Proactive Decision Making Module
On the basis of (near) real-time predictions about future failures that lay outside the “normal states space”, UPTIME_DECIDE is enacted online in order to generate proactive action recommendations, i.e. recommendations about optimal (perfect or imperfect) maintenance actions and the optimal times of proactive action implementation. To do this, it estimates when the Expected Maintenance Loss will be minimized.
KEY ADVANTAGES OF UPTIME_DECIDE :
• Brings prescriptive analytics into predictive maintenance for facilitating proactive decision making
• Processes streams of predictions in a scalable and efficient way
• Able to recommend actions for both perfect and imperfect (of various degrees) maintenance
• Models the decision-making process instead of the physical manufacturing process. In this way, it is generic and applicable to various manufacturing processes
DECISION MAKING IN PREDICTIVE MAINTENANCE
Industry 4.0 has led to an extensive use of sensors for condition monitoring, something which facilitates decision making under time constraints.
Decision making in predictive maintenance indicates the phase which is triggered by sensor-driven, (near) real-time predictions (e.g. about a future failure mode) in order to generate proactive recommendations about maintenance actions and plans that eliminate or mitigate the impact of the predicted equipment failures.
The P-F interval, i.e. the time between the point where it can be found out that it is failing (potential failure) and the point where it has failed (functional failure), can be seen as an opportunity window during which decision making algorithms can recommend actions with the aim to eliminate the anticipated functional failure or mitigate its effect. However, the stochastic degradation process leads to high uncertainty in (near) real-time decision making.
MINIMIZE EXPECTED MAINTENANCE LOSS
The UPTIME_DECIDE component shifts decision making in predictive maintenance from early warnings into business performance optimization by eliminating or mitigating the impact of a future failure. On the basis of (near) real-time predictions about future failures that lay outside the “Normal states space”, UPTIME_DECIDE is enacted online in order to generate proactive actions recommendations, i.e. recommendations about optimal (perfect or imperfect) maintenance actions and the optimal times of proactive actions implementation. To do this, it estimates when the Expected Maintenance Loss will be minimized.
For example, for 3 alternative actions (Action 1, Action 2, Action 3), the recommendation includes the action (Action 2) and the time with the minimum expected loss. Upon user feedback, the UPTIME_DECIDE component formulates the maintenance plan.
UPTIME Other Modules :
UPTIME_DETECT aims to identify the topical state/condition of technical equipment by continuously observing sensor data streams. UPTIME_PREDICT includes abnormal behaviour of technical equipment and accordingly the classification of the condition state (simple example could be traffic light indication such as green, yellow red state). This is done by the possibility to orchestrate so‐called calculation flows based on diagnosis and prediction algorithms that are already built in the algorithmic framework of the tool or that are built on purpose by implementing a simple programming interface.
UPTIME FMECA, Failure Modes Effects and Criticality Analysis, aims to assess failure impacts of a system components. The FMECA component starts from the identification of the failure modes (i.e. how something can break down or fail) associated to each system’s component of an equipment and analyse the impact of such failures on the whole system according to its physical and logical design.
UPTIME_ANALYZE is a data analytics engine driven by the need to leverage manufacturers’ legacy data and operational data related to maintenance, and to extract and correlate relevant knowledge. The ANALYZE component is designed to handle data‐at‐rest which signify data collected from various sources and physically stored across different manufacturers’ information systems.
UPTIME_VISUALIZE provides configurable visualization to save time analysing data and getting insights, to support decision making and develop new solutions.
Lepenioti K., Bousdekis A., Apostolou D., Mentzas G. (2019) – International Journal of Information Management, vol 50, 57-70, Elsevier
Bousdekis A., Mentzas G., Hribernik K., Lewandowski M., von Stietencron M., Thoben KD. (2019) – IN: Popplewell K., Thoben KD., Knothe T., Poler R. (eds) Enterprise Interoperability VIII. Proceedings of the I-ESA Conferences, vol 9. Springer, Cham
Lepenioti K., Bousdekis A., Apostolou D., Mentzas G. (2019) – IN: Abramowicz W., Paschke A. (eds) Business Information Systems Workshops. BIS 2018. Lecture Notes in Business Information Processing, vol 339. Springer, Cham
Bousdekis A., Mentzas G. (2018) – IN: Sifaleras A., Petridis K. (eds) Operational Research in the Digital Era – ICT Challenges. Springer Proceedings in Business and Economics (pp. 23-45). Springer, Cham
Bousdekis, A., Papageorgiou, N., Magoutas, B., Apostolou, D., & Mentzas, G. (2018) – Computers in Industry, 100, 173-183
Bousdekis, A., Papageorgiou, N., Magoutas, B., Apostolou, D., & Mentzas, G. (2017) -International Journal of Monitoring and Surveillance Technologies Research (IJMSTR), 5(4), 38-62