Technical products are becoming more independent, flexible and capable of action due to the increasing integration of information and automation technology. In this project, Fraunhofer IEM is working with düspohl Maschinenbau GmbH and encoway GmbH to develop Machine Learning (ML) algorithms for Embedded and Edge Devices that can be run in a decentralized manner. The focus is on two use cases: the intelligent setup of profile wrapping machines and the predictive maintenance of failure-critical components in materials handling applications, such as slippage of friction wheels and drive belts due to wear or damage to bearings and gears.

A major goal of the project is the development and implementation of learning methods in distributed, decentralized systems under consideration of resource constraints. The starting point for this is data from multimodal, active sensor systems with embedded, real-time data analysis methods that are enhanced with ML methods. These data are to be further processed locally in the machine or component and thus a data-centric automation of machine and plant engineering is to be developed.

Facts

Project: Embedded Artificial Intelligence for Production Systems (EASY)
Project duration: 01/10/2020 to 01/09/2023
Project volume: EUR 1.39 million