Pioneering AI technologies are set to further improve precision manufacturing. Image: Furtwangen University/ Silicya Roth
'PräziLoop' project starts at Furtwangen University with €1.2m in funding
Expensive measuring technology, high energy consumption and long downtimes - quality assurance in precision manufacturing has been time-consuming and cost-intensive up to now. This is set to change: In the new research project “PräziLoop”, Furtwangen University (HFU), together with partners from science and industry, is developing an AI-supported closed-loop solution to predict the quality of grinding processes at an early stage and thus drastically reduce the costly measurement effort on the finished component. The project is being funded with 1.2 million euros from the Carl Zeiss Foundation.
“With PräziLoop, we want to usher in a paradigm shift in manufacturing: away from complex measurement technology and towards predictive quality assurance through explainable clones. In this way, we not only reduce costs and energy consumption, but also create trust in intelligent production processes,” explains project manager Prof. Dr. Christoph Reich from the university's Institute for Data Science, Cloud Computing and IT Security, or IDACUS for short.
The focus is on the use of modern machine learning methods for time series analyses and explainable AI (XAI). The aim is to draw conclusions about component quality from a variety of sensor data, such as spindle load, vibrations or acoustic signals. In future, components will be classified as good parts, suspect parts or rejects during production. The adaptive control of the grinding process will then take place automatically.
The project addresses typical challenges in industrial practice: low data availability, high demands on process quality and the need to make decisions traceable. PräziLoop is based on a modular structure and pursues an open source approach in order to enable the transferability of the developed solution to other machining processes.
Strong partnership between science and practice
In the PräziLoop project, four professors at Furtwangen University are pooling their expertise to jointly research a new generation of intelligent manufacturing. Prof. Dr. Christoph Reich (IDACUS) coordinates the project and is responsible for the areas of artificial intelligence and machine learning. Prof. Dr.-Ing. Pascal Laube focuses on Machine Learning Operations (MLOps) and automation of data-driven AI processes. Bahman Azarhoushang (Head of the KSF Institute of Advanced Manufacturing) contributes many years of experience in machining and process optimisation. Prof. Dr. Verena Wagner-Hartl (Institute of Technical Medicine) conducts research into aspects of human-machine interaction and user-centered AI explainability.
In addition, the universities of Freiburg, Haute-Alsace and Plymouth, ETH Zurich and the Technical University of Dresden are five scientific partners and Ziersch GmbH, Inovex GmbH and Tepcon GmbH are industrial partners from the fields of machining, AI and digitalisation. The results are to be disseminated by the network partners (Cluster Zerspanungstechnik, IHK Arbeitskreis Produktion 2030, Innovationsnetzwerk SBH e.V., TechnologyMountains e.V.) and transferred to industry.
About the Carl Zeiss Foundation
The Carl Zeiss Foundation has set itself the goal of creating scope for scientific breakthroughs. As a partner of excellent science, it supports basic research as well as application-oriented research and teaching in the STEM disciplines (mathematics, computer science, natural sciences and technology). Founded in 1889 by the physicist and mathematician Ernst Abbe, the Carl Zeiss Foundation is one of the oldest and largest private science-promoting foundations in Germany. It is the sole owner of Carl Zeiss AG and SCHOTT AG. Its projects are financed from the dividends distributed by the two foundation companies.
Contact: Internal link opens in the same window:Prof. Dr. Christoph Reich