A probabilistic Stilssi function for modelling the S-N curves and its application on specimens made of steel S355J2+N

The fatigue life can be represented through S-N curves which describe the relationship between load cycles up to failure and stress range applied in a structure. Providing these curves help the engineers to estimate design stress levels with a high reliability. The nonlinear function proposed by Stussi offers a good approach to model the mentioned curves. However, he did not propose any statistical distribution which allows to make estimations with certain probability. Moreover, the Stussi function does not consider the influence of runouts and their subsequent retests. The Weibull model from Castillo et al. is a statistical method which overcomes this limitation. However, this method cannot be applied to model the S-N curves in the Low Cycle Fatigue regime. In this paper, a Weibull distribution is combined with the Stussi function in order to model the S-N curves, and the characteristics of this proposed method are compared with those of the Weibull model from Castillo et al. In order to establish the advantages and usability of both models, one application considering the experimental data of specimens made of steel S355J2 + N is presented. Finally, some recommendations regarding the planning of fatigue tests are made.