Improved Prediction for Nonlinear Thermal History of Mg Alloy Subjected to Multiple Electropulses

Abstract

The repeated rapid heating and nonlinear cooling associated with electropulsing treatment (EPT) hinder the accurate modeling of temperature variations based on a constitutive approach using physical models. This objective is not attainable through conventional machine learning (ML) approaches as well, such as artificial neural network (ANN) and long short‐term memory (LSTM). The present study investigates the intricate nonlinear thermal history of Mg alloys induced by EPT to improve a predictive model under multipulse conditions. Furthermore, it enhances the predictivity and generalizability of a given problem using an ML model called i‐LSTM by specifically tailoring a dataset. The i‐LSTM model performance surpasses that of the constitutive approaches and conventional ML models when predicting the complicated thermal history of EPT specimens in a wide variety of processing parameters. The mechanisms underlying this improvement are discussed based on several experimental datasets. This study not only addresses challenges in existing models but also offers a promising avenue for understanding and predicting the thermal dynamics of Mg alloys subjected to the multipulse EPT process.