The learning of the precipitates morphological parameters from the composition of nickel-based superalloys
Yunqiang Wang, Mingming Lu, Zi Wang, Jin Liu, Lei Xu, Zijun Qin, Zexin Wang, Bingfeng Wang, Feng Liu, Jianxin Wang
Abstract
It becomes a common practice to adopt high-throughput experiments on superalloys, which can generate a large amount of data. To address this large amount of data, we designed a machine learning (ML) based model to automate the experimental analysis process. More specifically, we adopted the Unet algorithm to segment the precipitated phases from superalloy images and subsequently used a regression algorithm to predict the morphological parameters of the microstructure of the segmented precipitated phases according to their composition. The method proposed in this work may provide guidance for the future design of the superalloy composition.