Big-Data and event-based adjustment for the configuration of resilient production systems
Project goal is the development of a Big Data platform including algorithms for data pattern detection to implement a proactivce disturbance management system in the production. Human data is considered as an additional data source. The disturbance management is further supported by an visualization of the disturbances and respective counteractions.
Since production systems are becoming more and more technically mature today's manufacturing industry sees itself confronted with a bigger and bigger pile of data. To make this data pile processable and, even more important, useable we made it our duty to develop models and algorithms to handle this abundance of data. The goal is to develop a Big-Data platform which is easy to implement and independent from its business area of implementation. Through this platform we gain access to real-time production process data which helps developing a data pattern detection. The data pattern detection can be used as a proactive disturbance management system to help identify production dysfunctions early or even prevent them. By recognizing human perception of the production processes' quality we add another dimension to the disturbance management system. Another aim is to develop a concept of vizualising the collected data to illustrate disturbances and countermeasures user-oriented to reach the best possible support of the decision-making level.
- Asseco Solutions AG, Karlsruhe
- AUTO HEINEN GmbH, Bad Münstereifel
- cognesys gmbh, Aachen
- DFA Demonstrationsfabrik Aachen GmbH, Aachen
- EICe Aachen GmbH, Aachen
- EML European Media Laboratory GmbH, Heidelberg
- FZI Forschungszentrum Informatik am Karlsruher Institut für Technologie , Karlsruhe
- i2solutions GmbH, Stolberg
- Robert Bosch GmbH, Gerlingen-Schillerhöhe
- Software AG, Darmstadt
- Laboratory for Machine Tools and Production Engineering (WZL) of RWTH Aachen University, Aachen