The increased flexibility resulting from the modularization of process plants requires an advanced strategy to supervise the distributed control systems (DCSs). The connection and coordination of multiple process equipment assemblies (PEAs) into a modular plant (MP) is called orchestration and conducted in a so‐called process orchestration layer (POL). Standardized interfaces enable a seamless integration of PEAs into an MP. Current process control systems do not yet meet all required features regarding to interfaces and possibility of import/export of different data structures. Several aspects are presented which shall be taken into account when designing a POL. The POL's several layers are described in detail, resulting especially in flexibility and reusability of modular plants.
Modulare Prozesseinheiten ermöglichen den flexiblen Aufbau prozesstechnischer Anlagen und damit eine schnelle Reaktion auf volatile Märkte und wechselnde Prozessbedingungen. In diesem Beitrag wird eine Methode zur Validierung dieser Anlagen mittels virtueller Inbetriebnahme vorgestellt. Dazu werden Wasserfahrtmodelle der zu kombinierenden Prozesseinheiten miteinander verbunden. Durch die Beschreibung über das Module Type Package und die Integration in eine virtuelle Anlage kann das Verhalten simuliert und die funktionale Eignung über die Ausführung von Rezepten analysiert werden.
Mounting sensors in disk stack separators is often a major challenge due to the operating conditions. However, a process cannot be optimally monitored without sensors. Virtual sensors can be a solution to calculate the sought parameters from measurable values. We measured the vibrations of disk stack separators and applied machine learning (ML) to detect whether the separator contains only water or whether particles are also present. We combined seven ML classification algorithms with three feature engineering strategies and evaluated our model successfully on vibration data of an experimental disk stack separator. Our experimental results demonstrate that random forest in combination with manual feature engineering using domain specific knowledge about suitable features outperforms all other models with an accuracy of 91.27 %.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.