Most machines, equipment and other industrial assets are nowadays maintained based on preventive
maintenance practices. Preventive maintenance ensures that maintenance processes are undertaken
at regular intervals in order to prevent equipment failure that could lead to quality degradation of
industrial processes (e.g., wear in manufacturing production), as well as “expensive” unplanned
downtime. Overall, preventive maintenance processes do not lead to optimal OEE (Overall Equipment
Eciency). O3 modules enable the evolution of maintenance processes from a preventive to a
predictive paradigm. Predictive maintenance involves the automated forecasting of a machine’s
end-of-life (EOL) based on the combination and processing of data associated with a variety of
sensors and other indicators that relate to the status of an asset. For example, the EOL of a machine
can be estimated based on the combination of sensor data streams from vibration, temperature
ultrasonic and acoustic sensors, as well as from thermal images.
With an accurate prediction of a machine’s EOL at hand,
predictive maintenance processes are capable of identifying
the optimal time slot for scheduling & performing the
maintenance, taking into account the status of industrial
operations(e.g., pending production orders) as reected in
business information systems (e.g., ERP and asset
management systems). In this way, predictive maintenance
optimizes OEE and yields a considerable ROI.
ODS implement the said use case in terms of productivity and production order
management in Sunbullah food and Zamil plastics. And enable their Digital
Transformation Journey and ensure sustainability by providing insights into all
facets of their manufacturing processes to reduce operating costs and improve
plant performance