Tensile properties of mechanically alloyed oxide dispersion strengthened iron alloys Part 1 - Neural networkmodels

Abstract

A neural network technique trained within a Bayesian framework has been applied to the analysis of the yield strength, ultimate tensile strength, and percentage elongation of mechanically alloyed oxide dispersion strengthened ferritic steels. The database used was compiled using information from the published literature, consisting of variables known to be important in influencing mechanical properties. The analysis has produced patterns which are metallurgically reasonable, and which permit the quantitative estimation of mechanical properties together with an indication of confidence limits.