Abstract

In this study, an additive scaling function based multi-fidelity (ASF-MF) surrogate model is constructed to fast predict fatigue life as well as the stress distribution for the welded single lap joint. The influence of leg length, leg height, the width of the specimen and load in the fatigue test are taken into consideration. In the construction of the MF surrogate model, the finite element model that is calibrated with the experiment is chosen as the high-fidelity (HF) model. While the finite element model that is not calibrated with the experiment is considered as the low-fidelity (LF) model, aiming to capture the trend of the HF model. The Leave-one-out (LOO) verification method is utilized to compare the prediction performance of the ASF-MF surrogate model with that of the single-fidelity Kriging surrogate model. Results show that the ASF-MF surrogate model can better predict the fatigue life as well as the stress distribution.

This content is only available via PDF.
You do not currently have access to this content.