Autor: Felix Reinhart

Data Science is an established tool for knowledge discovery, in particular from economic data. The progressing digitization of products and production systems enables the broader application of Data Science in technical systems. However, the requirements and constraints, e.g. for control and optimization of production processes, differ significantly from established Data Science applications. Industrial Data Science addresses the issues of applying machine learning to technical systems in industrial setups. This article characterizes challenges of Industrial Data Science, gives application examples of and general indicators for Industrial Data Science.

Mechatronic systems have to fulfill increasingly advanced functions and requirements to serve future customer needs and create reliable, resource-efficient and user-friendly systems. To realize tomorrow’s technical systems, solutions in context of self-optimization can be used. Thus, intelligent behavior can be integrated in technical systems. These systems are able to adapt their behavior autonomously and react to outer influences. The Leading-Edge Cluster “Intelligent Technical Systems OstWestfalenLippe (it’s OWL)” focuses on the described innovation leap from mechatronics to intelligent technical systems. Within this contribution we explain the capabilities of solutions in context of self-optimization on the example of machine learning methods. Furthermore, an approach for the identification of potentials for the integration of self-optimization in mechatronic systems will be introduced.