Abstract
The introduction and adoption of various semantic models for describing assets within a plant have paved the way for new opportunities. This contribution centers on the establishment and continuous maintenance of a plant asset management system based on knowledge graphs, utilizing the information contained in various semantic models. Additionally, it highlights how the graph can be leveraged in the creation and configuration of AI-based anomaly detection models, aimed at the monitoring of measurement values in a process plant. The concept paves the way for the wide deployment of AI models in monitoring applications in process industry.
Zusammenfassung
Die Etablierung und Einführung verschiedener semantischer Modelle zur Beschreibung von Assets innerhalb einer Anlage bilden die Grundlage für neue Anwendungsmöglichkeiten. In diesem Beitrag steht die Einrichtung und kontinuierliche Pflege eines auf Wissensgraphen basierenden Anlagenmanagementsystems im Fokus, das die in verschiedenen Modellen enthaltenen Informationen integriert. Darüber hinaus wird aufgezeigt, wie der Graph für die Erstellung und Konfiguration von KI-basierte Modellen zur Erkennung von Anomalien genutzt werden kann, die auf die Überwachung von Messwerten in einer Prozessanlage abzielen. Das Konzept ebnet den Weg für den umfangreichen Einsatz von KI-Modellen in Überwachungsanwendungen für Prozessindustrie.
About the authors
Ramy Hana graduated in electrical Engineering with a specialisation in process automation from TU-University in 2020. He worked as an intern for Bayer AG in the process performance improvement department where he developed an anomaly detection library for the purpose of process monitoring. In 2021, he joined the chair of Information and Automation Systems at the RWTH Aachen University with a research focus on field device performance monitoring.
Tobias Kleinert graduated in Mechanical Engineering at RWTH Aachen University and completed his PhD in 2005 at the chair of Prof. Jan Lunze at Ruhr-Universität Bochum. Until 2020, he worked at BASF in the fields of Advanced Control, Process Control Systems, Manufacturing Execution Systems, Functional Safety, Digitalization and Smart Manufacturing. Since 2020, he is head of Chair of Information and Automation Systems at RWTH, with a focus on data management and flexible automation in industrial productions.
-
Research ethics: Not applicable.
-
Author contributions: The authors have accepted responsibility for the entire content of this manuscript and approved its submission.
-
Competing interests: The authors state no conflict of interest.
-
Research funding: None declared.
-
Data availability: The raw data can be obtained on request from the corresponding author.
References
[1] A. Lüder and N. Schmidt, “AutomationML in a nutshell,” in Handbuch Industrie 4.0 Bd. 2: Automatisierung, Berlin, Heidelberg, Springer Berlin Heidelberg, 2017, pp. 213–258.10.1007/978-3-662-53248-5_61Search in Google Scholar
[2] S. Bader, et al.., “Details of the asset administration shell. Part 1 the exchange of information between partners in the value chain of industrie 4.0,” vol. 3.0, RC02 Germany, IDTA & ZVEI, 2022. Available at: https://www.plattform-i40.de/IP/Redaktion/EN/Downloads/Publikation/Details_of_the_Asset_Administration_Shell_Part1_V3.html [accessed 26.07.2024].Search in Google Scholar
[3] DEXPI Initiative,[Online]. “DEXPI data exchange in the process industry - Version 1.3,” 2021. [Online.] Available at: http://www.dexpi.org/specifications.Search in Google Scholar
[4] W. Marquardt, J. Morbach, A. Wiesner, and A. Yang, OntoCAPE: A Re-Usable Ontology for Chemical Process Engineering, Germany, Springer Publishing Company, Incorporated, 2010.10.1007/978-3-642-04655-1Search in Google Scholar
[5] NAMUR, “NE129: plant asset management,” NAMUR, 2009. Available at: https://www.namur.net.Search in Google Scholar
[6] A. Fan, C. Gardent, C. Braud, and A. Bordes, “Using local knowledge graph construction to scale seq2seq models to multi-document inputs,” arXiv preprint arXiv:1910.08435, 2019.10.18653/v1/D19-1428Search in Google Scholar
[7] A. Grigoriev, J. Van De Klundert, and F. C. Spieksma, “„Modeling and solving the periodic maintenance problem,” Eur. J. Oper. Res., vol. 172, no. 3, pp. 783–797, 2006. https://doi.org/10.1016/j.ejor.2004.11.013.Search in Google Scholar
[8] S. Luftensteiner, M. Mayr, G. C. Chasparis, and P. Mario, “Avubdi: a versatile usable big data infrastructure and its monitoring approaches for process industry,” Front. Chem. Eng., vol. 3, 2021. https://doi.org/10.3389/fceng.2021.665545.Search in Google Scholar
[9] A. Barthelmey, E. Lee, R. Hana, and J. Deuse, “Dynamic digital twin for predictive maintenance in flexible production systems,” in IECON 2019 – 45th Annual Conference of the IEEE Industrial Electronics Society, vol. 1, 2019, pp. 4209–4214.10.1109/IECON.2019.8927397Search in Google Scholar
[10] S. Fang, et al.., “An integrated system for regional environmental monitoring and management based on internet of things,” IEEE Trans. Ind. Inf., vol. 10, no. 2, pp. 1596–1605, 2014. https://doi.org/10.1109/tii.2014.2302638.Search in Google Scholar
[11] D. Hästbacka, L. Barna, M. Karaila, Y. Liang, P. Tuominen, and S. Kuikka, “Device status information service architecture for condition monitoring using OPC UA,” in Proceedings of the 2014 IEEE Emerging Technology and Factory Automation (ETFA), 2014, pp. 1–7.10.1109/ETFA.2014.7005141Search in Google Scholar
[12] A. Veichtlbauer, M. Ortmayer, and T. Heistracher, “OPC UA integration for field devices,” in IEEE 15th International Conference on Industrial Informatics (INDIN), 2017, pp. 419–424.10.1109/INDIN.2017.8104808Search in Google Scholar
[13] R. Henßen and M. Schleipen, “Interoperability between OPC UA and AutomationML,” Proc. CIRP, vol. 25, pp. 297–304, 2014, https://doi.org/10.1016/j.procir.2014.10.042.Search in Google Scholar
[14] S. Grüner, P. Weber, and U. Epple, “Rule-based engineering using declarative graph database queries,” in 12th IEEE International Conference on Industrial Informatics (INDIN), 2014, pp. 274–279.10.1109/INDIN.2014.6945520Search in Google Scholar
[15] C. von Trotha, T. Kleinert, and U. Epple, “Ein Konzept zur Kontextualisierung von Prozessdaten: Der erste Schritt auf dem Weg zur datenzentrierten Handlung,” Atp Mag., vol. 62, no. 10, pp. 68–76, 2020. https://doi.org/10.17560/atp.v62i10.2502.Search in Google Scholar
[16] Siemens, 2020, [Online]. Available at: https://support.industry.siemens.com/cs/document/109760571/asset-und-process-performance-suite-f%C3%BCr-industrielle-applikationen-und-services-zur-anlagen%C3%BCberwachung?dti=0&lc=de-DE Accessed: Nov. 3, 2023.Search in Google Scholar
[17] R. A. D. l. I. (READI), “READI,” The Norwegian Sector Board of Petroleum, 2022, [Online]. Available at: https://readi-jip.org/asset-information-modelling-framework/ Accessed: Nov. 3, 2023.Search in Google Scholar
[18] R. Hana, I. Ünal, and T. Kleinert, “Scaling up anomaly detection in measurement data for process plants,” Automation 2023, supp. VDI-Berichte Nr. 2419, pp. 915–926, 2023. https://doi.org/10.51202/9783181024195-915.Search in Google Scholar
[19] R. Hana and T. Kleinert, “Semantic models for field device performance monitoring in the process industry in the context of industry 4.0,” Automation 2023, supp. VDI-Berichte Nr. 2419, pp. 233–243, 2023. https://doi.org/10.51202/9783181024195-233.Search in Google Scholar
[20] K. Matthews and H. Harris, “Maintaining knowledge assets,” in Engineering Asset Management, London, Springer London, 2006, pp. 618–626.10.1007/978-1-84628-814-2_67Search in Google Scholar
[21] H. Van de Water, “A maintenance model for quality management,” Int. J. Qual. Reliab. Manag., vol. 7, no. 17, pp. 756–770, 2000. https://doi.org/10.1108/02656710010319838.Search in Google Scholar
[22] NAMUR, “NE159: standardized NAMUR interface for data exchange between CAE systems for process design and CAE systems for PCT hardware planning,” NAMUR, 2018. Available at: https://www.namur.net.Search in Google Scholar
[23] Rösberg, “ProDOK: process control engineering,” Rösberg, 2023. Available at: https://prodok.roesberg.com/.Search in Google Scholar
[24] M. Gärtler, et al.., “Machine learning approaches for phase identification using process variables in batch processes,” Chem. Ing. Tech., vol. 7, no. 95, pp. 989–1002, 2023. https://doi.org/10.1002/cite.202200231.Search in Google Scholar
[25] G. Stanley and R. Mah, “Observability and redundancy in process data estimation,” Chem. Eng. Sci., vol. 36, no. 2, pp. 259–272, 1981. https://doi.org/10.1016/0009-2509(81)85004-x.Search in Google Scholar
[26] B. R. Bakshi, “Multiscale PCA with application to multivariate statistical process monitoring,” AIChE J., vol. 44, no. 7, pp. 1596–1610, 1998. https://doi.org/10.1002/aic.690440712. Available at: https://aiche.onlinelibrary.wiley.com/doi/abs/10.1002/aic.690440712.Search in Google Scholar
[27] S. Guo and W. Guo, “Process monitoring and fault prediction in multivariate time series using bag-of-words,” IEEE Trans. Autom. Sci. Eng., vol. 19, no. 1, pp. 230–242, 2022. https://doi.org/10.1109/tase.2020.3026065.Search in Google Scholar
[28] A. Tulsyan, C. Garvin, and C. Ündey, “Advances in industrial biopharmaceutical batch process monitoring: machine-learning methods for small data problems,” Biotechnol. Bioeng., vol. 115, no. 8, pp. 1915–1924, 2018. https://doi.org/10.1002/bit.26605.Search in Google Scholar PubMed
[29] E. Quatrini, F. Costantino, G. Di Gravio, and R. Patriarca, “Machine learning for anomaly detection and process phase classification to improve safety and maintenance activities,” J. Manuf. Syst., vol. 56, pp. 117–132, 2020, https://doi.org/10.1016/j.jmsy.2020.05.013.Search in Google Scholar
[30] W. Li, S. Heppner, R. S. L. Hana, I. Kornijez, T. H. Miny, and T. T. Kleinert, “Praktische Anwendung von Verwaltungsschale zum Aufbau eines Digitalen Zwillings einer hierarchischen Prozessanlage in Laborumgebung,” in Transformation by automation : Automation 2023 : 24. Leitkongress der Mess- und Automatisierungstechnik, 2023, pp. 137–152.10.51202/9783181024195-137Search in Google Scholar
[31] T. Kohonen, “The self-organizing map,” Proc. IEEE, vol. 78, no. 9, pp. 1464–1480, 1990. https://doi.org/10.1109/5.58325.Search in Google Scholar
© 2024 Walter de Gruyter GmbH, Berlin/Boston