| Name: | Description: | Size: | Format: | |
|---|---|---|---|---|
| 466.18 KB | Adobe PDF |
Authors
Advisor(s)
Abstract(s)
The digital transformation of industrial environments requires the ability to collect, process, and integrate data from production systems in real time. However, many manufacturing facilities operate with legacy equipment that is perfectly functional and operational but lacks native connectivity or standardized interfaces for data acquisition. This paper presentes an approach to enable industrial digitalization through the implementation of a network architecture at the Operational Technology (OT) level that facilitates the collection of structured data from legacy and modern machines. The proposed solution ensures integration between production systems and supervisory platforms, supporting real-time monitoring through SCADA systems and providing relevant information for predictive maintenance strategies. The proposal is based on the implementation of a standardized and secure communication infrastructure between the shop floor and higher-level Information Technology (IT) systems, aligning with the principles of Industry 4.0. The solution has been implemented in a real industrial scenario, is fully operational and the results demonstrate significant benefits of integrating heterogeneous industrial assets into a unified data ecosystem, improving process insight, operational efficiency and supporting maintenance
decision-making.
Description
The authors would like to thank the industrial unit "The Navigator Company – Navigator Tissue Ródão S.A", for the opportunity and support provided during the implementation of the proposed solution on its shop floor.
Keywords
Industry 4.0 OPC UA Legacy equipment integration Industrial digitalization
Pedagogical Context
Citation
BOCHAROV, Nikita ; TORRES, Pedro M.B. ; MATOS, João (2025) - A practical approach to industrial digitalization through data acquisition and systems integration for predictive maintenance. EAI Endorsed Transactions on Digital Transformation of Industrial Processes. Vol. 1, issue 2 . DOI: 10.4108./dtip.9700
