Constantly emerging market requirements lead to growing complexity within production systems. The real-time accessibility of relevant information through a digital connected value chain becomes the basis for optimizing production systems with regard to cost, resource efficiency and availability. Thus, a paradigm shift within production and control architectures of production systems can be observed. Predetermined operational and organizational structures will be suppressed by flexible, adaptable and autonomous and therefore intelligent system configurations.
The goal of this research project is to provide context specific knowledge about data based complexity management in production by means of case-based reasoning.
Three basic steps build the basic for the case-based knowledge provisioning: First, domain specific attributes for both complexity in production systems as well as data based solutions to cope with this complexity are defined (knowledge representation). Second, algorithms to identify context specific knowledge are tested and implemented (knowledge identification). Third, systematic measures are defined to transfer knowledge to new application scenarios (knowledge transmission).