Enabling Federated Learning Services Using OPC UA, Linked Data and GAIA-X in Cognitive Production
Value creation in production is based on collaboration of different stakeholders and requires the secure and sovereign exchange of knowledge. Today, knowledge has mostly been built up individually and is only exchanged in a proprietary manner. This paper presents an exemplary pipeline for federated...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Publishing House of Wrocław Board of Scientific Technical Societies Federation NOT
2024-05-01
|
| Series: | Journal of Machine Engineering |
| Subjects: | |
| Online Access: | http://jmacheng.not.pl/Enabling-Federated-Learning-Services-Using-OPC-UA-Linked-Data-and-GAIA-X-in-Cognitive,188618,0,2.html |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Value creation in production is based on collaboration of different stakeholders and requires the secure and sovereign exchange of knowledge. Today, knowledge has mostly been built up individually and is only exchanged in a proprietary manner. This paper presents an exemplary pipeline for federated services in cross-domain and cross-company value creation networks for cognitive production. On the example of collaboratively training of a federated machine learning model, machine tool lifetime is predicted in industrial manufacturing for high-end operating resources (high-quality cutting tools). From the shop floor to the cloud, all service relevant information is structured using existing digital twin standards and a linked data approach. In particular, the Industry 4.0 Asset Administration Shell (AAS) and OPC UA are used for collecting and referencing operational and engineering data. GAIA-X connectors transfer the service relevant data through a shared data space. The solution enables intelligent analysis and decision-making under the prioritization of data sovereignty and transparency and, therefore, acts as an enabler for future collaborative, data-driven manufacturing applications. |
|---|---|
| ISSN: | 1895-7595 2391-8071 |