Steel annealing furnace robust neural network model

Abstract

In this day and age, galvanised coated steel is an essential product in several key manufacturing sectors because of its anticorrosive properties. The increase in demand has led managers to improve the different phases in their production chains. Among the efforts needed to accomplish this task, process modelling can be identified as the one with the most powerful outputs in spite of its non-trivial development. In many fields, such as industrial modelling, multilayer feedforward neural networks are often proposed as universal function approximators. These supervised neural networks are commonly trained by the traditional, back-propagation learning format, which minimises the mean squared error (mse) of the training data. However, in the presence of corrupted or extremely deviated samples (outliers), this training scheme may produce incorrect models, and it is well known that industrial data sets frequently contain outliers. The process modelled is a steel coil annealing furnace in a galvanising line, which shares characteristics with most of the furnaces used in galvanised lines all over the world. This paper reports the effectiveness of robust learning algorithms compared to the classical mse-based learning algorithm for the modelling of a real industry process. From this model an adequate line velocity (the velocity set point) for a coil, depending on its characteristics and the furnace condition to receive this coil (temperature set points), can be obtained. With this set point generation model the operator could set strategies to manage the line, i.e. set the order of the coil to be treated or preview the line's speed conditions for the transitory situations.

Improvement and optimisation of hot dip galvanising line using neural networks and genetic algorithms

“…Later on, it is proposed that the RBFN be used, which makes it possible to approach the problem for different types of steel, as well as the methodologies of robust and spurious training. 11,18 Database Data acquisition was performed by experts from the computer processing area based on historic data continuously generated during galvanising process (initially more than 6000 variables). The variables were selected according to their relevance to the process (furnace heating zone).…”

Advanced predictive quality control strategy involving different facilities

“…These strategies contribute to decision-making processes at the operator level, reduce the production of scrap, or help to produce better products. Indeed, they have also been used to model a furnace during the production process [18] or to simply model steel properties [16].…”

Reduce of adherence problems in galvanised processes through data mining techniques

“…Por ejemplo, estas técni-cas se utilizan para determinar las mejores consignas de un horno de una línea de galvanizado [13] , predecir temperaturas de arrabio de un horno alto [14] , determinar las propiedades metálicas de la banda en procesos del acero [15 y 16] , predecir el end-point de un convertidor [17] , deducir las propiedades de un acero ante altas temperaturas [18] , determinar la rugosidad final de la banda de acero [19] , entre otras muchas aplicaciones.…”