A neural network based model of sinter quality and sinter plant performance indices

Abstract

A prerequisite of a smooth operation of the ironmaking blast furnace is that the quality of the burden is stable. In blast furnaces where sinter is used as the (main) iron bearing material, its quality plays a crucial role in productivity and fuel economy. Simultaneously the corresponding factors must be considered for the sinter plant. The present paper studies the influence of three variables characterising the bedding piles and five sinter plant operation variables on sinter quality, sinter plant productivity, specific fuel consumption and share of cold return fines. Daily mean values for a period of five years of operation were used in the data driven modelling based on feedforward neural networks. The resulting models were found to describe the major changes in the outputs well. The input-output relations captured by the models were analysed by perturbing one input variable of the networks at a time and analysing the predicted behaviour of the outputs.

Immobilization of Chromium in Slags using MgO and Al2O3

“…Samples of each slag were crushed into fine powders and characterized by X-ray diffraction (XRD Bruker D8 Focus) and scanning electron microscopy coupled with energy dispersive spectroscopy (SEM-EDS, Jeol 6300). The chemical stability of the Cr-containing species present in the materials was evaluated by the following leaching technique, according to the Mexican environmental regulations [8]. 25 g of every slag were crushed below 741lm and contacted with 500 crrr' of an aqueous acetic acid solution at pH = 2.88 ± 0.05 in a rotary system during 20 h at 30 ± 2 rpm and 23 ± 2 "C. The solid residues were filtered through ash-free filter paper (Whatman 542) and the chromium present in the leachate was determined by atomic absorption spectrophotometry.…”

“…The morphology and composition of the slags were analysed by X-ray powder diffraction (XRD) and scanning electron microscopy coupled with energy dispersive spectroscopy (SEM-EDS). The chemical stability of chromium was evaluated determining the leaching levels of chromium according to the Mexican Waste Norms [8]; additionally, Eh-pH diagrams for the Ca-Cr-HzO and Mg-Cr-HzO systems at 25°C were constructed using the FACTSage thermodynamic software [9].…”

Methodology based on genetic optimisation to develop overall parsimony models for predicting temperature settings on annealing furnace

“…Using the proposed ESC, 27 we have found that the performance of the resulting models does not decrease, while the total computational costs are lower in two of the three cases studied (Figs. [9][10][11][12][13][14]. Figure 9 provides support for including a stopping criterion that significantly decreases the high risk of overfitting.…”

A Prediction System of Burn through Point Based on Gradient Boosting Decision Tree and Decision Rules

“…With the improvement of computer processing ability, some artificial intelligence methods have been applied to sintering process, such as support vector machine (SVM), artificial neural network (Ann) and so on. [15][16][17] This kind of algorithm has powerful nonlinear approximation ability. It is commonly used to establish a model of the relationship between observed data and state parameters.…”