Prediction of the Mechanical Properties of Aluminum Alloy Using Bayesian Learning for Neural Networks

Abstract

The strengthening mechanism of the 2000 series aluminum alloy has been studied using neural networks. We have constructed a neural network for the simultaneous prediction of multiple mechanical properties, including ultimate tensile strength, tensile yield strength, and elongation at break. The replica-exchange Monte Carlo method, an improved Markov chain Monte Carlo (MCMC) method, has been applied for Bayesian learning of the optimal neural network architecture and hyperparameters. The obtained neural network, combined with the thermodynamic analysis using the Thermo-Calc software, enables us to identify a dominant combination of additive elements and heat treatments for strengthening alloys. We have also addressed an inverse problem for optimizing the process parameters. The approach we propose will accelerate the design of high strength alloys for high-temperature applications.