DigiBatMat brings together data and knowledge about battery materials from different sources and moves as a border crosser between the innovation platform MaterialDigital and the competence cluster Prozell.


The analysis of battery material data enables quality prediction as well as the prediction of key figures. On this basis, a better understanding of the production and manufacturing processes can be created.


The aim is to develop a data-driven platform that provides the user with knowledge and recommendations on demand. This allows production errors to be detected at an early stage and battery key figures to be predicted as a function of selected process parameters. Sustainable production of high-performance battery cells can thus be ensured.

Video zum Projekt DigiBatMat

Your contact

Marcel Mutz

eMail: Marcel.Mutz@aws-institut.de
Phone: +49 681 96777297

In a nutshell


Batteries must become more powerful, more reliable and more durable. To meet the rapidly increasing requirements of the future, DigiBatMat is concerned with improving battery cell production. This central, digital platform for battery material data represents an extremely innovative solution to further advance the development and transparency of batteries, their production as well as materials used.


A digital platform for battery materials data management is being developed. The collected data will be described and linked in such a way that they can be used for quality predictions by means of machine learning and by means of correlation analysis to answer precisely posed questions. In this way, critical parameters in battery manufacturing are identified. The connection to ProZell, the German competence cluster for battery cell production, helps us to consider the needs of battery research in the development of the platform and to provide tools that can be widely used.

Initial situation

Digitale Plattform für Batteriematerialdaten

Powerful and durable batteries are important building blocks of the energy transition and crucial for competitive electric vehicles. Problems in production lead to low-quality batteries that cannot be used. The result is unnecessary environmental pollution. This must be avoided by predicting quality and possible defects before production.

In the development and analysis of lithium-ion batteries, the industry is faced with specific questions, for example about the durability or the chargeability of the batteries. Until now, these questions could only be answered with great effort in series tests. This is where the DigiBatMat research project comes in. With a digital platform for battery material data, battery material knowledge and their linking, an important foundation stone is being laid for future, sustainable battery production.

250 Mrd. €

could be the market potential for automotive batteries in Europe in the mid-2020s.


to the added value of an electric car is the battery.

The August-Wilhelm Scheer Institute develops the following basic components:

Implementation and realization of a holistic platform. For this purpose, the AWS Institute is developing an application for structured data collection. Here, data from different sources are merged and linked.

Predictable quality assurance. The AWS Institute uses machine learning and artificial intelligence methods to enable data analysis as well as battery quality prediction.



The DigiBatMat project is funded by the German Federal Ministry of Education and Research.