Composition-based aluminum alloy selection using an artificial neural network

Abstract

Materials selection for aluminum alloys with desired fatigue and other mechanical properties is very difficult. Usually, when fatigue properties are maximized, other mechanical properties should be compromised. In this paper, an artificial neural network was utilized to build two prediction models that has the purpose of predicting fatigue life from composition and inverse design to predict composition from fatigue properties as a tool for materials selection. A first model was built to predict fatigue life using information on alloy composition, heat treatment, and other mechanical properties. The second model is an inversion of the first model, which predicts the material compositions to get the desired fatigue performance and other mechanical properties. Both models produce good performances based on the R2 scoring metric, where the values were found to be 0.92 and 0.96 for the first and second models, respectively. This study proved that the inversion model for predicting composition based on fatigue properties can reach acceptable accuracy and can be used as a materials selection tool. In addition, to investigate how atomic properties can affect fatigue life, the third model was built. It was found that atomic properties, such as electronegativity and the radius of alloying elements, are closely related to fatigue life and can be used to predict fatigue life as well. The significance of our work is that users can design new alloys for specific applications as well as select available alloys based on fatigue property criteria.

Comment on ‘Composition-based aluminum alloy selection using an artificial neural network’

“…Examples are shown in figures 4 and 5. Fatriansyah et al (2023) are to be complimented on their expertise in ANN modelling and also the processing of very large amounts of aluminium alloy property data, particularly with respect to metal fatigue. They have provided an exemplary contribution to understanding the precariousness and limitations of ANN modelling when it is applied without sufficient engineering knowledge about the properties, selection criteria, alloy compositions and processing of aerospace structural aluminium alloys.…”

“…Recently a paper was published in which artificial neural network (ANN) modelling was used to suggest selection of an aluminium alloy for aerospace applications on the basis of chemical composition, mechanical properties (especially unnotched fatigue strength), and atomistic features (Fatriansyah et al 2023). Three ANN models were used:…”

Machine learning enhanced prediction of permittivity of spinel microwave dielectric ceramics compared to traditional C-M calculation

“…Subsequently, experimental synthesis can be performed based on these predictions, thus improving the efficiency of research and development to a large extent [25,26]. Consequently, material scientists have actively applied these methods to predict various material properties, such as formation energy [27], band gap [28,29], electrical impedance [30], and fatigue life [31]. Moreover, machine learning approaches have been widely employed for predicting relative permittivity [32].…”