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

Abstract

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.

Optimization of S-N curve fitting based on neighborhood rough set reduction with improved firefly algorithm

“…Compared with other methods, for the calculation results and the accuracy of fatigue life, the nodal force based structural stress method can be used to analyze more precisely. We have studied the fatigue life prediction method for aluminum alloy welded joints in the early stage and achieved preliminary research results [15,16]. How to further reduce the scatter of fatigue data and improve the accuracy for fatigue life is a significant issue that needs to be solved, which is very important for the application of the method in engineering.…”