DISTRAL: Industrial Process Monitoring for Injection Molding with Distributed Transfer Learning (Innolink: 101.787 IP-ENG)

• Unité de recherche: INNOSUISSE
• Numéro de projet: 101.787 IP-ENG
• Titre du projet anglais: DISTRAL: Industrial Process Monitoring for Injection Molding with Distributed Transfer Learning (Innolink: 101.787 IP-ENG)

Mots-clé (Anglais)

Engineering, Advanced manufacturing

Résumé des résultats (Abstract) (Anglais)

We develop a distributed machine learning system to sort out defect plastic parts during production. The 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.