Classification of T6 Tempered 6XXX Series Aluminum Alloys Based on Machine Learning Principles

Abstract

Aluminum alloys are widely used in each sector of engineering because of their lower density coupled with higher strength compared to many existing alloys of other metals. Due to these unique characteristics, there is acceleration in demand and discovery of new aluminum alloys with targeted properties and compositions. Traditional methods of designing new materials with desired properties, like ‘domain specialists and trial-and-error ' approaches, are laborious and costly. These techniques also lead to the expansion of alloy search area. Also, high demand for recycling of aluminum alloys requires fewer alloy groups. We suggest a machine learning design system to reduce the number of grades in the 6XXX series of aluminum alloys by collecting the features involving chemical composition and tensile properties at T6 tempering state. This work demonstrates the efficiency of grouping the aluminum alloys into a number of clusters by a combined PCA and K-means algorithm. To understand the physics inside the clusters we used an explainable artificial intelligence algorithm and connected the findings with sound metallurgical reasoning. Through machine learning we will narrow down the search space of 6XXX series aluminum alloys to few groups. This work offers a useful method for reducing compositional space of aluminum alloys.