About this Abstract |
Meeting |
MS&T24: Materials Science & Technology
|
Symposium
|
Additive Manufacturing Modeling, Simulation, and Machine Learning: Microstructure, Mechanics, and Process
|
Presentation Title |
Heat Treatment Design for Laser-Melted Medium Entropy Alloys via Machine Learning and Gradient-Temperature Experiments |
Author(s) |
Luis Ladinos Pizano, Daozheng Li, Wei Zhang , Wei Xiong |
On-Site Speaker (Planned) |
Luis Ladinos Pizano |
Abstract Scope |
The medium entropy alloy prepared with 77wt%In718 and 23wt%SS316L stands out for having a refined granular structure after being printed using the laser powder bed fusion technique. However, it is necessary to strengthen the material by precipitating the γ' and γ'' phases through post-heat treatments. In this work, supported by high-throughput experiments, the machine learning method is used to explore the effect of aging conditions on hardening effects. Through a gradient-temperature heat treatment, a large dataset of hardness was generated and used to build a Gaussian progress regression model. The hardness profiles showed a Gaussian distribution with a peak around 720ºC. However, the transformation of γ” into δ decreases the hardness. Furthermore, it was discovered that the most energy-effective way to maximize the alloy strength is to use a heat treatment defined as 715ºC/4h + 600ºC/9h. This work proposes a novel methodology to optimize aging heat treatment, maximizing resources. |