Additive manufacturing, and 3D printing in particular, has been rapidly gaining momentum in the industry in recent years. 3D printed parts have many unique properties compared to traditionally manufactured parts due to the combination of new processes, materials, and machines that are still under constant development. In this context, the outcome and quality of the resulting parts are often significantly influenced by the capabilities of the 3D printing machine. An in-depth understanding of the operating characteristics of additive manufacturing equipment, and in particular its wear profile, is therefore essential to ensure reliable results - and thus save resources and time in the long term.
The evaluation and prediction system being developed as part of the "HEROD - Ontology-Driven Digital Manufacturing Based on Heterogeneous Data" project aims to enable the estimation of defect conditions and the quality of manufactured parts even before actual production. In addition, predictions of machine wear are to be generated. To enable such a holistic analysis, a large number of heterogeneous factors must be taken into account. These include the characteristics of the 3D printing machines, the duration of the printing process, or the material to be printed. In addition, environmental factors such as room climate or power quality can have a strong influence on the printing result. In order to make 3D printing more robust and reliable in the future, the HEROD project will develop both a data model (based on ontologies) and a special data storage method for managing complex, heterogeneous data in 3D printing. Based on this, a predictive maintenance model will be developed that can provide information about the expected quality of the parts as well as the wear and tear of the machines.
Head of Visual Analytics, Visual Analytics
johanna.schmidt(at)vrvis.at +43 1 908 98 92 302Start: 04.2023
End Date: 09.2025
HAKOM Time Series GmbH, Lithoz GmbH
FFG
No blind spots on train roofs thanks to depth cameras.
The project REINFORCE researches how reinforcement learning and human-centered visualization methods can be used to solve complex control problems in an efficient, fast, and flexible way.
VR and AR provide new solutions for the automotive industry, especially in the prototyping phase: Perfect digital VR twins can be used to easily check how new designs or adaptations affect the prototype.
With the help of 3D printing (additive manufacturing), spare parts for defective trains can be produced more easily and in a sustainable way as well as faster and cheaper - a great potential for the climate-friendly future of train transport companies.
Training AI algorithms requires a great amount of data. However, raw data often contains sensitive information. Homomorphic encryption offers a solution for secure machine learning - with protected sensitive data.
This project aims at accelerating and automating image-based decision making with an application focus on medicine, recycling and quality assurance processes in manufacturing.
The primary goal of project INGRESS is to accelerate and improve the process of data scientists working with Industry 4.0 and Internet of Things (IoT) data, by enabling a closer integration of visual analysis into the existing workflows.
The RAILING project deals with the research and development of interactive, scalable and trust-building visualization and analysis tools for the exploration of time-dependent and complex data.
The goal of the project MARAMT is to develop a software framework to significantly reduce the effort required to work with existing and future complex cyber-physical systems.
