DISTRAL: Industrial Process Monitoring for Injection Molding with Distributed Transfer Learning
Auf einen Blick
- Projektleiter/in : Prof. Dr. Thilo Stadelmann
- Stellv. Projektleiter/in : Prof. Dr. Matthias Rosenthal
- Projektteam : Dr. Ahmed Abdulkadir, Paul-Philipp Luley, Simone Jana Schwizer, Damian Wildmann, Peng Yan
- Projektvolumen : CHF 1'170'000
- Projektstatus : laufend
- Drittmittelgeber : Innosuisse (Innovationsprojekt / Projekt Nr. 62174.1 IP-ENG)
- Kontaktperson : Thilo Stadelmann
Beschreibung
We develop a distributed machine learning system to sort out defect plastic parts during production. Main challenge is the transferability of learnt process know-how from case to case; the solution builds on domain adaptation, continual data-centric deep learning and federated edge computing.
Publikationen
-
Luley, Paul-Philipp; Deriu, Jan Milan; Yan, Peng; Schatte, Gerrit A.; Stadelmann, Thilo,
2023.
From concept to implementation : the data-centric development process for AI in industry [Paper].
In:
2023 10th IEEE Swiss Conference on Data Science (SDS).
10th IEEE Swiss Conference on Data Science (SDS), Zurich, Switzerland, 22-23 June 2023.
IEEE.
S. 73-76.
Verfügbar unter: https://doi.org/10.1109/SDS57534.2023.00017