Machine learning-aided design of aluminum alloys with high performance

In this work, various machine learning (ML) techniques were employed to accelerate the designing of aluminum (Al) alloys with improved performance based on the age hardening concept. For this purpose, data of Al-Cu-Mg-x (x: Zn, Zr, etc.) alloys, including composition, aging condition (time and temperature), important physical and chemical properties, and hardness were collected from the literature to train the ML algorithms for predicting Al alloys with superior hardness. The results showed that the model obtained by the gradient boosted tree (GBT) could efficiently predict the hardness of unexplored alloys.

Automated summary

Through the use of various machine learning techniques, this study accelerated the process of designing aluminum alloys and found that the model obtained by gradient boosted tree (GBT) could efficiently predict the hardness of alloys.