Wei Hu, Krishna Rajan
This thesis explores data-driven methodologies for metallurgical design aimed at enhancing the performance of high strength low alloy (HSLA) steels. The objective is to develop models that predict the mechanical properties of HSLA steel by utilizing multivariate data. The research employs techniques such as linear regression, artificial neural networks, and recursive partitioning to analyze input variables and their interactions. Through comprehensive data collection and model evaluation, the study identifies critical factors influencing yield strength and ultimate tensile strength of HSLA steels. The results indicate that the integrated modeling approach can significantly improve the predictive accuracy of steel property outcomes. Insights gained from this research have considerable implications for advancing metallurgical design practices and optimizing the material properties of HSLA steels for various industrial applications.
@article{23cd14ed-b8d8-4196-9643-3e6d6ceb1acf,
title={Data-driven metallurgical design for high strength low alloy (HSLA) steel},
author={Wei Hu and Krishna Rajan},
year={2008},
language={English}
}TY - JOUR TI - Data-driven metallurgical design for high strength low alloy (HSLA) steel AU - Wei Hu AU - Krishna Rajan PY - 2008 LA - English ER -
Richard Ngenda Banka
Ce document présente une synthèse de la métallurgie du cobalt, en abordant successivement ses propriétés, ses minerais et ses procédés d’extraction. I
Blair Burwell
The exhaustion of current vanadium sources and the emergence of new applications are driving the need for innovative methods of extraction. The aim of
Rajesh Jha, Bimal Kumar Jha
This book describes the application of artificial intelligence (AI) and machine learning (ML) concepts to develop predictive models that can be used t
Reza Arghandeh, Alexandra von Meier
Modern society relies heavily upon complex and widespread electric grids. In recent years, advanced sensors, intelligent automation, communication net
Frank Hohls, Armin C. Welker
The Josephson effect in superconductors links a quantized output voltage Vout = f ·(h/2e) to the natural constants of the electron's charge e, Planck'