Zusammenfassung
A key performance indicator for sensors in production systems is their accuracy. In order to respond to the flexible requirements posed to production systems, there are currently two possibilities to realize the needed accuracy. Either the sensors can be changed frequently, so that the lowest still sufficient accuracy can always be achieved or the production system can be equipped directly with highly accurate sensors. These two options come with high costs, originating from the manual effort and the proportionality of accuracy and cost for most of the commonly used sensors. Industrially used resistance-based sensors such as pressure, force or temperature sensors represent a special case here, because their inaccuracy traces back to few major sources. To eliminate some of these sources or to decrease their impacts, instance-specific characteristics are used in an accuracy model provided by an intelligent Digital Twin. Using varying accuracy models provides different levels of accuracy. The presented concept provides the needed accuracy permanently or as a service for periods the production system needs the higher accuracy, called Accuracy-as-a-Service (AaaS), benefiting setup efficiency, costs and flexibility. To validate the presented concept, the proposed model is used for an analog pressure sensor in a fluidic test setup. The control unit of the system is provided with a standard model as well as a more accurate one. It is demonstrated in the paper how the usage of the individual model can improve the accuracy of a special sensor significantly by a factor of four.
Nutzer
