The Design of a Digital-Twin for Predictive Maintenance

Predictive maintenance in a manufacturing company is strategic, in order to maintain high production quality and to avoid unexpected production downtimes. In this scenario, the prediction of future machineries health status is necessary in order to plan maintenance cycles and to optimize the production. The proposed approach relies on the use of Electronic Design Automation (EDA) techniques mapped from the electronic domain to the production line domain. This paper proposes a general framework based on the EDA approach that allows to set-up a maintenance strategy by analyzing data retrieved from sensors. An MSM, is associated to each observable measurement, while a Supervisor monitors the current state of each Monitoring State Machine (MSM) by raising alerts when the monitored equipment is deviating from its normal behavior. This framework is the Digital-Twin of the plant devoted to its monitoring. It has some execution modalities ranging from online monitoring to predictive maintenance. The methodology has been applied to a mechanical transmission system showing its effectiveness.