Experience of Using Manganese-Containing Materials in Blast-Furnace Charge

Semenov, Yu. S.; Gorupakha, V. V.; Кузнецов, А. М.; Semion, I. Yu.; Schumel’chik, E. I.; Ващенко, С. В.; Khudyakov, A. Yu.

doi:10.1007/s11015-020-00920-1

Cited by 18 publications

(8 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Complementarily, the Pearson correlation coefficient (R) was calculated for each neural network and it was found that the results presented are better than those predicted in the literature [2][3][4][5][6][7][8], and [22][23][24][25][26][27][28][29][30][31][32][33][34]. The analysis of Fig.…”

Section: Resultsmentioning

confidence: 95%

“…Since the information on the training error does not provide information on which neural model provides the best generalization, the complexity problem was first solved by dividing the available data into 3 sets, the so-called training set and 2 other sets used for testing and validation to solve the neural model complexity problem [26][27][28][29].…”

Section: Neural Network Architecturementioning

confidence: 99%

See 1 more Smart Citation

Prediction of silicon content in the hot metal using Bayesian networks and probabilistic reasoning

Cardoso

Felice

2021

Int. J. Adv. Intell. Informatics

View full text Add to dashboard Cite

The blast furnace is the principal method of producing cast iron. In the production of cast iron, the control of silicon is vital because this impurity is harmful to almost all steels. Artificial neural networks with Bayesian regularization are more robust than traditional back-propagation networks and can reduce or eliminate the need for tedious cross-validation. Bayesian regularization is a mathematical process that converts a nonlinear regression into a "well-posed" statistical problem in the manner of ridge regression. The main objective of this work was to develop an artificial neural network to predict silicon content in hot metal by varying the number of neurons in the hidden layer by 10, 20, 25, 30, 40, 50, 75, and 100 neurons. The results show that all neural networks converged and presented reliable results, neural networks with 20, 25, and 30 neurons showed the best overall results. However, In short, Bayesian neural networks can be used in practice because the actual values correlate excellently with the values calculated by the neural network.

show abstract

Section: Resultsmentioning

confidence: 95%

Section: Neural Network Architecturementioning

confidence: 99%

Prediction of silicon content in the hot metal using Bayesian networks and probabilistic reasoning

Cardoso

Felice

2021

Int. J. Adv. Intell. Informatics

View full text Add to dashboard Cite

show abstract

“…Встановлено, що з введенням в шихту марганцю знижується коливання теплового стану, виражене в зменшенні середньоквадратичного відхилення кремнію в чавуні, зменшується витрата коксу на 4%. Встановлено, що при виробництві чавуну раціональним діапазоном вмісту марганцю в чавуні є 0,25-0,35% [26].…”

Section: науково-технічні результатиunclassified

“…Так, наприклад, вміст окатишів в суміші з агломератом змінювався від 10 до 90%, агломерат використовувався як виробництва місцевої аглофабрики зі значною кількістю в ньому вторинних ресурсів, так і привізний. У складі шихти також використовували різноманітні добавки: залізну руду, вапняк, конвертерний шлак, брикети з відсіву окатишів, марганцевмісні добавки, що володіють ефектом промивок горна [26]. Якість коксу при цьому змінювалась в широкому діапазоні, використовували кокс як місцевого виробництва, так і привізний від широкого спектра постачальників.…”

unclassified

Development and implementation of the new approaches to diagnostics and management of the blast furnace smelting

Semenov¹,

Shumel’chik²,

Horupakha³

2019

Fund.Appl.Probl.F.Met

View full text Add to dashboard Cite

The article presents a brief description of the results of blast furnace production research carried out at the Yenakiieve Iron & Steel Works and the Dneprovsky Iron & Steel Integrated Works in 2011–2019. For the conditions of transition modes of blast furnace to ensure its stability in changing the qualitative and quantitative composition of the components of the charge materials, as well as in the change of fuel additives in the blast, the complex use of information of modern means of automated control is proved: stationary thermosets and thermocouples to the lining. New approaches to the choice of rational charging programs using the principle of variable maximum ore loading along the radius of the furnace within the charging cycle for working conditions on a charge of low quality have been developed. The implementation of such a charging program over the next three years has allowed to ensure a stable and economical course of melting, and its adaptation to the technology of using pulverized coal has allowed to reduce the gas flow temperature of the peripheral zone throughout the height of the blast furnace, as well as to preserve the cooling system during the development of lining-free. Expert module of adjustment of the program of charging using the established rational ranges of change of temperature indices of gas flow distribution along the radius of the furnace under different technological conditions of blast furnace has been developed and implemented on three blast furnaces. The method of reasonable choice of location of closed air tuyeres or air tuyeres of different diameter was developed and tested using information on change of lining temperatures on height and circumference of blast furnace. The method of equalizing the raceway adiabatic flame temperature around the blast furnace circumference by creating a non-uniform flow rate of pulverized coal in the air tuyeres has been improved and implemented. The basic technological requirements for blast furnace blasting after its long stop without release of "gantry" cast iron and scraping of materials from the furnace, the use of which before and in the blast furnace blasting of the Yenakiieve Iron & Steel Works and the Dneprovsky Iron & Steel Integrated Works after a long-lasting set-up were developed economic indicators, while ensuring the preservation of refractory lining, structures and equipment.

show abstract

“…The most common artificial neural network architectures are single-layer feed-forward networks, multilayer feedforward networks, recurrent networks, and lattice networks 2,27 . In this paper, a single-layer feedforward architecture with a sigmoid activation function and the Levenberg-Marquardt training algorithm was chosen.…”

Section: Introductionmentioning

confidence: 99%

Artificial Neural Network for Predicting Silicon Content in the Hot Metal Produced in a Blast Furnace Fueled by Metallurgical Coke

2022

View full text Add to dashboard Cite

The main production route for cast iron and steel is through the blast furnace. The silicon content in cast iron is an important indicator of the thermal condition of a blast furnace. High silicon contents indicate an increase in the furnace's thermal input and, in some cases, may indicate an excess of coke in the reactor. As coke costs predominate in the production of cast iron, tighter control of the silicon content therefore has economic advantages. The main objective of this article was to design an artificial neural network to predict the silicon content in hot metal, varying the number of neurons in the hidden layer by 10, 20, 25, 30, 40, 50, 75, 100, 125 , 150, 170 and 200 neurons. In general, all neural networks showed excellent results, with the network with 30 neurons showing the best results among the 12 modeled networks. The validation of the models was confirmed using the Mean Square Error (MSE) and Pearson's correlation coefficient. The cross-validation technique was used to re-evaluate the performance of neural networks. In short, neural networks can be used in practical operations due to the excellent correlations between the real values and those calculated by the neural network.

show abstract

Experience of Using Manganese-Containing Materials in Blast-Furnace Charge

Cited by 18 publications

References 3 publications

Prediction of silicon content in the hot metal using Bayesian networks and probabilistic reasoning

Prediction of silicon content in the hot metal using Bayesian networks and probabilistic reasoning

Development and implementation of the new approaches to diagnostics and management of the blast furnace smelting

Artificial Neural Network for Predicting Silicon Content in the Hot Metal Produced in a Blast Furnace Fueled by Metallurgical Coke

Contact Info

Product

Resources

About