Help Desk -
9958816305, 9810335381
Email
Password

Japanese Scientists Use ML to Understand Aluminum Alloys

Metal News - Published on Mon, 03 Aug 2020

Image Source: Machine Learning Aluminum Alloys
Japanese scientists have developed a machine learning approach that can predict the elements and manufacturing processes needed to obtain an aluminum alloy with specific, desired mechanical properties. Ryo Tamura and colleagues at Japan’s National Institute for Materials Science and Toyota Motor Corporation developed a materials informatics technique that feeds known data from aluminum alloy databases into a machine learning model. This trains the model to understand relationships between alloys’ mechanical properties and the different elements they are made of, as well as the type of heat treatment applied during manufacturing. Once the model is provided enough data, it can then predict what is required to manufacture a new alloy with specific mechanical properties, all this without the need for input or supervision from a human.

They wrote “The relations between the mechanical properties, heat treatment, and compositions of elements in aluminum alloys are extracted by a materials informatics technique. In our strategy, a machine learning model is first trained by a prepared database to predict the properties of materials. The dependence of the predicted properties on explanatory variables, that is, the type of heat treatment and element composition, is searched using a Markov chain Monte Carlo method. From the dependencies, a factor to obtain the desired properties is investigated. Using targets of 5000, 6000, and 7000 series aluminum alloys, we extracted relations that are difficult to find via simple correlation analysis. Our method is also used to design an experimental plan to optimize the materials properties while promoting the understanding of target materials.”

Aluminum alloys are lightweight, energy-saving materials made predominantly from aluminum, but also contain other elements, such as magnesium, manganese, silicon, zinc and copper. The combination of elements and manufacturing process determines how resilient the alloys are to various stresses. The model found 5000 series aluminum alloys that are highly resistant to stress and deformation can be made by increasing the manganese and magnesium content and reducing the aluminum content.

The 5000 series aluminum alloys are classified into alloys that cannot be heat treated, where Mg is added to increase the strength. In addition to Al (94.25–99.19 wt%) and Mg (0.40–5.05 wt%), Fe (0.13–0.35 wt%), Mn (0.01–0.75 wt%), Si (0.08–0.23 wt%), Ti (0.00–0.10 wt%), Cu (0.02–0.10 wt%), Cr (0.00–0.25 wt%), and Zn (0.015–0.125 wt%) are mixed in the alloys. The two-dimensional temper designations HXn (X = 1, 2, 3, 4 and n = 1, ..., 9) are used to distinguish the applied combination of basic operations X and the degree of strain-hardening n. Table S1 summarizes the meanings of these temper designations [41,42]. The temper designations are used for explanatory variables as well as for the compositions of the elements above. When the mechanical properties are predicted, an integer value of the temper designations is adopted.

The 6000 and 7000 series aluminum alloys are the heat-treatable alloys. For these alloys, the temper designation is given as TX (X = 1, ..., 10) [41,42] (Table S2). In the 6000 series, Fe (0.18–0.50 wt%), Mn (0.02–0.70 wt%), Si (0.40–1.00 wt%), Al (96.16–98.63 wt%), Mg (0.48–1.00 wt%), Ti (0.00–0.08 wt%), Cu (0.05–0.43 wt%), Cr (0.00–0.25 wt%), and Zn (0.05–0.13 wt%) elements are contained, while Fe (0.06–0.35 wt%), Mn (0.03–0.45 wt%), Si (0.05–0.35 wt%), Al (87.05–98.10 wt%), Mg (0.05–2.75 wt%), Ti (0.00–0.17 wt%), Cu (0.05–2.30 wt%), Cr (0.00–1.15 wt%), V (0.00–0.05 wt%), Zr (0.00–0.15 wt%), and Zn (1.05–7.80 wt%) elements are mixed in the 7000 series. The one-dimensional integer temper designation is used as an explanatory variable for the 6000 and 7000 series. The detailed databases for the 5000, 6000, and 7000 series are 5000.csv, 6000.csv, and 7000.csv, respectively.

Source :

Posted By : Yogender Pancholi on Mon, 03 Aug 2020
Related News from Metal segment