Cluster of Excellence "Internet of Production (IoP)"
The goal of the research project "CoE IoP" is to improve cross-domain collaboration over the entire product lifecycle by real-time capable and context-dependent provision of all relevant data.
Although large amounts of data are available in modern companies, they are neither easily accessible, interpretable nor networked in such a way that knowledge can be generated from them. The data is available in individual expert systems that are not linked to other systems. This makes learning about the product lifecycle (from development, through production and usage phase) more difficult.
In cooperation with more than 30 Aachen institutes, a conceptual reference infrastructure ("Internet of Production") is designed and implemented, which enables the generation and use of cross-domain knowledge. The FIR is active in the research focus Production Management. Decision support systems are developed on the basis of practice-oriented usecases, which serve to improve the decision quality and the implementation speed in long-term as well as short-term production management. Different methods like machine learning or process mining are used to process the data.
As a result in the area of long-term production management, a drastic increase in the decision quality is aimed at by supporting the decision maker in the proactive design and improvement of production structures in uncertain business environments through intelligent decision methods and the corresponding algorithms.
The intended result in the area of short-term production management is the development of self-learning production systems to compensate for disturbances within the production system. Likewise, changes triggered by product development and customer use should be reacted to more quickly.
Benefits for the target group
- Greater transparency with regard to and more confidence in decision-making needs, influencing factors and uncertainties as well as in the effects of areas such as product development and use
- Radically reduce the amount of time required to bring the production system back to a stable state after process adjustments and thus cope with rapid change requests