Mahr F, Kratzke C, Franke J, Ockel M (2026)
Publication Type: Conference contribution
Publication year: 2026
Publisher: Institute of Electrical and Electronics Engineers Inc.
Pages Range: 359-360
Conference Proceedings Title: 2026 International Conference on Electronics Packaging and Hybrid Bonding Symposium, ICEP-HBS 2026
ISBN: 9784991483516
DOI: 10.23919/ICEP-HBS69241.2026.11550601
Unplanned downtime in Surface-Mount Technology (SMT) production represents a critical bottleneck for achieving high Overall Equipment Effectiveness (OEE). While Predictive Maintenance systems detect trend anomalies, they lack the transition to actionable Prescriptive Maintenance with multi-dimensional instructions. This paper introduces the architecture of a prescriptive maintenance system built upon a Multi-Agent System (MAS) leveraging Large Language Models (LLMs). The system generates context-aware maintenance recommendations in real-time, even from uncertain anomaly data, transforming one-dimensional predictions into human-centric instructions.
APA:
Mahr, F., Kratzke, C., Franke, J., & Ockel, M. (2026). Towards a multi-agent-based diagnostic system for prescriptive maintenance applications in industrial environments. In 2026 International Conference on Electronics Packaging and Hybrid Bonding Symposium, ICEP-HBS 2026 (pp. 359-360). Hiroshima, JP: Institute of Electrical and Electronics Engineers Inc..
MLA:
Mahr, Felix, et al. "Towards a multi-agent-based diagnostic system for prescriptive maintenance applications in industrial environments." Proceedings of the 25th International Conference on Electronics Packaging, held in conjunction with the IEEE EPS Hybrid Bonding Symposium, ICEP-HBS2026, Hiroshima Institute of Electrical and Electronics Engineers Inc., 2026. 359-360.
BibTeX: Download