2025-04-14 アメリカ合衆国・リーハイ大学
＜関連情報＞
- https://engineering.lehigh.edu/news/article/novel-machine-learning-model-can-predict-material-failure-it-happens
- https://www.nature.com/articles/s41524-025-01530-8
稀な現象の予測を学ぶ：異常な粒成長の事例 Learning to predict rare events: the case of abnormal grain growth
Houliang Zhou,Benjamin Zalatan,Joan Stanescu,Martin P. Harmer,Jeffrey M. Rickman,Lifang He,Christopher J. Marvel & Brian Y. Chen
npj Computational Materials Published:27 March 2025
DOI:https://doi.org/10.1038/s41524-025-01530-8
Abstract
Abnormal grain growth (AGG) in polycrystalline microstructures, characterized by the rapid and disproportionate enlargement of a few “abnormal” grains relative to their surroundings, can lead to dramatic, often deleterious changes in the mechanical properties of materials, such as strength and toughness. Thus, the prediction and control of AGG is key to realizing robust mesoscale materials design. Unfortunately, it is challenging to predict these rare events far in advance of their onset because, at early stages, there is little to distinguish incipient abnormal grains from “normal” grains. To overcome this difficulty, we propose two machine learning approaches for predicting whether a grain will become abnormal in the future. These methods analyze grain properties derived from the spatio-temporal evolution of grain characteristics, grain-grain interactions, and a network-based analysis of these relationships. The first, PAL (Predicting Abnormality with LSTM), analyzes grain features using a long short-term memory (LSTM) network, and the second, PAGL (Predicting Abnormality with GCRN and LSTM), supplements the LSTM with a graph-based convolutional recurrent network (GCRN). We validated these methods on three distinct material scenarios with differing grain properties, observing that PAL and PAGL achieve high sensitivity and precision and, critically, that they are able to predict future abnormality long before it occurs. Finally, we consider the application of the deep learning models developed here to the prediction of rare events in different contexts.
