DISTRAL: Industrial Process Monitoring for Injection Molding with Distributed Transfer Learning
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.
Eckdaten
Projektleitung
Stellv. Projektleitung
Projektteam
Simone Jana Schwizer, Damian Wildmann, Peng Yan, Paul-Philipp Luley, Dr. Ahmed Abdulkadir
Projektstatus
abgeschlossen, 10/2022 - 03/2025
Institut/Zentrum
Centre for Artificial Intelligence (CAI); Institute of Embedded Systems (InES)
Drittmittelgeber
Innovationsprojekt / Projekt Nr. 62174.1 IP-ENG
Projektvolumen
1'170'000 CHF
School of Engineering
Technikumstrasse 71
8400 Winterthur