Megabytes for metals: development of computer applications in the iron and steel industry

Aylen, Jonathan

doi:10.1179/030192304225019324

Cited by 10 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As with the chemical industry, iron and steel production is a process industry, − but it has its own characteristics, such as a production process with high temperature and high energy consumption, , production scheduling with complicated planning, , and different products with different phase changes and technologies. − Customer demands for small batches and varieties of products have been increasing recently. The product quality requirements in terms of strip thickness, strip crown, and strip flatness are also higher than ever.…”

Section: Introductionmentioning

confidence: 99%

Global Method for a Class of Operation Optimization Problem in Steel Rolling Systems

Tang

Liu

et al. 2019

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

Many steel products are produced in hot or cold rolling lines with multiple stands. The steel material becomes thinner after being rolled at each stand. Steady-state parameters for controlling the rolling line need to be set so as to satisfy the final product specifications and minimize the total energy consumption. This paper develops a generalized geometric programming model for this setting problem and proposes a global method for solving it. The

show abstract

Section: Introductionmentioning

confidence: 99%

Global Method for a Class of Operation Optimization Problem in Steel Rolling Systems

Tang

Liu

et al. 2019

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

show abstract

“…The cracks are usually induced by severe microsegregation of trace elements such as P and S when austenite dendrites form instead of ferrite dendrites, so how to regulate the content and morphology of ferrites in austenitic stainless steels is a common concerned problem. 4,[9][10][11][12][13] In 1997, the laser treatment and the directional solidification technique were introduced into the study of solidification behaviour of Fe-Cr-Ni alloy. 14 As cooling rate equals growth velocity multiplied by temperature gradient in directional solidification, so the cooling condition can be easily controlled and measured.…”

Section: Introductionmentioning

confidence: 99%

Phase evolution of AISI 321 stainless steel during directional solidification

Liang¹,

Gao²,

Li³

et al. 2009

Ironmaking & Steelmaking

View full text Add to dashboard Cite

The phase evolution of AISI 321 stainless steel was studied by directional solidification and quenching techniques. Two interfaces, solid/liquid and the peritectic reaction interface, were found to exist in the directional solidification structure. With increasing growth velocity the solid/ liquid interface changed in the sequence of planar, cellular, dendritic and the primary phase changed from austenite to ferrite. The phase and morphology selection was verified by the interface response functions (IRFs) and the maximum growth temperature criterion. The ferritic island banding structure was observed, not only in the austenite cellular primary growth condition (3 mm s 21 ), but also in the dendritic ferrite primary growth one at relatively low growth velocity (5 mm s 21 ). It is deemed that the former resulted from the nucleation of ferrite in the continuous matrix of austenite phase, yet the latter is the residual primary ferrite attributed to the growth of austenite. Both of them do not come from the nucleation near the solid/liquid interface.

show abstract

“…The availability of a considerable amount of data is a quite crucial point for the implementation of NNbased models, as well as for optimization of more traditional ones, but this is no more a problem, as the increasing degree of automation in the steelmaking plants and the continuously enlarging possibilities of modern computers and tools for storing data [14] offers to researchers the possibility of extracting information and even new knowledge from all such data, provided that suitable data processing techniques are exploited and used jointly with the available comprehension of the processes occurring on the plant from which the data are extracted. Statistical analysis of the data collected from the plants has become a very important field of steelmaking research, even more important with respect to other industrial fields, if one considers the difficulty in observing and monitoring the physical and chemical processes involved in the steelmaking practice.…”

Section: Introductionmentioning

confidence: 99%

Neural network based prediction of roughing and finishing times in a hot strip mill

Colla¹,

Vannucci²,

Valentini³

2010

REVMETAL

View full text Add to dashboard Cite

The paper presents a model based on neural networks which is able to predict the time required to pass the different gauges of a roughing and finishing mill as function of some slab features and process parameters. The final aim of the work is to increase the rolling efficiency while avoiding collisions and queues that cause time and energy losses. Neural networks are suitable to this prediction task as they are particularly able to cope with unknown non linear relationships between input and output variables. Moreover they can learn from real industrial data and therefore do not require prior assumptions or mathematical modelling of the process and transferability is ensured by the possibility to use different databases coming from different rolling mills. In the paper, two different kinds of neural network-based models have been proposed, their performances have been discussed and compared. KeywordsHot rolling steel; Slab; Coil; Mill pacing; Neural networks. Predicción basada en redes neuronales del tiempo de procesamiento de los trenes desbastador y laminador en una instalación de laminación en caliente ResumenEn este artículo se presenta un modelo basado en redes neuronales capaz de predecir el tiempo necesario para pasar las diferentes galgas de un tren desbastador y acabador en función de ciertas características del desbaste y paráme-tros de proceso. El objetivo final es aumentar la eficacia de la laminación evitando colisiones y colas que provoquen pérdidas de tiempo y energía. Se propone utilizar para esta tarea redes neuronales por su capacidad de predicción en aquellos casos en los que existen relaciones no lineales desconocidas entre las variables de entrada y las de salida. Además, son capaces de aprender de datos industriales reales y, por tanto, no requieren suposiciones previas o modelos matemáticos del proceso, estando la transferibilidad asegurada ya que es posible utilizar distintas bases de datos procedentes de diferentes trenes de laminación. Palabras claveLaminación en caliente; Desbaste; Bobina; Ritmo de laminado; Red neuronal.

show abstract

Megabytes for metals: development of computer applications in the iron and steel industry

Cited by 10 publications

References 13 publications

Global Method for a Class of Operation Optimization Problem in Steel Rolling Systems

Global Method for a Class of Operation Optimization Problem in Steel Rolling Systems

Phase evolution of AISI 321 stainless steel during directional solidification

Neural network based prediction of roughing and finishing times in a hot strip mill

Contact Info

Product

Resources

About