Researchers utilize machine learning to predict elastic properties of amorphous metal alloys

A paper saw light in Physica A: Statistical Mechanics and Its Applications.

Artificial intelligence defines the relationship between different physical and chemical characteristics and evaluates the value of the Jung module (elastic modulus).

"The modulus of elasticity is the key mechanical property determining the stability of solid bodies to stretching and compression. It plays a crucial role in the development of functional materials based on amorphous metal alloys. The Jung module directly characterizes the mechanical stability of constructions," explains Bulat Galimzyanov, Associate Professor of the Department of Computational Physics and Modeling of Physical Processes.

The value of amorphous alloys (they are obtained by quickly cooling the metal melt) is that they can be stronger than their crystalline counterparts. Amorphous alloys are used in the production of various materials for mechanical engineering and other industries.

KFU physicists used data on over 300 alloys containing aluminium, copper, iron, and other metals to train the neural network.

"Artificial intelligence helped us find out that the modulus of elasticity is mainly influenced by two indicators: the yield limit and the glass transition temperature of the material. The first value shows at what physical load the alloy begins to deform, and the second—the temperature at which the liquid melt solidifies into amorphous alloy," adds Galimzyanov.

For two parameters, the error of the results of the neural network in determining the Jung module was only 2 percent. At the same time, it was found that the chemical properties of the alloy (quantity and molecular mass of its constituent elements) do not affect the resistance to tension and compression.

he method developed at Kazan University will help simplify and accelerate the development of new metals for the industry.

More information:
Machine learning-based prediction of elastic properties of amorphous metal alloys
www.sciencedirect.com/science/ … ii/S0378437123002339

Provided by Kazan Federal University