Bytefabrik

This project is brought forward by Bytefabrik.AI GmbH. Large automated production plants comprising several machines and robots require permanent maintenance due to a large number of wearing parts. A common problem in the manufacturing industry is shortage of skilled workers. As a result, workers are often responsible for the operation of multiple assembly lines at the same time. This leads to a high amount of worker stress and reactive behavior, since workers are often forced to turn into “firefighting mode”, solving one critical problem after the other. To counter this problem, predictive maintenance applications have become an important driver to reduce downtime by better scheduling of maintenance operations. However, the uptake of such applications is still hindered by a lack of data science & AI expertise especially for SMEs.

Focusing on Challenge 6 ‘Collaboration between AI and Human Supervisors to solve complex problems’, the overall goal of the MANIAC project is the development of the Manufacturing Analytics Copilot, which continuously analyses process parameters from machines, robots and assembly lines in real-time. It automatically detects relevant situations and creates “Data Stories”, which shop floor workers can use to quickly understand problems and prioritize maintenance. As a flexible AI system, the manufacturing copilot reduces stress at work and increases productivity by reducing system downtimes and failures. The developed solution will be based on Apache StreamPipes, an open source toolbox for industrial data analytics with currently more than 20.000 downloads. StreamPipes was initiated by the founders of Bytefabrik.AI. Following an open core business model, Bytefabrik.AI offers support for Apache StreamPipes and commercial extensions. MANIAC targets Flanders Make, building block #13 ‘Predictive Maintenance’ in order to benefit from Flanders Make experience on methodology on predictive maintenance, such as expertise related to suitable algorithms for various manufacturing processes.

Our exploitation strategy foresees to extend our open source software with novel predictive maintenance algorithms and additional connectors for industrial machinery, further increase the visibility of the open source project and to extend Bytefabrik.AI’s commercial product portfolio with the manufacturing analytics copilot as an innovative add-on.