Efficient screening of low liquidus Ti-based amorphous brazing filler metals via machine learning with limited experimental iteration
This work introduces a machine learning (ML) driven iterative framework for the accelerated design of low-liquidus-temperature Ti-based amorphous alloys in multicomponent alloy systems and identifies the optimal amorphous composition Ti60Cu11Ni19Zr10, exhibiting a low liquidus temperature of 1121 K.