Data-driven prediction of fracture toughness size effect in ductile-to-brittle transition using Two-Step-Scaling procedure

The fracture properties of ferritic steels in transition temperature region are usually statistically treated by models that presuppose the existence of various forms of quenched disorder (critical cleavage triggers). In this study, the fracture toughness from the Euro fracture toughness dataset (stress intensity factor used in the master curve KJc) for reactor steel 22NiMoCr37 is used with the aim of outlining a methodology for using the recently proposed two-step scaling (2SS) method. Three widely different temperatures (-154 degrees C, -91 degrees C, and 0 degrees C), which cover the entire range from lower shelf to upper shelf fracture, are selected to demonstrate the accuracy of extrapolation and interpolation of the fracture toughness CDF (cumulative distribution function) and the pertinent issues related to the procedure application. The obtained predictions at the two lower temperatures are in good agreement with the experimental results and well within the inherent experimental data scatter, while 2SS method is shown not to be applicable in upper-shelf transition region. Special attention is devoted to the effect of statistical sample size on prediction accuracy/reliability along with the minimum sample size requirement. Moreover, the reduction in random sample size affects the Weibull parameters, which in turn impacts the accuracy of predictions, introducing a degree of uncertainty and highlighting limitations in the method.