Effect of processing parameters on scale formation during hot steel strip rolling

Júnior, Sergio de Oliveira Lima; Bellon, Júlio Cezar; Júnior, Paulo Antônio de Souza; Araújo, Fernando Gabriel da Silva; Cota, André Barros

doi:10.1590/s1516-14392010000100004

Cited by 10 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…As carepas são geralmente classificadas em três tipos: a) primária, formada nos fornos de reaquecimento de placas; b) secundária, formada durante a laminação de desbaste; e por fim, c) terciária, formada durante a laminação de acabamento. Ao longo da linha ocorre a descarepação, por meio de jatos de água em alta pressão com o objetivo de remover os óxidos de ferro mais grosseiros [11]; [4]. Contudo, estes processos de remoção não são capazes de retirar por completo toda a carepa.…”

Section: Introductionunclassified

Aplicação De Rede Neural Artificial Na Predição Do Defeito Carepa Na Laminação De Tiras a Quente

Rodrigues,

Possatti,

Messner

et al. 2023

ABM Proceedings

View full text Add to dashboard Cite

ResumoEste estudo demonstra a aplicação de uma rede neural artificial (RNA) na predição do defeito carepa, na laminação de tiras quentes. A geração da carepa é inerente ao processo pela afinidade do ferro com o oxigênio em altas temperaturas. Manter o nível deste defeito sob controle e atendendo às especificações da aplicação final, evitam o desperdício com a desclassificação de material. Baseado em uma produção de 6.200 bobinas, foram coletados os parâmetros de temperaturas de processamento e quilometragem dos cilindros, resultando em 43 variáveis de entradas e 4 defeitos de saída. Após as simulações da RNA com 3 funções de ativação, 2 otimizadores e 2 quantidades de neurônios, adotou-se a função de ativação logistic com o otimizador lbfgs e uma camada com 87 neurônios. A performance da RNA foi avaliada por meio da matriz de confusão, obtendo-se uma acurácia de 81%, precisão média 54%, recall médio de 51% e média harmônica (f1score) de 52%. A RNA demonstra um desempenho excelente na predição da não ocorrência do defeito, obtendo-se 90% média harmônica (f1-score). Contudo, devese dar continuidade no aprendizado da rede para que a métrica recall tenha melhores resultados evitando-se classificar produtos com defeito como isentos de defeito.

show abstract

Section: Introductionunclassified

Aplicação De Rede Neural Artificial Na Predição Do Defeito Carepa Na Laminação De Tiras a Quente

Rodrigues,

Possatti,

Messner

et al. 2023

ABM Proceedings

View full text Add to dashboard Cite

show abstract

“…If hot rolling is performed without lubricant, then higher work roll roughness leads to cracked oxide scale layer. Introduction of hot rolling lubricant provides better surface finish under higher reductions with reduced tertiary scale formation 1,2 …”

Section: Introductionmentioning

confidence: 99%

Qualitative study and a novel solution to nozzle clogging problem in roll gap lubrication used in hot rolling

Chakraborty

Dutta

Bhagat

et al. 2020

Lubrication Science

View full text Add to dashboard Cite

Nozzle clogging in roll gap lubrication (RGL) is a pain area for hot strip steel rolling. Nozzle clogging severely affects lubrication affecting rolled surface quality causing prominent hot rolling defects like banding and peel-off phenomenon in work roll. Uneven coefficient of friction leads to variable or poor lubrication, which raises the chances of cobble and tail chewing in coils, lowers roll force reductions ultimately increasing the power consumption of the mill. The present work focuses on a holistic approach where causes leading to nozzle clogging have been identified and eliminated in a stepwise manner. Gas chromatography has been employed for the first time to get an understanding about the specific carbon chains contributing towards pulp generation. Optimising the distance between mixer and spray header and using indigenously modified spray header improves the lubrication during hot rolling. roll force reduction upto 15%-16% could be achieved.

show abstract

“…Scale is a layer of oxides that forms at the surface of the slab under the influence of high temperatures and in the presence of oxygen and other gases in the furnace. It has been examined how process parameters affect scale formation [1] and using data mining methods for scale defect prediction on the finished product [2]. Scale can cause problem in the hot rolling process, if it isn't removed from the slab surfaces.…”

Section: Introductionmentioning

confidence: 99%

Scale Monitoring System Tested at Ruukki Metals Plate Mill in Raahe

Niemi¹,

Nilsson²,

Helkomaa

et al. 2013

MSF

View full text Add to dashboard Cite

Some surface defects on hot rolled steels arise due to poor descaling. Generally reheated slabs are efficiently descaled but, now and then, residual scale remains on the slab after primary descaling. Commonly it is difficult to trace the few poorly descaled slabs since there often is no scale monitoring system. In the work presented here an image based primary scale monitoring-and evaluation system is presented. It is a stand-alone online vision system consisting of a camera connected to a computer. The camera is located directly after the descaling unit and the computer in the control room. The program automatically locates the boundaries of the top surface of a slab and calculates the quantity of residual scale on the top surface. The quantity of residual scale is logged and can afterwards be evaluated together with process parameters and downstream surface defects to identify problem areas. The system has been tested in industrial scale in the Ruukki plate mill. This work is a cooperation between Swerea MEFOS and Ruukki. The result of the test demonstrated the feasibility of using vision system for detection of residual scale. Some problems were identified and suggestions for solving them are reported. If the suggested modifications are carried out, it is believed that the vision system can be an on-line tool for the operator and also be an off-line resource for the ongoing quality work at the hot rolling mill.

show abstract

Effect of processing parameters on scale formation during hot steel strip rolling

Cited by 10 publications

References 8 publications

Aplicação De Rede Neural Artificial Na Predição Do Defeito Carepa Na Laminação De Tiras a Quente

Aplicação De Rede Neural Artificial Na Predição Do Defeito Carepa Na Laminação De Tiras a Quente

Qualitative study and a novel solution to nozzle clogging problem in roll gap lubrication used in hot rolling

Scale Monitoring System Tested at Ruukki Metals Plate Mill in Raahe

Contact Info

Product

Resources

About