Project ML4P: Machine Learning for Production


In the Machine Learning for Production (ML4P) flagship project, we assume that performance in modern production facilities - both in the process and unit-production industries - can be optimized with the help of machine learning.

Under the auspices and coordination of Fraunhofer IOSB, several Fraunhofer institutes are pooling their application experience and expertise in machine learning to develop solutions for industry. In ML4P, intelligent methods for meeting the needs of industry will be formulated and the way to flexible, fast-learning systems will be prepared. A "learning machine" could, for example, involve the installation of intelligent components or efficient, holistic handling of very large amounts of data.  


Targets of ML4P:

  • Development of a tool-supported process model
  • Realization of a software tool with which the actual state is recorded and analyzed in order to identify possible optimization potentials
  • Derivation and selection of suitable machine learning methods in production 



Fraunhofer-Institut für Intelligente Analyse und Informationssysteme IAIS
Fraunhofer-Institut für Fabrikbetrieb und -automatisierung IFF
Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung IOSB
Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung, Institutsteil IOSB-INA
Fraunhofer-Institut für Techno- und Wirtschaftsmathematik ITWM
Fraunhofer-Institut für Werkstoffmechanik IWM
Fraunhofer-Institut für Werkzeugmaschinen und Umformtechnik IWU

On February 7, 2018, the kick-off for the Fraunhofer lead project "ML4P" took place at Fraunhofer IOSB.


Lead projects - rapid implementation for the market

The Fraunhofer-Gesellschaft is addressing the current challenges facing German industry. With its Lead projects it sets strategic priorities in order to develop concrete solutions for the benefit of Germany as a business location. The topics are geared to the needs of industry. The goal is to quickly turn original scientific ideas into marketable products. The participating Fraunhofer institutes pool their expertise and involve industry partners in the projects at an early stage. 


Projekttitel: ML4P: Machine Learning 4 Production
Laufzeit: 01.03.2017 - 28.02.2022
Förderung: Leitprojekt der Fraunhofer-Gesellschaft
Ziel: Toolgestütztes Vorgehensmodell für 4 standardisierte Arbeitsschritte zum Einsatz Maschineller Lernverfahren