.png){kind=icon}
.png){kind=icon}
Return
A pretraining-finetuning computational framework for material homogenization
.png){kind=icon}
PRE
AI
DOI：10.1016/j.ijmecsci.2026.111388.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• PreFine-Homo is a pretraining--finetuning framework for homogenization. • PreFine-Homo combines data-driven pretraining and physics-informed fine-tuning. • PreFine-Homo self-learns as data grows, strengthening the pretraining stage. • Fine-tuning ensures high precision and improved robustness. • PreFine-Homo achieves high efficiency, accuracy, and resolution independence.
Keywords:
pretraining
fine-tuning
material homogenization
data-driven
physics-informed
Journal
IF:
9.4
Papers:
1.0W
Citations:
4.5W
Organization
View more organizations