Fraunhofer Institute for Production Technology IPTResearch project "AI-gent3D"
More productivity in the production of 3D printed components
Due to their material properties, components made of high-temperature-resistant thermoplastic materials such as polyetheretherketone (PEEK) are used in safety-critical applications with high quality requirements, for example, in medicine, aviation or the energy sector. When manufacturing such components using 3D printing in the fused deposition modeling process (FDM), the challenges are to optimize productivity, improve product quality and adapt processes to material changes.
Experience shows that far-reaching process improvements in manufacturing in general, but also in additive manufacturing in particular, can be achieved by means of artificial intelligence (AI). Especially small and medium-sized companies involved in 3D printing of polymers, as well as companies developing AI solutions, will benefit from the combination of the two topics in this research project: Investigating AI support in FDM manufacturing of PEEK
Artificial intelligence to increase efficiency in plastic 3D printing
The aim of the BMBF-funded project "AI-gent3D – AI-supported generative 3D printing" is to improve the efficiency of the FDM process for manufacturing components made of PEEK by using artificial intelligence. Increased productivity of manufacturing processes, shorter start-up times, improved product quality, and machine and process reliability are expected to help reduce manufacturing costs and make the entire value chain more efficient. Part of the research here is to analyze how the results can be transferred to a wide range of other production processes, especially in the FDM process and for additive manufacturing.
In the project, the partners are developing a procedure for automated linking and processing of the different data sources and data types for polymer 3D printing. On this basis, three AI applications relevant for production lines with high quality requirements will be implemented as examples: AI-based process parameter setting, prediction of product quality during processing, and predictive maintenance and prediction of machine status. An innovation for polymer 3D printing here is the combination of data from the process with data from product and process development. By linking the different data, it is possible to flexibly initiate process improvements in a short time based on more precise information about the current manufacturing process, thus saving time and costs.
Consortium
Project coordinator: Bond High Performance 3D technology BV, Enschede (NL)
Project partners:
- dida Datenschmiede GmbH, Berlin
- Fraunhofer Institute for Production Technology IPT, Aachen
Funding
This research and development project is funded by the German Federal Ministry of Education and Research (BMBF) as part of the research program "Innovations for the production, service and work of tomorrow" under the funding code 02P20A500 and is supervised by the Project Management Karlsruhe (PTKA).
Publications from this project
| Jahr Year | Titel/Autor:in Title/Author | Publikationstyp Publication Type |
|---|---|---|
| 2023 | Hybrid ML for Parameter Prediction in Production Dorißen, Jonas; Heymann, Henrik; Schmitt, Robert H. |
Zeitschriftenaufsatz Journal Article |
| 2023 | Assessment Framework for Deployability of Machine Learning Models in Production Heymann, Henrik; Mende, Hendrik; Frye, Maik; Schmitt, Robert H. |
Zeitschriftenaufsatz Journal Article |
| 2023 | Machine Learning Pipeline for Predictive Maintenance in Polymer 3D Printing Heymann, Henrik; Schmitt, Robert H. |
Zeitschriftenaufsatz Journal Article |
Diese Liste ist ein Auszug aus der Publikationsplattform Fraunhofer-Publica
This list has been generated from the publication platform Fraunhofer-Publica