Capturing Local Temperature Evolution during Additive Manufacturing through Fourier Neural Operators (2024)

Skip Nav Destination

Article navigation

Research Papers

Accepted Manuscript

Jiangce Chen,

Jiangce Chen

5000 Forbes Ave. Pittsburgh, PA 15213-3890

Email: jiangce.chen@uconn.edu

Search for other works by this author on:

This Site

PubMed

Google Scholar

Wenzhuo Xu,

Wenzhuo Xu

5000 Forbes Ave Pittsburgh, PA 15289

Email: wxu2@andrew.cmu.edu

Search for other works by this author on:

This Site

PubMed

Google Scholar

Martha Baldwin,

Martha Baldwin

5000 Forbes Ave Pittsburgh, PA 15289

Email: mebaldwi@andrew.cmu.edu

Search for other works by this author on:

This Site

PubMed

Google Scholar

Bjorn Nijhuis,

Bjorn Nijhuis

P.O. Box 217 Enschede, Enschede NL7500AE Netherlands

Email: b.nijhuis@utwente.nl

Search for other works by this author on:

This Site

PubMed

Google Scholar

Ton van den Boogaard,

Ton van den Boogaard

P.O. Box 217 no Enschede, 7500 AE Netherlands

Email: A.H.vandenBoogaard@utwente.nl

Search for other works by this author on:

This Site

PubMed

Google Scholar

Abstract

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, the complexities of part geometries make it challenging for current models to maintain high accuracy across a wide range of geometries. Additionally, 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 paper presents a data-driven model that uses the Fourier Neural Operator to capture the local temperature evolution during the AM process. Beside 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.

Issue Section:

Research Paper

Keywords:

Modeling and simulation, Rapid prototyping and solid freeform fabrication

Topics:

Additive manufacturing, Modeling, Temperature, Convolutional neural networks, Architecture, Computer simulation, Design, Errors, Finite element methods, Production planning, Rapid prototyping, Simulation, Stereolithography, Weight (Mass)

This content is only available via PDF.

You do not currently have access to this content.

Sign In

Purchase this Content

$25.00

Purchase

Learn about subscription and purchase options

Product added to cart.

Check Out Continue Browsing Close Modal

1 Views

View Metrics

Get Email Alerts

Article Activity Alert

Accepted Manuscript Alert

New Issue Alert

Close Modal

Cited By

Google Scholar

Latest
Most Read
Most Cited

Investigation of Fiber Orientation of Fused Filament Fabricated CFRP Composites via an External Magnetic Field

J. Manuf. Sci. Eng

Identification of the Constitutive and Friction Models Parameters via a Multi-Objective Surrogate-Assisted Algorithm for the Modeling of Machining—Application to Arbitrary Lagrangian Eulerian Orthogonal Cutting of Ti6Al4V

J. Manuf. Sci. Eng (June 2024)

A manufacturability evaluation of complex architectures by laser powder bed fusion additive manufacturing

J. Manuf. Sci. Eng

Hole Edge Metrology and Inspection by Edge Diffractometry

J. Manuf. Sci. Eng

Understanding Process Parameter Effects of RepRap Open-Source Three-Dimensional Printers Through a Design of Experiments Approach

J. Manuf. Sci. Eng (February,2015)

Multiphysics Modeling and Experiments of Grayscale Photopolymerization With Application to Microlens Fabrication

J. Manuf. Sci. Eng (September,2021)

Hybrid-Light-Source Stereolithography for Fabricating Macro-Objects With Micro-Textures

J. Manuf. Sci. Eng (March,2022)

Scalable Multi-Material Additive Manufacturing of Bioinspired Polymeric Material With Metallic Structures Via Electrically Assisted Stereolithography

J. Manuf. Sci. Eng (January,2023)

Related Proceedings Papers

Physics-Based Feedforward Control of Thermal History in Laser Powder Bed Fusion Additive Manufacturing

MSEC2023

Modeling and Fabrication of Heterogeneous Three-Dimensional Objects Based on Additive Manufacturing

IMECE2013

Capturing Local Temperature Evolution During Additive Manufacturing Through Fourier Neural Operators

IDETC-CIE2023

Related Chapters

Design of Space Net Capture System and Simulation

International Conference on Mechanical and Electrical Technology, 3rd, (ICMET-China 2011), Volumes 1–3

Advances in the Stochastic Modeling of Constitutive Laws at Small and Finite Strains

Advances in Computers and Information in Engineering Research, Volume 2

Novel and Efficient Mathematical and Computational Methods for the Analysis and Architecting of Ultralight Cellular Materials and their Macrostructural Responses

Advances in Computers and Information in Engineering Research, Volume 2

Capturing Local Temperature Evolution during Additive Manufacturing through Fourier Neural Operators (2024)

Abstract

Sign In

Purchase this Content

Product added to cart.

Get Email Alerts

Cited By

Related Articles

Related Proceedings Papers

Related Chapters

References