A modelling strategy has been developed to reduce the overspread at the finisher of the HSM in Avilés. A new hybrid data based model elaborates the roughing and finishing mills set up. It has made it possible to reduce the overspread by 1.5 mm at the finisher since March 2005. The model is modular and flexible and it can be transferred to other installations.

Virtual sensors allow the measuring of variables for which no physical sensor is available using indirect measurements of related variables. In this work we describe the implementation of a virtual sensor for the zinc coating thickness in a hot dip galvanizing line from related process variables such as blowing pressure, knives-to-strip distance, knives-topot distance, etc., based on artificial neural networks that model nonlinear dynamical relationships. The virtual sensor is currently working on Avilés Galvanizing 2.

A new on-line guidance tool has been implemented to help the mill operator with the achievement of a thickness performance that meets the ever more stringent requirements for DWI material. The tool makes it possible to analyse the causes of thickness defects that are originated by the HSM or by the tandem mill.

The main objective of this paper is to present a model based on advanced artificial intelligence techniques to determine the preset values of the roll forces to be applied on the temper mill of a galvanizing line. This model will preset both the roll force needed for the required material and will also preset the necessary tension. The roughness is also foreseen by applying this method.