Select your language
Directorate for Development and Projects
Risk-based Maintenance prediction using enriched digital twins (2020-1.2.3-EUREKA-2022-00021 )
Project ID: 2020-1.2.3-EUREKA-2022-00021
Project description:
The project's fundamental concept is integrating digital twins of production systems to support the risk analysis and provide an optimization model for scheduling. There are three novelties of the concept:
1) RFID-based sensor solution for complex machine condition monitoring,
2) sensor data-based model mining to discover production machines' statuses, and
3) support the risk analysis and provide an optimization model for scheduling.
We will establish a broad IIoT sensor network that detects the environmental conditions of a plant and internal parameters. Influencing factors such as vibrations and temperature are to be measured, affecting the plant's actuators. On the other hand, the workpieces are to be detected to identify their characteristics using RFID technology. For evaluation of anomalies during production, it is essential that, especially in individual production, it is recognized which type of workpiece is currently being processed and whether the influences on the actuators in the system are usual or unusual. With sensors, we can determine whether, for example, vibrations affect the machine from the exterior and thus influence the internal sensors or whether the machining of the system itself causes these influences because we know which component is currently being machined. We can further determine whether strong vibrations, e.g., at the milling spindle, are usual during machining a given workpiece or whether a short-term defect is about to occur and machining should be stopped. The concept enables the real-time, simultaneous optimization of the production and maintenance. We develop a framework that integrates machine learning models to predict the remaining useful life of the systems and monitor the health of the production units and simulators of digital twins to estimate the consequences of the events. These modules are integrated into the existing CMMS (Computerized maintenance management system) software, will be tested in industrial case studies.
Project duration: 01.10.2023.-30.09.2026.
Total project cost: 1 306 382 EUR
Grant of the Hungarian partners: 194 939 606 Ft
Support rate: 84,92 %
Consortium Leader: University of Pannonia
Consortium partners: University of Pannonia, Silver Frog Ltd., proTEC-Vision Automation
GmbH, University of Stuttgart
Project Cost for University of Pannonia: 100 388 169 Ft
Support rate of the University of Pannonia: 100 %
Research leader: Dr. Tamás Ruppert
Research leader ’s email address:
Project manager: Szabolcs Fehérvölgyi
Project manager's email address: