Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
169 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Capturing Local Temperature Evolution during Additive Manufacturing through Fourier Neural Operators (2307.01804v1)

Published 4 Jul 2023 in cs.LG and cs.CG

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 (part). However, in each time step, most areas of the domain do not experience significant changes in temperature, except for the heat-affected zones near recent depositions. Therefore, the MSE-based fidelity measurement of the models may be overestimated. This paper presents a data-driven model that uses Fourier Neural Operator to capture the local temperature evolution during the additive manufacturing process. In addition, the authors propose to evaluate the model using the $R2$ metric, which provides a relative measure of the model's performance compared to using mean temperature as a prediction. The model was tested on numerical simulations based on the Discontinuous Galerkin Finite Element Method for the Direct Energy Deposition process, and the results demonstrate that the model achieves high fidelity as measured by $R2$ and maintains generalizability to geometries that were not included in the training process.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (39)
  1. Skexgen: Autoregressive generation of cad construction sequences with disentangled codebooks. arXiv preprint arXiv:2207.04632, 2022.
  2. Large-scale metal additive manufacturing: a holistic review of the state of the art and challenges. International Materials Reviews, 67(4):410–459, 2022.
  3. Geometry-agnostic data-driven thermal modeling of additive manufacturing processes using graph neural networks. Additive Manufacturing, 48:102449, 2021.
  4. Mechanical properties of hybrid additively manufactured inconel 718 parts created via thermal control after secondary treatment processes. Journal of Materials Processing Technology, 291:117047, 2021.
  5. Modeling process–structure–property relationships in metal additive manufacturing: a review on physics-driven versus data-driven approaches. Journal of Physics: Materials, 4(3):032002, 2021.
  6. Dataset of process-structure-property feature relationship for laser powder bed fusion additive manufactured ti-6al-4v material. Data in Brief, page 108911, 2023.
  7. Process-structure linkages using a data science approach: application to simulated additive manufacturing data. Integrating materials and manufacturing innovation, 6(1):54–68, 2017.
  8. Defect structure process maps for laser powder bed fusion additive manufacturing. Additive Manufacturing, 36:101552, 2020.
  9. Data-driven analysis of process, structure, and properties of additively manufactured inconel 718 thin walls. npj Computational Materials, 8(1):1–15, 2022.
  10. Melt pool feature analysis using a high-speed coaxial monitoring system for laser powder bed fusion of ti-6al-4 v grade 23. The International Journal of Advanced Manufacturing Technology, 120(9):6497–6514, 2022.
  11. Simulation of melt pool behaviour during additive manufacturing: Underlying physics and progress. Additive Manufacturing, 31:100909, 2020.
  12. Evaporation model for keyhole dynamics during additive manufacturing of metal. Physical Review Applied, 14(6):064039, 2020.
  13. T Mukherjee and Tarasankar DebRoy. Mitigation of lack of fusion defects in powder bed fusion additive manufacturing. Journal of Manufacturing Processes, 36:442–449, 2018.
  14. Evolution of grain structure during laser additive manufacturing. simulation by a cellular automata method. Materials & Design, 106:321–329, 2016.
  15. A new procedure for implementing the modified inherent strain method with improved accuracy in predicting both residual stress and deformation for laser powder bed fusion. Additive Manufacturing, 47:102345, 2021.
  16. Efficient thermal simulation of large-scale metal additive manufacturing using hot element addition. Computers & Structures, 245:106463, 2021.
  17. Differentiable simulation for material thermal response design in additive manufacturing processes. Additive Manufacturing, 61:103337, 2023.
  18. Thermodynamics-guided alloy and process design for additive manufacturing. Nature communications, 13(1):1–12, 2022.
  19. Applications of machine learning in process monitoring and controls of l-pbf additive manufacturing: A review. Applied Sciences, 11(24):11910, 2021.
  20. In-situ monitoring of sub-surface and internal defects in additive manufacturing: A review. Materials & Design, page 111063, 2022.
  21. Data-driven prediction of the high-dimensional thermal history in directed energy deposition processes via recurrent neural networks. Manufacturing letters, 18:35–39, 2018.
  22. A real-time iterative machine learning approach for temperature profile prediction in additive manufacturing processes. In 2019 IEEE International Conference on Data Science and Advanced Analytics (DSAA), pages 541–550. IEEE, 2019.
  23. Real-time simulation for long paths in laser-based additive manufacturing: a machine learning approach. The International Journal of Advanced Manufacturing Technology, 104(5):1967–1984, 2019.
  24. Data-driven modeling of thermal history in additive manufacturing. Additive Manufacturing, 32:101017, 2020.
  25. Towards a generic physics-based machine learning model for geometry invariant thermal history prediction in additive manufacturing. Journal of Materials Processing Technology, 302:117472, 2022.
  26. Multilayer feedforward networks are universal approximators. Neural networks, 2(5):359–366, 1989.
  27. Universal approximation to nonlinear operators by neural networks with arbitrary activation functions and its application to dynamical systems. IEEE Transactions on Neural Networks, 6(4):911–917, 1995.
  28. Model reduction and neural networks for parametric pdes. arXiv preprint arXiv:2005.03180, 2020.
  29. Neural operator: Graph kernel network for partial differential equations. arXiv preprint arXiv:2003.03485, 2020.
  30. Deeponet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators. arXiv preprint arXiv:1910.03193, 2019.
  31. Fourier neural operator for parametric partial differential equations. arXiv preprint arXiv:2010.08895, 2020.
  32. A physics-informed operator regression framework for extracting data-driven continuum models. Computer Methods in Applied Mechanics and Engineering, 373:113500, 2021.
  33. Neural discrete representation learning. Advances in neural information processing systems, 30, 2017.
  34. Modified inherent strain method for predicting residual deformation and stress in metal additive manufacturing. Additive Manufacturing Technology: Design, Optimization, and Modeling, pages 219–265, 2023.
  35. A comprehensive survey on transfer learning. Proceedings of the IEEE, 109(1):43–76, 2020.
  36. Physics informed deep learning (part i): Data-driven solutions of nonlinear partial differential equations. arXiv preprint arXiv:1711.10561, 2017.
  37. Machine learning for metal additive manufacturing: predicting temperature and melt pool fluid dynamics using physics-informed neural networks. Computational Mechanics, 67(2):619–635, 2021.
  38. Model order reduction of physical systems, February 2 2023. US Patent App. 17/386,674.
  39. Surrogate modeling for physical systems with preserved properties and adjustable tradeoffs. arXiv preprint arXiv:2202.01139, 2022.
Citations (2)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now