Digital Twin (DT) is an underused tool in the Oil & Gas industry. Today, the behaviour of Oil and Gas plants is realised by the non-real-time analysis software. In contrast, the DT is a framework capable of controlling and managing a plant in real-time by exploiting sensors, virtual spaces, and the continuous connection between real and digital parts. In this paper, the DT of an experimental plant is presented; the DT is based on a model for evaluating the behaviour of an ejector. In contrast to research on DT in the literature, the proposed model is derived from the use of three Artificial Neural Networks (ANNs) and obtains the values of water pressure (ANN1), airflow (ANN3) and water flow (ANN2) at the ejector inlet. The three Multi Layers Perceptron networks, trained on a dataset obtained from the plant, represent the ejector behaviour at 97.85%, 97.79% and 97.94%, the score of each ANN. This modelling approach for DT is currently not widely used but, given the results, is a good alternative to the traditional techniques used.
Artificial Neural Networks approach for Digital Twin modelling of an ejector / Pietrangeli, I.; Mazzuto, G.; Ciarapica, F. E.; Bevilacqua, M.. - 2023-:(2023). (Intervento presentato al convegno 35th European Modeling and Simulation Symposium, EMSS 2023 tenutosi a grc nel 2023) [10.46354/i3m.2023.emss.007].
Artificial Neural Networks approach for Digital Twin modelling of an ejector
Pietrangeli I.;Mazzuto G.;Ciarapica F. E.;Bevilacqua M.
2023-01-01
Abstract
Digital Twin (DT) is an underused tool in the Oil & Gas industry. Today, the behaviour of Oil and Gas plants is realised by the non-real-time analysis software. In contrast, the DT is a framework capable of controlling and managing a plant in real-time by exploiting sensors, virtual spaces, and the continuous connection between real and digital parts. In this paper, the DT of an experimental plant is presented; the DT is based on a model for evaluating the behaviour of an ejector. In contrast to research on DT in the literature, the proposed model is derived from the use of three Artificial Neural Networks (ANNs) and obtains the values of water pressure (ANN1), airflow (ANN3) and water flow (ANN2) at the ejector inlet. The three Multi Layers Perceptron networks, trained on a dataset obtained from the plant, represent the ejector behaviour at 97.85%, 97.79% and 97.94%, the score of each ANN. This modelling approach for DT is currently not widely used but, given the results, is a good alternative to the traditional techniques used.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
