基于损失函数和激活函数的无违背物理机器学习方法预测增材制造材料的应力-应变行为
摘要
预测增材制造材料的应力-应变行为对于增材制造中零件资格认证至关重要。传统物理基本构模型常简化材料特性，而数据驱动机器学习模型又缺乏物理一致性和可解释性。为此，我们提出一种物理信息机器学习（PIML）框架，以提高预测应力-应变曲线的预测性能和物理一致性。采用多项式回归模型预测AM工艺参数下的屈服点，然后将应力-应变曲线分割为弹性和塑性区域。分别训练两个长短期记忆网络（LSTM）预测两个区域。对于弹性区域，针对聚合物和金属均嵌入胡克定律；对于塑性区域，针对聚合物嵌入沃谢硬化定律，针对金属嵌入霍尔蒙定律。developed by embedding the physical laws into the loss and activation functions, respectively. The performance of the two PIML architectures are compared with two LSTM-based ML models, three additional ML models, and a physics-based constitutive model. These models are built on experimental data collected from two additively manufactured polymers (i.e., Nylon and carbon fiber-acrylonitrile butadiene styrene) and two additively manufactured metals (i.e., AlSi10Mg and Ti6Al4V). Experimental results demonstrate that two PIML architectures consistently outperform the other models. The segmental predictive model with activation-based PIML architecture achieves the lowest MAPE of 10.46+/-0.81% and the highest R^2 of 0.82+/-0.05 across four datasets.
引用
@article{arxiv.2603.14489,
title = {Predicting Stress-strain Behaviors of Additively Manufactured Materials via Loss-based and Activation-based Physics-informed Machine Learning},
author = {Chenglong Duan and Dazhong Wu},
journal= {arXiv preprint arXiv:2603.14489},
year = {2026}
}