Fatigue life prediction of welded joints based on improved support vector regression model under two‐level loading.

To meet the lightweight needs of modern machinery equipment, welded structure is widely used in practical engineering. During the service period, the welded structure is often subjected to multilevel variable amplitude loading, and fatigue failure is easy to occur. Due to the complexity and stochasticity of fatigue process, the traditional life prediction models cannot meet the demand of practical engineering. In this work, a novel prediction model based on the whale optimization algorithm (WOA) together with the support vector regression (SVR), namely, a WOA‐SVR model, is established. It combines the advantages of WOA and SVR for global searching optimization and high prediction accuracy dealing with small sample size. By taking into account the sequence of loadings and the interaction effect between loadings, the proposed WOA‐SVR model could overcome the deficiencies and shortcomings in existing models. Experiment results show that WOR‐SVR has better prediction performance than five models. Highlights: The WOA‐SVR model is established to predict the fatigue life under two‐level loading.The proposed model is verified by 190 experimental results.The proposed model has higher accuracy compared with other five models.The proposed model can be effectively applied to both welded joints and metal materials. [ABSTRACT FROM AUTHOR]