Materials informatics approach to understand aluminum alloys

Abstract

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.

Materials informatics for developing new restorative dental materials: a narrative review

“…Materials informatics (MI) is a field of research in materials science, and its significance has increased steadily in the discovery of new materials such as alloys (1)(2)(3), polymers (4,5), and ceramics (6). Some of materials have been successfully synthesized according to the discovery (7)(8)(9).…”

Experimental and Numerical Simulation Studies on V-Shaped Bending of Aluminum/CFRP Laminates

“…CFRP/metal composite laminates [7][8][9] can effectively reduce the cost of production, without compromising strength and stiffness, while overcoming the shortcomings of single material performance [10,11]. With the development of automotive lightweighting, 7000 series aluminum alloy materials have gradually replaced traditional steel materials [12][13][14][15][16]. A composite of 7000 series aluminum alloy and CFRP material can obtain excellent comprehensive performance of the high strength of CFRP and the good toughness of aluminum alloy.…”

Experimental design for the highly accurate prediction of material properties using descriptors obtained by measurement

“…A reliable strategy for obtaining an accurate prediction model is feature selection, which searches for important features that increase prediction performance [19][20][21][22]. In this study, however we focus on another strategy: active learning, which selects new data points to be added to the training dataset to improve the prediction accuracy.…”