Prediction of the Fatigue Strength of Steel Based on Interpretable Machine Learning

Abstract

Most failures in steel materials are due to fatigue damage, so it is of great significance to analyze the key features of fatigue strength (FS) in order to improve fatigue performance. This study collected data on the fatigue strength of steel materials and established a predictive model for FS based on machine learning (ML). Three feature-construction strategies were proposed based on the dataset, and compared on four typical ML algorithms. The combination of Strategy Ⅲ (composition, heat-treatment, and atomic features) and the GBT algorithm showed the best performance. Subsequently, input features were selected step by step using methods such as the analysis of variance (ANOVA), embedded method, recursive method, and exhaustive method. The key features affecting FS were found to be TT, mE, APID, and Mo. Based on these key features and Bayesian optimization, an ML model was established, which showed a good performance. Finally, Shapley additive explanations (SHAP) and symbolic regression (SR) are introduced to improve the interpretability of the prediction model. It had been discovered through SHAP analysis that TT and Mo had the most significant impact on FS. Specifically, it was observed that 160 < TT < 500 and Mo > 0.15 was beneficial for increasing the value of FS. SR was used to establish a significant mathematical relationship between these key features and FS.

Prediction of martensite start temperature of steel combined with expert experience and machine learning

“…The original features of the dataset include T Aust , Gc, and alloy element compositions. Additionally, studies indicate that incorporating atomic features can significantly improve the model’s predictive performance [ 31 , 38 , 39 ]. Factors such as electronegativity, atomic mass, and atomic radius can influence the process of austenite-to-martensite transformation.…”

An Overview of Estimations for the High-Cycle Fatigue Strength of Conventionally Manufactured Steels Based on Other Mechanical Properties

“…For example, He et al [88] employed artificial neural networks to predict the S-N curve based on chemical composition and monotonic tensile properties. While not directly correlating fatigue strength with other mechanical properties, Agrawal and Choudhary [89] and Liu et al [90] developed machine learning tools based on data from the Japanese National Institute for Materials Science in order to predict fatigue strength based on chemical composition and material processing parameters (e.g., tempering temperature). During the development of such machine learning model, the quality and quantity of training data are of critical importance.…”