Martensite Start Temperature Modeling via Artificial Neural Network Model

The martensite start temperature (M s ) of steels plays an important role in the formulation of heat‐treatment processes. Therefore, it is of great practical importance to predict M s accurately and rapidly. In the present work, machine learning (ML) methods are used to model M s based on the M s data of 1177 steels. Moreover, its generalization performance is verified using fivefold cross validation. Three different back‐propagation (BP) neural network algorithms (genetic algorithm [GA], particle swarm optimization, mind evolutionary algorithm) are used for optimal model selection. The results indicate that, among the three BP neural network algorithms, the GA–BP model has the highest prediction accuracy on the test set. The performances of GA–BP, Thermal–Calc, and JMatPro in predicting the M s of medium‐ and low‐carbon steels and high‐carbon steels are analyzed using an unknown dataset. The results show that the GA–BP model has strong generalization ability and can predict M s relatively accurately. The influence of alloying elements on M s is analyzed using the GA–BP model and the shapley additive explanation method, which provides strategies for studying the microstructure evolution of steel or optimizing the heat‐treatment process.