A solidification heat transfer model and a neural network based algorithm applied to the continuous casting of steel billets and blooms

Abstract

This work presents the development of a computational algorithm applied to improve the thermal behaviour in the secondary cooling zone of steel billets and blooms produced by continuous casting. A mathematical solidification heat transfer model works integrated with a neural network based algorithm (NNBA) connected to a knowledge base of boundary conditions of operational parameters and metallurgical constraints. The improved strategy selects a set of cooling conditions (in the secondary cooling zone) and metallurgical criteria established to attain high product quality, which are related to a more homogeneous thermal behaviour during solidification. Initially, the results of simulations performed by using the mathematical model are validated against experimental industrial data, and good agreement is observed, in any case examined, permitting the determination of nominal heat transfer conditions by the inverse heat conduction method. By using the numerical model linked to a NNBA results have been produced determining a set of casting conditions, which has permitted better strand surface temperature profile and metallurgical length to be attained during the continuous casting of SAE 1007 billets and SAE 1025 blooms.

Explicit Modelling of Slag Infiltration and Shell Formation during Mould Oscillation in Continuous Casting

“…Mean values for v c ϭ0.6, 0.9, 1.2 and 1.5 m/min are 6.1, 9.1, 11.8 and 15.0 mm, respectively. This is in excellent agreement with the values for the theoretical pitch (6,9,12 All of the trends discussed in this section (Figs. 9 and 10) were observed over a wide range of casting speeds from 0.6 to 1.8 m/min, although the magnitude of the variations varied.…”

“…[9][10][11] Numerical simulations suffer from similar problems since the majority of models address only a limited number of phenomena (such as the interaction of metal flow with heat transfer or heat transfer effects on solidification) but ignore the behaviour of molten slag inside the shell-mould gap. 3,12) Again, this problem has been addressed through algebraic and empirical models based on plant measure-ments of powder consumption rates. [13][14][15] However, these models provide only limited information on the conditions prevailing in the meniscus during initial solidification (where most defects arise).…”

Finite Element Methods to Optimize by Factorial Design the Solidification of Cu-5wt%Zn Alloy in a Sand Mold

“…The mathematical formulation of heat transfer to predict the temperature distribution during solidification is based on the general equation of heat conduction in the unsteady state, which is given in two-dimensional heat flux form for the analysis of the present study Santos et al, 2005;Shi & Guo, 2004;Dassau et al, 2006). [m] and represents the term associated to the latent heat release due to the phase change.…”

“…In the current system, no external heat source was applied and the only heat generation was due to the latent heat of solidification, L (J/kg) or ΔH (J/kg). is proportional to the changing rate of the solidified fraction, f s , as follow Santos et al, 2005;Shi & Guo, 2004).…”

Performance of neural networks in materials science

“…For example, the work of Santos et al in which a heat transfer model was combined with neural network based algorithms to improve the manufacturing strategy of the continuous casting of steel billets and blooms. 20 …”