Utilization of Experimental Data as Boundary Conditions for the Solidification Model Tempsimu-3D

Self Cite

The formation of defects such as cracks in continuous casting deteriorates the quality of cast products and efficiency of steelmaking. To evaluate the risks and identify the root causes of defect formation, phenomenological quality criteria computed with a solidification and microstructure model known as InterDendritic Solidification (IDS) have previously been applied. This approach is computationally efficient and provides a fundamental perspective to defect formation in continuous casting. The aim of this work is to study the capabilities of these criteria as features in predicting transverse cracking with interpretable machine learning models. IDS is coupled with a heat transfer model known as Tempsimu to simulate the continuous casting process. Measured compositions are utilized in the simulations and defects reported at a steelmaking plant are used as labels in classification. Logistic regression, decision tree, and Gaussian Naïve Bayes classifiers are developed to predict transverse cracking in peritectic C–Mn, low‐carbon B–Ti microalloyed, and peritectic Nb‐microalloyed steels. The corresponding balanced accuracies of the best classifiers from cross‐validation are 92%, 94.6%, and 82.8%. Due to the good performance and the interpretability of the developed classifiers, the fundamental causes of transverse cracking and possibilities of avoiding it by changes in the compositions are identified.

Section: Tempsimumentioning

confidence: 99%

Coupling of Solidification and Heat Transfer Simulations with Interpretable Machine Learning Algorithms to Predict Transverse Cracks in Continuous Casting of Steel

Norrena,

Louhenkilpi,

Visuri

et al. 2024

Self Cite

“…Tempsimu is a software tool used for the steady-state simulation of heat transfer with 3D models for the mold and strand of a continuous casting machine. [29,30,[35][36][37][38] Tempsimu calculates not only the strand and mold temperatures but also other relevant information, such as the shell thickness and the total mold heat flux. As basic input information, Tempsimu requires the mold material properties, the secondary cooling configuration including the types and locations of the spray nozzles and rolls, the dimensions of the strand, the material properties of the steel grade, the spray cooling water flow rates, the amount of superheat, and the steady-state casting speed.…”

Section: Heat Transfer Modelmentioning

confidence: 99%

“…Further information regarding the fundamentals, assumptions, and validation of Tempsimu and CastManager for continuous casting is available in refs. [29,30,[35][36][37][38]…”

Section: Heat Transfer Modelmentioning

confidence: 99%

Assessing the Effects of Steel Composition on Surface Cracks in Continuous Casting with Solidification Simulations and Phenomenological Quality Criteria for Quality Prediction Applications

Norrena

Louhenkilpi

Visuri

et al. 2023

Self Cite

Crack formation is an issue that significantly undermines the quality and productivity of steel production. In previous studies, a solidification and microstructure model known as InterDendritic Solidification (IDS) has been developed and implemented in various slab casters in Finland. Numerous quality criteria have been derived from the model outputs to identify the general phenomena which increase the risks of defect formation in different steel grades. The aim of this study is to study the feasibility of these criteria in providing input data for predicting quality in a group of defect‐prone steel grades with rule‐based decision‐making and machine learning algorithms. To this end, three steel grades are studied by utilizing measured compositions and comparing the quality criteria with plant data regarding reported defects. The computations are carried out by coupling IDS with a fundamental model for simulating heat transfer (Tempsimu) in continuous casting. The results indicate that for the studied steel grades, phenomenological quality criteria can be applied to predict the formation of cracks and other defects. Trends contributing to increased risks of defect formation are identified for all the studied steel grades, and possibilities for avoiding defects by changes in the compositions of these steel grades are also proposed.

“…For the modeling of heat removal along with the mold/strand interface, a temperature‐dependent local HTC is similarly applied, as proposed by Hietanen et al [ 15 ] and Preuler et al [ 16 ] The temperature of the mold is assumed to be 150 °C. The total heat withdrawal in the mold is adjusted to the measured integral heat flux.…”

Section: Numerical Modeling Of Solidificationmentioning

confidence: 99%

“…In the case of secondary cooling, four zones of heat removal can be distinguished, [ 16 ] shown in Figure 2 and summarized in Table 1 : The heat removal at the strand/roll contact is defined with an HTC of 700 Wm −1 K −1 and a roll temperature of 150 °C; [ 17 ] the contact length is fixed at 20 mm. [ 17 ] Bearing blocks interrupt the guiding rolls, and in these areas, heat removal is currently simplified as radiation only.…”

Section: Numerical Modeling Of Solidificationmentioning

confidence: 99%

A Near‐Process 2D Heat‐Transfer Model for Continuous Slab Casting of Steel

Bernhard

Santos

Preuler

et al. 2022

Self Cite

Continuous casting has become a highly developed technology for producing steel grades with the highest surface and internal quality. Adequate numerical simulation tools have accompanied this enormous progress in process development with practical relevance for continuous casting. Computation modeling so far addresses a wide variety of the phenomena involved such as heat transfer, fluid flow, thermomechanics, phase transformations, and all aspects of product quality, as recently reviewed by Thomas. [1] For process control, standard solidification models solve the heat-transfer equation in 2D or 3D under stationary or transient boundary conditions and provide information about shell growth and temperature distribution. [2] For online process models, the quality of the thermal boundary conditions and the thermophysical properties of the cast steel grade is decisive for the accuracy of the calculation results.The working group M 2 CC at Montanuniversitaet Leoben has been working on the experimental and numerical simulation of quality-relevant aspects of casting for decades. Meanwhile, the characterization of phase transformations in steels [3][4][5] and the assessment of thermodynamic databases [6] have become a further research focus. The numerical models, databases, measurement techniques, and laboratory experiments developed are linked in the noncommercial offline "casting development platform" m 2 CAST, schematically illustrated in Figure 1. [7] The main emphasis behind the solidification model m 2 CAST is the transfer of process information to lab experiments and vice versa. The general concept and individual steps can be summarized as follows:Thermodynamic data in the material module m 2 MAT is based on extensive internal differential scanning calorimetry (DSC) measurements and thermodynamic calculations, for example, by FactSage 8.0 software and its databases. [8] The calculated thermophysical properties of the steel grade of interest, for example, phase fractions, heat capacity, thermal conductivity, and density, are required to solve the heat conduction equation.In the caster configurator, the slab dimensions and geometry, that is, thickness, width, and casting gap, must be defined along with the mesh size.