TY - JOUR
T1 - Capturing Local Temperature Evolution During Additive Manufacturing Through Fourier Neural Operators
AU - Chen, Jiangce
AU - Xu, Wenzhuo
AU - Baldwin, Martha
AU - Nijhuis, Björn
AU - van Den Boogaard, Ton
AU - Grande Gutiérrez, Noelia
AU - Prabha Narra, Sneha
AU - Mccomb, Christopher
N1 - Publisher Copyright:
Copyright © 2024 by ASME.
PY - 2024/9/1
Y1 - 2024/9/1
N2 - High-fidelity, data-driven models that can quickly simulate thermal behavior during additive manufacturing (AM) are crucial for improving the performance of AM technologies in multiple areas, such as part design, process planning, monitoring, and control. However, complexities of part geometries make it challenging for current models to maintain high accuracy across a wide range of geometries. In addition, many models report a low mean-square error (MSE) across the entire domain of a part. However, in each time-step, most areas of the domain do not experience significant changes in temperature, except for the regions near recent depositions. Therefore, the MSE-based fidelity measurement of the models may be overestimated. This article presents a data-driven model that uses the Fourier neural operator to capture the local temperature evolution during the AM process. Besides MSE, the model is also evaluated using the R2 metric, which places great weight on the regions where the temperature changes significantly than MSE. The model was trained and tested on numerical simulations based on the discontinuous Galerkin finite element method for the direct energy deposition AM process. The results shows that the model maintains 0.983-0.999 R2 over geometries not included in the training data, which is higher than convolutional neural networks and graph convolutional neural networks we implemented, the two widely used architectures in data-driven predictive modeling.
AB - High-fidelity, data-driven models that can quickly simulate thermal behavior during additive manufacturing (AM) are crucial for improving the performance of AM technologies in multiple areas, such as part design, process planning, monitoring, and control. However, complexities of part geometries make it challenging for current models to maintain high accuracy across a wide range of geometries. In addition, many models report a low mean-square error (MSE) across the entire domain of a part. However, in each time-step, most areas of the domain do not experience significant changes in temperature, except for the regions near recent depositions. Therefore, the MSE-based fidelity measurement of the models may be overestimated. This article presents a data-driven model that uses the Fourier neural operator to capture the local temperature evolution during the AM process. Besides MSE, the model is also evaluated using the R2 metric, which places great weight on the regions where the temperature changes significantly than MSE. The model was trained and tested on numerical simulations based on the discontinuous Galerkin finite element method for the direct energy deposition AM process. The results shows that the model maintains 0.983-0.999 R2 over geometries not included in the training data, which is higher than convolutional neural networks and graph convolutional neural networks we implemented, the two widely used architectures in data-driven predictive modeling.
KW - NLA
KW - directed energy deposition
KW - Fourier neural operators
KW - modeling and simulation
KW - rapid prototyping and solid freeform fabrication
KW - temperature evolution
KW - thermal simulation
KW - additive manufacturing
UR - http://www.scopus.com/inward/record.url?scp=85195404900&partnerID=8YFLogxK
U2 - 10.1115/1.4065316
DO - 10.1115/1.4065316
M3 - Article
AN - SCOPUS:85195404900
SN - 1087-1357
VL - 146
JO - Journal of manufacturing science and engineering
JF - Journal of manufacturing science and engineering
IS - 9
M1 - 091001
ER -