Anna-Lena Hager, Shubham Sharma, Lisa Sonnleithner,
"Variability-Driven Knowledge Discovery in IEC 61499 Systems, IEEE 2024"
: Proceedings of the IEEE International Conference on Emerging Technologies and Factory Automation (ETFA 2024), IEEE, New York, USA, Seite(n) 1-4, 10-2024, ISBN: 979-8-3503-6123-0
Original Titel:
Variability-Driven Knowledge Discovery in IEC 61499 Systems, IEEE 2024
Sprache des Titels:
Englisch
Original Buchtitel:
Proceedings of the IEEE International Conference on Emerging Technologies and Factory Automation (ETFA 2024)
Original Kurzfassung:
Cyber-physical production systems (CPPSs) are advanced manufacturing systems that integrate the latest information technology techniques to enable flexible and adaptive production processes. The IEC 61499 standard defines a domain-specific modeling language for developing control software for distributed CPPSs. In CPPS, as well as in other domains, variability must be managed. However, effective management first requires the identification and extraction of this variability. Thus, this paper aims to explore and implement machine learning-based Knowledge Discovery techniques within the IEC 61499 standard. By employing a first case study, we demonstrate how to extract variability in IEC 61499-based applications. Our approach leverages techniques such as Term Frequency Inverse Document Frequency (TF-IDF) vectorization and cosine similarity to identify and cluster variations in software components. In the future, we plan to apply this approach to a greater scope of the IEC 61499 standard and develop evaluation methods to validate and improve our methodology. From the first results, integrating machine learning-based Knowledge Discovery techniques into the IEC 61499 standard shows potential for effectively extracting variability from control software.
Forschungs-