Low-cycle fatigue life prediction of austenitic stainless steel alloys: A data-driven approach with identification of key features

Abstract

A data-driven approach for predicting the low-cycle fatigue (LCF) life of austenitic stainless steel (AusSS) is proposed to address the limitations of classical fatigue life prediction models. This approach integrates four key characteristics of the AusSS alloys, namely chemical compositions, microstructure, material processing parameters, and experimental parameters, to compile a comprehensive fatigue life prediction dataset. By employing the classification and regression technique, the relationship between various input features and LCF life is analyzed in depth, leading to the eventual identification of eight key features. Subsequently, various machine learning (decision tree, random forest, XGBoost, and support vector regression) and artificial neural network (ANN) are utilized to predict the LCF life using the compiled dataset. Comparative analysis of the results reveals higher prediction accuracy of ANN, with respective R2 and mean squared error values of 0.941 and 0.024, showcasing superior performance over the classical Basquin-Coffin-Manson model. This proposed methodology effectively captures the intricate feature-life relationships in AusSS, potentially reducing experimental time and costs of fatigue life estimation and offering promising applications in alloy design and manufacturing optimization.