Publication:

Multivariate statistical methods in bioprocess fault detection and performance forecasting (1997)

Author(s): M. Ignova;J. Glassey;A. C. Ward;G. A. Montague

  • : Multivariate statistical methods in bioprocess fault detection and performance forecasting

Abstract: This paper demonstrates how multivariate statistical data analysis procedures used as feature extraction methods can assist in the operation of an industrial fermentation process. The quality of the production fermenter seed and the subsequent forecasting of productivity are the two examples considered, with results presented from industrial plant. The feature extraction methodologies utilised are based around principal component analysis (PCA) and the extension to batch systems through the use of multi-way PCA.

Notes: Times Cited: 3

  • Short Title: Multivariate statistical methods in bioprocess fault detection and performance forecasting
  • Journal: Transactions of the Institute of Measurement and Control
  • Volume: 19
  • Issue: 5
  • Pages: 271-279
  • Publication type: Article
  • Bibliographic status: Published

Keywords: principal component analysis (PCA); partial least-squares regression (PLS); fault detection; forecasting; fermentation principal component analysis; monitoring batch processes; diagnosis

Staff

Emeritus Professor Alan Ward
Emeritus Professor