Anomalies and errors in the production process usually result in cost-intensive rework, elaborate final inspections and delivery delays, which in turn have a negative impact on productivity and sustainability. The goal should therefore be to ensure quality directly at the time of process execution. This is precisely where the German-Czech research project AIQUAMA (AI-based Quality Management for Smart Factories) comes in, which has now been launched with a kick-off at the Forum Digitale Technologien in Berlin.

Aiming for zero-defect production

The zero-defect production targeted by AIQUAMA is to be based on incremental quality monitoring in real time. For this purpose, multi-sensor data streams are evaluated using artificial intelligence methods. The evaluation itself is based on real, but also synthetic (training) data, which is analyzed using a combination of symbolic models and statistical machine learning.

Duration of three years

AIQUAMA is a German-Czech research cooperation in the field of Industry 4.0 that builds on common foundations, such as from RICAIP (EU H2020). The project is funded by the German Federal Ministry of Education and Research over a period of three years, with a total volume of approximately 1.8 million euros. The project partners are in detail: the German Research Center for Artificial Intelligence DFKI, the Czech Institute of Informatics, Robotics and Cybernetics (CIIRC) at the Czech Technical University Prague (CTU), the Central European Institute of Technology at the University of Brno (CEITEC BUT) and the Technical University of Ostrava together with the application partners Volkswagen AG and Škoda Auto (no funding).

Together with Volkswagen, DFKI will also implement and realistically evaluate an AIQUAMA demonstration system in the field of manual and hybrid assembly in Saxony.

Video