• DocumentCode
    2619027
  • Title

    Stacking approaches for the design of soft sensors using small data set

  • Author

    Di Bella, A. ; Graziani, S. ; Napoli, G. ; Xibilia, M.G.

  • Author_Institution
    DIEES, Univ. degli Studi di Catania, Catania
  • fYear
    2008
  • fDate
    25-27 June 2008
  • Firstpage
    1810
  • Lastpage
    1815
  • Abstract
    In this paper a number of approaches to design a soft sensor for an industrial plant in case of small data set are compared. In particular different strategies to aggregate suboptimal models obtained by bootstrapped neural networks and noise injection are considered. An industrial case of study, consisting in the estimation of the T95% of a Thermal Cracking Unit (TCU) of a refinery in Sicily is considered to evaluate the performance of the different approaches.
  • Keywords
    data structures; industrial engineering; neural nets; virtual instrumentation; bootstrapped neural network; industrial plant; noise injection; small data set; soft sensor design; stack approach; Aggregates; Automatic control; Design automation; Industrial plants; Monitoring; Neural networks; Petroleum; Refining; Stacking; Training data; Industrial plants; neural models; small data sets; soft sensors; stacking approaches;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Control and Automation, 2008 16th Mediterranean Conference on
  • Conference_Location
    Ajaccio
  • Print_ISBN
    978-1-4244-2504-4
  • Electronic_ISBN
    978-1-4244-2505-1
  • Type

    conf

  • DOI
    10.1109/MED.2008.4602160
  • Filename
    4602160