Predicting the in-plane mechanical anisotropy of 7085 aluminum alloys through crystal plasticity simulations and machine learning

Abstract

The crystallographic texture of rolled 7xxx series aluminum alloys may lead to mechanical properties anisotropy which undermines the formability and performance of the material. This article aims to explore the quantitative relationship between texture and the in-plane anisotropy of 7085 aluminum alloy. A comprehensive computational method combining crystal plasticity simulation with machine learning and experiment was used to establish an analytical model and train a machine learning model to predict the anisotropy of 7085 aluminum alloys. We first performed a full-field crystal plasticity spectral simulations using fast Fourier transformation (CPFFT) to predict the anisotropy of 7085 aluminum alloy at different annealing times. Then, based on the CPFFT simulation data, the quantitative relationship between texture and the in-plane anisotropy of the r-value was established by using the multiple linear regression and gradient boosting regressor model. The results indicate that CPFFT simulation can effectively capture the influence of texture changes on anisotropy, and the model established through the gradient boosting regressor model is in good agreement with experimental results, providing effective guidance for improving the performance of 7085 aluminum alloy sheets.