Enabling Federated Learning Services Using OPC UA, Linked Data and GAIA-X in Cognitive Production
 
More details
Hide details
1
IIoT Controls, Fraunhofer IWU, Germany
 
2
Faculty of Informatic/Mathematic, HTW Dresden, Germany
 
3
Digital Production, Fraunhofer IWU, Germany
 
4
Engineering, Katulu GmbH, Germany
 
These authors had equal contribution to this work
 
 
Submission date: 2024-04-12
 
 
Final revision date: 2024-05-13
 
 
Acceptance date: 2024-05-13
 
 
Online publication date: 2024-05-19
 
 
Publication date: 2024-06-19
 
 
Corresponding author
Christian Friedrich   

IIoT Controls, Fraunhofer IWU, Pforzheimer Straße 7a, 01189, Dresden, Germany
 
 
Journal of Machine Engineering 2024;24(2):18-33
 
KEYWORDS
TOPICS
ABSTRACT
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.
 
REFERENCES (35)
1.
VOLKWEIN M., SCHMITT J., HEIDELBACH J., SCHÖLLHAMMER O., EVCENKO D., KETT H., 2022, Blinde Flecken in der Umsetzung von Industrie 4.0 – identifizieren und verstehen, Acatech, https://publica. fraunhofer. de/handle/publica/434370.
 
2.
HILLERMEIER O., PUNTER M., SCHWEICHHART K., USLÄNDER T., 2021, Data Sovereignty – Critical Success Factor for the Manufacturing Industry, https://doi.org/10.5281/zenodo....
 
3.
OPC FOUNDATION, UA Companion Specifications, 2024, https://opcfoundation.org/abou....
 
4.
Plattform Industrie 4.0, 2024, Details of the Administration Shell – Part 1: The Exchange of Information Between Partners in the Value Chain of Industrie 4.0, available from: https://www.platt-form i40.de/ip/redaktion/de/ downloads/publikation/details_of_the_asset_administration_shell_part1_v3.pdf.
 
5.
IDS International Data Spaces Association, 2024, IDS Reference Architecture Model (Version 3.0).
 
6.
OTTO B., RUBINA A., EITEL A., TEUSCHER A., SCHLEIMER A.M., LANGE C., et al, 2021, GAIA-X and IDS, International Data Spaces Association.
 
7.
GAIA-X Technical Architecture, 2024, GAIA-X- Architecture Documnt, https://gaia-x.eu/wp-content/u... 2022/06/gaia-x-architecture-document-22.04-release.pdf.
 
8.
Eclipse Foundation, 2024, Eclipse Dataspace Components Connector, https://github.com/eclipse-edc.
 
9.
NEUBAUER M., STEINLE L., REIFF C., AJDINOVIC S., KLINGEL L., LECHLER A., et al, 2023, Architecture for Manufacturing-X: Bringing Asset Administration Shell, Eclipse Dataspace Connector and OPC UA Together, Manufacturing Letters, 37, 1–6.
 
10.
ZHENG Z., ZHOU B., ZHOU D., SOYLU A., KHARLAMOV E., 2022, ExeKG: Executable Knowledge Graph System for User-Friendly Data Analytics, Proceedings of the 31st ACM International Conference on Information & Knowledge Management, https://doi.org/10.1145/351180....
 
11.
ZHENG Z., ZHOU B., ZHOU D., ZHENG X., CHENG G., SOYLU A., et al, 2022, Executable Knowledge Graphs for Machine Learning: A Bosch Case of Welding Monitoring, The Semantic Web – ISWC 2022, 21st International Semantic Web Conference, Virtual Event, Proceedings, Berlin, Heidelberg, Springer-Verlag, 791–809.
 
12.
FRIEDEMANN M., WENZEL K., SINGER A., 2019, Linked Data Architecture for Assistance and Traceability in Smart Manufacturing, MATEC Web. Conf., 304, 4006.
 
13.
XU Z., ZHANG Y., Andrew G., Choquette-Choo C.A., KAIROUZ P., MCMAHAN H.B., et al, 2023, Federated Learning of Gboard Language Models with Differential Privacy, Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics.
 
14.
Apple Machine Learning Research. Learning Iconic Scenes with Differential Privacy, 2024, https://machine learning.apple.com/research/scenes-differential-privacy.
 
15.
VETRICHELVAN G., SUNDARAM S., KUMARAN S.S., VELMURUGAN P.,2015, An Investigation of Tool Wear Using Acoustic Emission and Genetic Algorithm, Journal of Vibration and Control, 21, 3061–3066.
 
16.
LIU C., WANG G.F., LI Z.M., 2015, Incremental Learning for Online Tool Condition Monitoring Using Ellipsoid Artmap Network Model, Applied Soft Computing, 35, 186–198.
 
17.
SALONITIS K., KOLIOS A., 2014, Reliability Assessment of Cutting Tool Life Based on Surrogate Approximation Methods, The International Journal of Advanced Manufacturing Technology, 71/5, 1197–1208.
 
18.
REHORN A.G., JIANG J., ORBAN P.E., 2005, State-of-the-Art Methods and Results in Tool Condition Monitoring: A Review. The International Journal Of Advanced Manufacturing Technology, 26/7, 693—710.
 
19.
KARANDIKAR J., MCLEAY T., TURNER S., SCHMITZ T., 2015, Tool Wear Monitoring Using Naïve Bayes Classifiers, The International Journal of Advanced Manufacturing Technology, 77/9, 1613–1626.
 
20.
FRIEDRICH C., IHLENFELDT S., 2021, Model Calibration for a Rigid Hexapod-Based End-Effector with Integrated Force Sensors, Sensors, 21/10, 3537; https://doi.org/10.3390/s21103....
 
21.
KAUSCHINGER B., FRIEDRICH C., ZHOU R., IHLENFELDT S., 2020, Fast Evaluation of the Volumetric Motion Accuracy of Multi-Axis Machine Tools Using a Double-Ballbar, Journal of Machine Engineering, 20/3, 44–62.
 
22.
FRIEDRICH C., GEIST A., YAQOOB Mf., HELLMICH A., IHLENFELDT S., 2024, Correction of Thermal Errors In Machine Tools by a Hybrid Model Approach, Applied Sciences, 14/2, 671, https://doi.org/10.3390/ app14020671.
 
23.
WEISS A., IHLENFELDT S., 2022, Integration of Opc Ua Information Models Into Enterprise Knowledge Graphs, Journal of Machine Engineering, 22/2, 138—147.
 
24.
UMATI, 2024, OPC 40501 UA for Machine Tools, https://umati.org/industries_m....
 
25.
DRATH R., MOSCH C., HOPPE S., 2023, Diskussionspapier – Interoperabilität mit der Verwaltungsschale, OPC UA und Automationm, Zielbild und Handlungsempfehlungen für Industrielle Interoperabilität.
 
26.
FRAUNHOFER IOSB, 2023, FA³ST Service: Getting Started, https://faaast-service.readthe... /getting-started.html.
 
27.
FRAUNHOFER, 2024, Linked Factory Industrial Digital Twins: Documentation of The Linkedfactory Data Formats and APIs, https://github.com/linkedfacto....
 
28.
ECLIPSE FOUNDATION, 2024, Eclipse Semantic Modelling Framwork (ESMF) Project Documentation - Semantic Aspect Meta Model (SAMM) Introduction, https://eclipse-esmf.github.io... /index.html.
 
29.
W3C, 2024, Sparql 1.1 Federated Query, https://www.w3.org/tr/sparql11....
 
30.
ITDA, 2024, Idta 02008-1-1 Time Series Data, https://industrialdigitaltwin.... 2023/03/idta-02008-1-1_submodel_timeseriesdata.pdf.
 
31.
FRAUNHOFER IOSB, 2024, Edc-Extension-for-AAS, https://github.com/fraunhoferi....
 
32.
ITDA, 2024, Specification of the Asset Administration Shell Part 1 Metamodel, https://industrialdigitaltwin.....
 
33.
KAIROUZ P., MCMAHAN H.B., AVENT B., BELLET A., BENNIS M., BHAGOJI A.N, et al, 2021, Advances and Open Problems in Federated Learning, https://doi.org/10.48550/arXiv....
 
34.
MCMAHAN H.B., MOORE E., RAMAGE D., HAMPSON S., ARCAS B.A., 2023, Communication-Efficient Learning of Deep Networks from Decentralized Data, Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS), Fort Lauderdale, Florida, USA. JMLR: W&CP volume 54.
 
35.
SATTLER F., MÜLLER K-R., SAMEK W., 2019, Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraints, https://doi.org/10.48550/arXiv....
 
eISSN:2391-8071
ISSN:1895-7595
Journals System - logo
Scroll to top