ScholarWorks@경상국립대학교

초록

Optimizing heat treatment processes requires an understanding of the complex relationships between compositions, processing parameters, microstructures, and properties. Traditional experimental approaches are costly and time-consuming, whereas machine learning methods suffer from critical data scarcity. In this study, gradient boosting models were developed to predict microstructural phase fractions and mechanical properties using synthetic training data generated from an established metallurgical theory. A 400-sample dataset spanning eight AISI steel grades was created based on Koistinen-Marburger martensite kinetics, the Grossmann hardenability theory, and empirical property correlations from ASM handbooks. Following systematic hyperparameter optimization via 5-fold cross-validation, gradient boosting achieved R2 = 0.955 for hardness (RMSE = 2.38 HRC), R2 = 0.949 for tensile strength (RMSE = 87.6 MPa), and R2 = 0.936 for yield strength, outperforming the Random Forest, Support Vector Regression, and Neural Networks by 7-13%. Feature importance analysis identified the tempering temperature (38.4%), carbon equivalent (15.4%), and carbon content (13.0%) as the dominant factors. Model predictions demonstrated physical consistency with the literature data (mean error of 1.8%) and satisfied the fundamental metallurgical relationships. This methodology provides a scalable and cost-effective approach for heat treatment optimization by reducing experimental requirements based on learning curve analysis while maintaining prediction accuracy within the measurement uncertainty.

키워드