In this paper two Soft Sensors, for the estimation of pollutants in the output flow of a Sour Water Stripping plant, are described. The plant operates in a large refinery in Italy. The Soft Sensors have been implemented by non linear data-driven approaches, by using neural networks. In order to face the issue of different sampling intervals of process and quality variables, a deep learning approach has been adopted. The deep learning approach allowed for exploiting all recorded historical data, solving the typical problem of data scarcity. For sake of comparison, traditional MLP based models have been also identified. Reported results show that the proposed approach improves the performance of neural network based Soft Sensors.

A deep learning based soft sensor for a sour water stripping plant

GRAZIANI, Salvatore
Primo
;
Xibilia, M. G.
Ultimo
2017-01-01

Abstract

In this paper two Soft Sensors, for the estimation of pollutants in the output flow of a Sour Water Stripping plant, are described. The plant operates in a large refinery in Italy. The Soft Sensors have been implemented by non linear data-driven approaches, by using neural networks. In order to face the issue of different sampling intervals of process and quality variables, a deep learning approach has been adopted. The deep learning approach allowed for exploiting all recorded historical data, solving the typical problem of data scarcity. For sake of comparison, traditional MLP based models have been also identified. Reported results show that the proposed approach improves the performance of neural network based Soft Sensors.
2017
9781509035960
File in questo prodotto:
File Dimensione Formato  
paper_imtc17_deepsws_07969924.pdf

solo gestori archivio

Tipologia: Versione Editoriale (PDF)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 1.41 MB
Formato Adobe PDF
1.41 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11570/3119618
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 16
  • ???jsp.display-item.citation.isi??? 0
social impact