MLOps for Cyberphysical Production Systems: Challenges and SolutionsShow others and affiliations
2025 (English)In: IEEE Software, ISSN 0740-7459, E-ISSN 1937-4194, Vol. 42, no 1, p. 65-73Article in journal (Refereed) Published
Abstract [en]
While machine learning operations (MLOps) have received significant interest, much less work has been published addressing MLOps in industrial production settings lately, particularly if solutions are not cloud based. This article addresses this shortcoming based on our and our partner's real industrial experience across different application domains.
Place, publisher, year, edition, pages
IEEE COMPUTER SOC , 2025. Vol. 42, no 1, p. 65-73
Keywords [en]
Data models; Production; Inspection; Training; Task analysis; Chemicals; Production systems
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:liu:diva-210638DOI: 10.1109/MS.2024.3441101ISI: 001373292400004Scopus ID: 2-s2.0-85201304541OAI: oai:DiVA.org:liu-210638DiVA, id: diva2:1925228
Note
Funding Agencies|German Federal Ministry of Education [01-S22030E]; Netherlands Enterprise Agency RVO [AI212001]; Sweden's Innovation Agency (Vinnova) [2021-04336]; German Ministry of Economics; Climate Action (BMWK) [01MK20006C]
2025-01-082025-01-082025-05-05