In the paper, a method for improving the performance of data-driven Soft Sensors in the presence of small datasets problems is proposed. The method is based on a preliminary feature extraction phase, followed by a data selection method. Selected data are used to train neural-network-based Soft Sensors, modeling the featureoutput nonlinear relationship. A case of study referring to a Sour Water Stripping plant is used in the paper to validate the suitability of the proposed methodology.

Improving soft sensors performance in the presence of small datasets by data selection

Xibilia M. G.
Ultimo
2020-01-01

Abstract

In the paper, a method for improving the performance of data-driven Soft Sensors in the presence of small datasets problems is proposed. The method is based on a preliminary feature extraction phase, followed by a data selection method. Selected data are used to train neural-network-based Soft Sensors, modeling the featureoutput nonlinear relationship. A case of study referring to a Sour Water Stripping plant is used in the paper to validate the suitability of the proposed methodology.
2020
978-1-7281-4460-3
File in questo prodotto:
File Dimensione Formato  
imtc_xibi_2020.pdf

solo gestori archivio

Tipologia: Versione Editoriale (PDF)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 1.5 MB
Formato Adobe PDF
1.5 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/11570/3180529
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 3
  • ???jsp.display-item.citation.isi??? ND
social impact