3D temperature field prediction in direct energy deposition of metals using physics informed neural network

• 全文链接
• 请求原文

作   者：

Xie, Jibing;  Chai, Ze;  Xu, Luming;  Ren, Xukai;  Liu, Sheng;  Chen, Xiaoqi; 

作者机构：

Shanghai Jiao Tong Univ; 

关键词：

DIRECT LASER DEPOSITION;  Direct energy deposition;  VALIDATION;  PATHS;  Physics-informed neural network;  Temperature field;  Physics-data hybrid machine learning; 

期刊名称：

The International Journal of Advanced Manufacturing Technology

i s s n：

0268-3768

年卷期：

2022 年 119 卷 5/6 期

页   码：

3449-3468

页   码：

摘   要：

Predicting the temperature field during the direct energy deposition (DED) process is vital for the microstructure control and property tuning of fabricated metals. The widely used data-driven machine learning method for accurate temperature prediction, however, is impractical and computation-intensive due to its sole reliance on large datasets; also being a blackbox model in nature, it lacks interpretability. We propose a physics informed neural network (PINN) model, which adopts a novel physics-data hybrid method by embedding the heat transfer law into the loss function of the neural network, to model the temperature field in both single-layer and multi-layer DED. The results show that the PINN-based models with additional extrapolation ability can accurately predict temperatures with a mean relative error of 4.83%, and achieve identical prediction accuracy with only 20% of the labeled data required for training the data-driven deep neural network. The proposed model is more explainable in terms of the physics of the DED process and is also applicable for the DED of different metals.