Your browser doesn't support javascript.
loading
Soft Sensing of LPG Processes Using Deep Learning.
Sifakis, Nikolaos; Sarantinoudis, Nikolaos; Tsinarakis, George; Politis, Christos; Arampatzis, George.
Afiliación
  • Sifakis N; Industrial and Digital Innovations Research Group (INDIGO), School of Production Engineering and Management, Akrotiri Campus, Technical University of Crete, 73100 Chania, Greece.
  • Sarantinoudis N; Industrial and Digital Innovations Research Group (INDIGO), School of Production Engineering and Management, Akrotiri Campus, Technical University of Crete, 73100 Chania, Greece.
  • Tsinarakis G; Industrial and Digital Innovations Research Group (INDIGO), School of Production Engineering and Management, Akrotiri Campus, Technical University of Crete, 73100 Chania, Greece.
  • Politis C; Industrial and Digital Innovations Research Group (INDIGO), School of Production Engineering and Management, Akrotiri Campus, Technical University of Crete, 73100 Chania, Greece.
  • Arampatzis G; Industrial and Digital Innovations Research Group (INDIGO), School of Production Engineering and Management, Akrotiri Campus, Technical University of Crete, 73100 Chania, Greece.
Sensors (Basel) ; 23(18)2023 Sep 13.
Article en En | MEDLINE | ID: mdl-37765914
This study investigates the integration of soft sensors and deep learning in the oil-refinery industry to improve monitoring efficiency and predictive accuracy in complex industrial processes, particularly de-ethanization and debutanization. Soft sensor models were developed to estimate critical variables such as the C2 and C5 contents in liquefied petroleum gas (LPG) after distillation and the energy consumption of distillation columns. The refinery's LPG purification process relies on periodic sampling and laboratory analysis to maintain product specifications. The models were tested using data from actual refinery operations, addressing challenges such as scalability and handling dirty data. Two deep learning models, an artificial neural network (ANN) soft sensor model and an ensemble random forest regressor (RFR) model, were developed. This study emphasizes model interpretability and the potential for real-time updating or online learning. The study also proposes a comprehensive, iterative solution for predicting and optimizing component concentrations within a dual-column distillation system, highlighting its high applicability and potential for replication in similar industrial scenarios.
Palabras clave

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Tipo de estudio: Prognostic_studies Idioma: En Revista: Sensors (Basel) Año: 2023 Tipo del documento: Article País de afiliación: Grecia Pais de publicación: Suiza

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Tipo de estudio: Prognostic_studies Idioma: En Revista: Sensors (Basel) Año: 2023 Tipo del documento: Article País de afiliación: Grecia Pais de publicación: Suiza