Application of machine learning approaches for modelling crack growth rates

Abstract The scientific community has widely accepted the use of machine learning techniques to tackle complex engineering problems. Among most intriguing problems is finding correlation between alloy steel properties and cyclic fatigue crack growth rate. Employing machine‐learning models can provide more robust accurate predictive address such challenges. This paper presents application four models, namely decision trees (DT), random forest (RF), adoptive boosting (AdaBoost), gradient regression tree (GBRT) predict rate steel/alloys. study utilizes a large database gathered from literature construct compares results using various statistical metrics graphical representation. study's findings demonstrate effectiveness suitability handle databases related