Statistical modeling of charcoal consumption of blast furnaces based on historical data

Faleiro, Rosiane Mary Rezende; Velloso, Cláudio Musso; Castro, Luiz Fernando Andrade de; Sampaio, Ronaldo Santos

doi:10.1016/j.jmrt.2013.04.002

Cited by 6 publications

(5 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Gasparini et al [15] apresentaram um modelo termoquímico para predição do consumo de carbono no alto-forno, com base nos dados dos gases de topo, carregamento, sopro, escória, gusa produzido e perda de calor, sendo que o modelo obtido com R 2 =79,3%.…”

Section: Discussão Dos Resultadosunclassified

Redes Neurais Artificiais Para Predição Do Consumo Total De Combustível De Um Alto-Forno

Gois¹,

Carvalho²,

Andretti³

et al. 2019

TMM

View full text Add to dashboard Cite

Este artigo propõe o uso de redes neurais artificiais para a previsão do consumo total de combustível no alto-forno. Para tanto, foi considerado um conjunto de dados contendo 270 registros, com 19 variáveis de entrada, com base nos dados históricos médios de operação de um alto-forno no período de janeiro/2016 a junho/2017, e verificou-se que o modelo apresentou bons resultados com coeficiente de correlação de 0,837, rmse de 11,8 (treino) e 12.7 (teste). O modelo final apresenta uma camada de entrada com 19 neurônios, camada intermediária com 19 neurônios e camada de saída com 1 neurônio. Palavras-chave: Redes neurais artificiais; Consumo de combustível; Alto-forno.

show abstract

Section: Discussão Dos Resultadosunclassified

Redes Neurais Artificiais Para Predição Do Consumo Total De Combustível De Um Alto-Forno

Gois¹,

Carvalho²,

Andretti³

et al. 2019

TMM

View full text Add to dashboard Cite

show abstract

“…The impact on pig iron production operational cost due to this change was calculated using a model developed by Faleiro et al (2013), and a negative NPV impact of USD 4.4M was estimated. Despite this, the gain in iron ore lump reserve and reduction of mine operational costs summed to an overall positive impact of USD 25.6M in the NPV, indicating the feasibility of the production plan for the mine/mill system.…”

Section: Discussionmentioning

confidence: 99%

“…The raw material quality influences the charcoal consumption in these blast furnaces, which accounts for much of the steel production cost. Faleiro et al (2013) developed a statistical model to predict charcoal consumption in blast furnaces based on response surface models and linear regression models. This model estimated charcoal consumption and pig iron production cost as functions of raw material quality, including Fe and contaminant content in the iron ore lumps.…”

Section: Methodsmentioning

confidence: 99%

“…Higher volumes of alumina raise the fusion point of the slag, implying a higher demand for charcoal in order to raise the temperature of the reactor, avoiding cold runs. Based on the model developed by Faleiro et al (2013), among the evaluated variables, Al 2 O 3 is the one that affects pig iron operational cost most. While an increase of 1% of Al 2 O 3 in iron ore increases the specific consumption of charcoal by 20 kg/t, the same changes in SiO 2 and LOI levels represent increases of only 0.01 kg/t and 0.16 kg/t, respectively.…”

Section: Impact On Mine/mill Systemmentioning

confidence: 99%

See 1 more Smart Citation

Mine/Mill production planning based on a Geometallurgical Model

Gomes

Tomi

Assis

2016

Rem: Rev. Esc. Minas

View full text Add to dashboard Cite

The Pau Branco mine supplies two blast furnaces with iron ore lumps, and currently, charcoal consumption for pig iron production accounts for 47% of the blast furnaces' operational cost. A geometallurgical model is presented to support an economic study considering reserve volumes, product quality, and operational costs based on the metallurgical performance of different iron ore typologies. Sample analysis provides values required in the model. From the model, an alternative production plan is presented with a positive impact of USD 25.6M over the current net present value of the mining/mill system.

show abstract

“…Moreover, the blast-furnace practice involves many different parallel physical and chemical processes, process defining parameters are hard to be measured and a set of controlling actions giving the possibility of tests at the facility is limited. The analysis of blast-furnace processes based on mathematical, physical modeling as well as experimental tests is given in the works [1][2][3][4][5][6][7][8][9][10][11][12].…”

Section: Introductionmentioning

confidence: 99%

Identification Method of Blast-Furnace Process Parameters

Kazarinov

Barbasova

2016

KEM

View full text Add to dashboard Cite

This work considers performance identification by operation statistics aimed to mathematical descriptions of blast-furnace processes. In case of the blast-furnace process automation the operational task of process conditions optimization shall preferably be implemented based on the algorithm of performance identification by operation statistics alongside with control and stabilization of process conditions.

show abstract

Statistical modeling of charcoal consumption of blast furnaces based on historical data

Cited by 6 publications

References 8 publications

Redes Neurais Artificiais Para Predição Do Consumo Total De Combustível De Um Alto-Forno

Redes Neurais Artificiais Para Predição Do Consumo Total De Combustível De Um Alto-Forno

Mine/Mill production planning based on a Geometallurgical Model

Identification Method of Blast-Furnace Process Parameters

Contact Info

Product

Resources

About