The paper saw the light in Physica A: Statistical Mechanics and Its Applications.
Artificial intelligence defines the relationships between various physical and chemical properties and evaluates the value of the Jungian modulus (modulus of elasticity).
“The elastic modulus is an important mechanical property that determines the stability of solids against tension and compression. It plays an important role in the development of functional materials based on amorphous metal alloys. ,” explains Bulat Galimzyanov, Associate Professor in the Department of Computational Physics and Modeling of Physical Processes.
The value of amorphous alloys (obtained by rapidly cooling a metallic melt) is that they can be stronger than their crystalline counterparts. It is used in the manufacture of various materials.
Physicists at KFU trained the neural network using data on over 300 alloys including aluminum, copper, iron, and other metals.
“Thanks to artificial intelligence, we have found that the modulus is primarily influenced by two indices: the yield limit and the glass transition temperature of the material. The first value indicates the physical load at which the alloy begins to deform. , the second value is the temperature at which the liquid melt solidifies into an amorphous alloy,” Garimzhanov adds.
For two parameters, the neural network’s resulting error in determining the Jungian module was only 2%. At the same time, we found that the chemical properties of the alloy (the amounts and molecular weights of its constituent elements) do not affect its resistance to tension and compression.
A method developed at Kazan University will help simplify and accelerate the development of new metals for industry.
For more information:
Machine Learning Based Prediction of Elastic Properties of Amorphous Metal Alloys
www.sciencedirect.com/science/…ii/S0378437123002339
Courtesy of Kazan Federal University
