Abstract
Although the principles of microalloying are well established, the complexity of thermomechanical processing is such that it is difficult to deconvolute the contribution to strength of the microalloying additions as a function of the many variables involved. We report in this article the analysis of a large database on hot-rolled steels to create a neural network model which estimates the strength as a function of chemical composition and process variables. This model is then used to make comparisons against equivalent data in order to realize the role of minute additions of carbide formers in changing the properties of steels.
ACKNOWLEDGMENTS
The authors are also grateful to Drs Jae Kon Lee, Young Roc Im, and Jung Hyeung Lee of POSCO for their help in this work, and to Professor Hae-Geon Lee for the provision of laboratory facilities at GIFT.