Next generation control units simplifying industrial machine learning

The increasing amount of sensor data creates new possibilities through data-driven projects in industry. The demands on the final solution architecture are different and typically include at least one controller (e.g. PLC). In this paper, we focus on these industrial controllers and identify their possible roles in smart factories: Collection, distribution and preprocessing of field data, execution of intelligence and functionalities to ease rapid prototyping approaches. Furthermore, we specify the capabilities leading to the fulfillment of these roles and present an application example of drive anomaly detection to demonstrate how to setup an industrial controller for machine learning projects.