Soft sensor - based artificial neural networks and fuzzy logic: application to quality monitoring in hot rolling

  • Authors:

  • Salah Bouhouche;Mostefa Yahi;Benjam Hocine;Jürgen Bast

  • Affiliations:

  • Iron and Steel Applied Research Unit, CSC, Annaba, Algeria;Welding and Control Research Center, Cheraga, Algiers, Algeria;Iron and Steel Applied Research Unit, CSC, Annaba, Algeria;HGUM, Institut für Maschinenbau, TU Bergakademie Freiberg, Germany

  • Venue:
  • ACMOS'08 Proceedings of the 10th WSEAS International Conference on Automatic Control, Modelling & Simulation
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

On line quality monitoring is an important domain particularly in the complex processes where the characteristic of the product quality is difficult to measure directly. Soft sensor based modelling and monitoring techniques can be considered as an alternative to solve such complex problem. We consider in this work a contribution for product quality monitoring in hot rolling. Data mining and modelling based Artificial Neural Network (ANN) is used to determine optimal model. Deviations between optimal and actual conditions characterised by dynamic properties of residual are used as a tool to compute a quality index in basis of fuzzy reasoning. Application in hot rolling shows that this approach can be recommended as part of a tool of on line quality monitoring and classification.