Development of a multiple linear regression model to estimate the ductile-brittle transition temperature of ferritic low-alloy steels based on the relationship between small punch and Charpy V-notch tests

The transition temperatures of Cr-0.5Mo, Cr-Mo, and Cr-Mo-V steels were determined using the Charpy V-notch (CVN) and the small punch (SP) tests. It was confirmed that there was a linear correlation between the transition temperature of ductile-brittle behavior determined by the Charpy V-notch test and that obtained from the small punch test. However, the estimation of CVN transition temperature by means of this linear equation is not completely reliable because of the large experimental scatter of data. In order to improve the reliability of the transition temperature estimation, a multiple linear regression (MLR) analysis was conducted to evaluate the effect of different variables of the manufacturing process and service conditions. This analysis permitted the determination of the following regression equation: CVNDBTT = 1.35 SPDBTT - 0.84 x 10(3) d(-1/2) + 326. This equation enables one to assess more accurately the transition temperature corresponding to the Charpy V-notch test using that of the small punch test and the austenitic grain size, expressed by d(-1/2).