An artificial neural network model is used to predict high-temperature ductility of steels from their composition and thermal history. The model used literature data on reduction of area (RA). In most types of steel, RA has a U-shaped or V-shaped function of temperature; this shape was represented using a Gaussian fit. The predictive model considers conditions, including alloy composition and thermal conditions. The predicted values agreed well with most experimental values. This model can predict ductility trough for a wider composition range and thermal history than previous studies have achieved. The model also presents how fine components such as titanium (Ti) and nitrogen (N) affect changes in the hot-ductility trough. This model can be used to set steel-casting operating conditions to ensure that steel is not at the temperature in which ductility is low when the slab passes through the bending/unbending area of a continuous caster.

No abstract

No abstract

No abstract

Comparison of reheating tensile test (RHT) and re-melting tensile test (RMT) reveals the effect of interdendritic impurity segregation on hot ductility in lowcarbon steels. Two low-carbon steels with different amounts [wt%] of impurity elements (Steel A: P ¼ 0.005, S ¼ 0.001; Steel B: P ¼ 0.01, S ¼ 0.004) are tensiletested at temperatures 600-1000 C after reheating to 1350 C and re-melting at 1570 C. Steel A shows similar hot ductility behavior in the RHT and RMT, whereas the high-impurity steel shows a significant decrease in hot ductility at 900 C in the RMT compared with the RHT. Crack initiation at the interdendritic segregation region is suggested as an origin of the degradation of hot ductility in the high-impurity steel. The effect of interdendritic impurity segregation on the hot ductility behavior of continuously cast steel is further discussed.