learning supported automated laboratory for multi-dimensional Operando Tomography of solid-state batteries under real operating conditions" (TomoFestBattLab, FKZ 03XP0462) is funded by the Federal Ministry of Education and Research (BMBF) as part of the initiative to expand the national research infrastructure in the field of battery materials and technologies (ForBatt). The project is funded from 01.09.2022 to 31.08.2024.
- AI agents deliver results – but do they reason scientifically?A research team co-led by Kevin Maik Jablonka from the Helmholtz Institute for Polymers in Energy Applications Jena (HIPOLE Jena) and N. M. Anoop Krishnan from the Indian Institute of Technology Delhi has developed Corral, a new benchmark for AI agents in science. The preprint “AI scientists produce results without reasoning scientifically” has been published on arXiv (https://doi.org/10.48550/arXiv.2604.18805). The analysis shows that current systems can execute scientific workflows and deliver results; however, they often do not follow the basic principles of scientific testing and reasoning.
- Magnetic field during catalyst synthesis triples ammonia yieldApplying an external magnetic field during the synthesis of CoFe₂O₄ electrocatalysts triples the ammonia yield during electrocatalytic conversion. The magnetic field alters the surface states of the spinel oxide thin films, making catalytically active sites more accessible. In the journal 'Advanced Functional Materials', a team led by Marcel Risch at HZB and Sanjay Mathur at University of Cologne demonstrates a scalable strategy for developing next-generation electrocatalysts for efficient and sustainable chemical production.
- Materials chemistry shapes the future of catalysisThe synthesis of materials can serve as a tool for developing smart, adaptive electrocatalysts. This rapidly evolving field of research involves in-situ analytics, data-driven discoveries and autonomous robotics. These new approaches could accelerate the discovery of long-lasting and efficient catalysts for future energy conversion and the decarbonisation of the chemical industry. A recent article by Dr Prashanth Menezes and his team in the renowned journal Angewandte Chemie provides an overview of this research.