Machine learning assisted design of Ni-based superalloys with excellent high-temperature performance

Due to compositional complexity, designing superalloys with multiple targeted properties is a great challenge. Here, we propose a workflow that incorporates composition and high-temperature mechanical performance into machine learning to optimize commercial K403 superalloys for the needs of increasing service temperature of hot-end parts in aircraft engine and gas turbine. Moreover, multiple properties including microstructure stability, the volume fraction of gamma' precipitates, processing window, freezing range and density were simultaneously optimized to select 7 superalloys from 15,625 candidates. One selected superalloy was experimentally synthesized. Compared with the commercial K403 superalloy, the creep rupture life of the newly-designed superalloy is improved around three times at 975 degrees C and even 1025 degrees C. The predicted high-temperature creep rupture life and yield strength using the machine learning model is in excellent agreement with experiments. The current machine learning approach provides guidance for the rapid design of multi-component superalloys with targeted multiple desired functionalities.

Automated summary

By integrating composition and high-temperature mechanical performance into machine learning, a workflow was proposed to optimize commercial K403 superalloys for increased service temperature of hot-end parts in aircraft engines and gas turbines. The machine learning model successfully selected 7 superalloys, one of which exhibited improved creep rupture life compared to the commercial K403 alloy.