Modern approaches to processing technological information in industrial automation systems based on knowledge bases

Authors

DOI:

https://doi.org/10.31548/

Abstract

This article is dedicated to the analysis of existing approaches and the synthesis of novel methods for processing technological information in industrial automation systems in the context of modeling digital twins of various interconnected sections and systems. The aim of the research is to analyze the challenges of knowledge base modeling and improve the efficiency of information processing by considering heterogeneous data. The study focuses on the automation systems of three sugar production sections: diffusion, defecosaturation, and evaporation. As part of the research, a general associative map was developed, enabling the structured organization of industrial automation systems, establishing relationships, and enriching data with context for further processing. A semantic knowledge base model was designed to define data influence zones and generate a data schema that accounts for data heterogeneity. The developed semantic model allows for rapid contextual and criteria-based searches, analysis of subsystem interactions, and the calculation of similarity levels in data and anomalies, which is crucial for mathematical modeling and the synthesis of multi-layered or cognitive digital twins of processes. Based on the semantic model, a production section visualization model was created, integrating technological documentation, SCADA system data, industrial data archives, external sources, and knowledge bases via the web using meta-knowledge. Using the Clojure programming language, search queries were generated to explore influence zones, context and mentions, as well as to calculate knowledge similarity. This approach enables the integration of multiple system models without significant additional costs, ultimately defining the structure of the digital twin while accounting for potential changes in knowledge systems. This ensures a systematic and efficient approach to data collection, processing, storage, and integration with other technological systems. An additional advantage is the ability to combine individual, already described digital twins into a multi-layered comprehensive model, providing a detailed representation of the technological process and enhancing decision-making efficiency.

Key words: ontology, digital twin, knowledge base, data, intelligent knowledge management systems, automation

References

1. Gao, T., Chai, Y. and Liu, Y. (2018). A review of knowledge management about theoretical conception and designing approaches. International Journal of Crowd Science, 2 (1), 42–51. Available at: https://doi.org/10.1108/ijcs-08-2017-0023

2. Chavez, V., Wollert, J. (2024). Development of an Industry 4.0 Ontology to Enable Semantic Interoperability at the Field Level, Sensors and Transducers, 265 (2), 139–147. Available at: https://www.researchgate.net/publication/381120487

3. Singh, S., Shehab, E., Higgins, N., Fowler, K., Reynolds, D., Erkoyuncu, J.A., Gadd, P. (2020). Data management for developing digital twin ontology model. Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture, 235 (14), 2323–2337. Available at: https://doi.org/10.1177/0954405420978117

4. Kafeza, E., Drakpopoulos, G., Mylonas, P. (2024). Graph Neural Networks in PyTorch for Link Prediction in Industry 4.0 Process Graphs. IFIP Advances in Information and Communication Technology, 220–234. Available at: https://doi.org/10.1007/978-3-031-63219-8_17

5. Cimino, A., Longo, F., Mirabelli, G., Solina, V., Verteramo, S. (2024). An ontology-based, general-purpose and Industry 4.0-ready architecture for supporting the smart operator (Part II – Virtual Reality case). Journal of Manufacturing Systems, 73, 52–64. Available at: https://doi.org/10.1016/j.jmsy.2024.01.001

6. D’Amico, R.D., Sarkar, A., Karray, M.H., Addepalli, S., Erkoyuncu, J.A. (2024). Knowledge transfer in Digital Twins: The methodology to develop Cognitive Digital Twins // CIRP Journal of Manufacturing Science and Technology, 52, 366–385. Available at: https://doi.org/10.1016/j.cirpj.2024.06.007

7. Zheng, X., Petrali, P., Lu, J., Turrin, C., Kiritsis, D. (2022). RMPFQ: A Quality-Oriented Knowledge Modelling Method for Manufacturing Systems Towards Cognitive Digital Twins // Frontiers in Manufacturing Technology, 2. Available at: https://doi.org/10.3389/fmtec.2022.901364

8. Rongen, S., Nikolova, N., Mark (2023). Modelling with AAS and RDF in Industry 4.0. Computers in Industry, 148, 103910: https://doi.org/10.1016/j.compind.2023.103910

9. Valdez-Valenzuela, A., Gómez-Adorno, H. (2024). text2graphAPI: A library to transform text documents into different graph representations. SoftwareX, 101888. Available at: https://doi.org/10.1016/j.softx.2024.101888

10. Blankenberg, C., Gebel-Sauer, B., Schubert, P. (2022). Using a graph database for the ontology-based information integration of business objects from heterogenous Business Information Systems. Procedia Computer Science, 314–323. Available at: https://doi.org/10.1016/j.procs.2021.12.019

11. Sun, Q., Luo, Y., Zhang, W., Li, S., Li, J., Niu, K., Kong, X., Liu, W. (2024). Docs2KG: Unified Knowledge Graph Construction from Heterogeneous Documents Assisted by Large Language Models. arXiv. Available at: https://arxiv.org/abs/2406.02962

12. Abonyi, J., Nagy, L., Tamás (2024). Ontology-Based Development of Industry 4.0 and 5.0 Solutions for Smart Manufacturing and Production. Available at: https://books.google.com.ua/books?hl=ru&lr=&id=_bfrEAAAQBAJ&oi=fnd&pg=PR5&dq=ontology+knowledge+management+in+SCADA&ots=_UDeFsHuOX&sig=b_9W_QTb-NfAHVicu-CQkJ6aeIE&redir_esc=y#v=onepage&q=ontology%20knowledge%20management%20in%20SCADA&f=false

13. Gebreab, S., Musamih, A., Salah, K., Jayaraman, R., Boscovic, D. (2024). Accelerating Digital Twin Development with Generative AI: A Framework for 3D Modeling and Data Integration. IEEE Access, 1–1. Available at: https://doi.org/10.1109/access.2024.3514175

Published

2025-06-26

Issue

No. 2 (2025)

Section

Статті

License

Relationship between right holders and users shall be governed by the terms of the license Creative Commons  Attribution – non-commercial – Distribution On Same Conditions 4.0 international (CC BY-NC-SA 4.0):https://creativecommons.org/licenses/by-nc-sa/4.0/deed.uk

Authors who publish with this journal agree to the following terms:

  • Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
  • Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
  • Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).