Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
89 tokens/sec
Gemini 2.5 Pro Premium
50 tokens/sec
GPT-5 Medium
29 tokens/sec
GPT-5 High Premium
28 tokens/sec
GPT-4o
90 tokens/sec
DeepSeek R1 via Azure Premium
55 tokens/sec
GPT OSS 120B via Groq Premium
468 tokens/sec
Kimi K2 via Groq Premium
207 tokens/sec
2000 character limit reached

A Spectral-based Physics-informed Finite Operator Learning for Prediction of Mechanical Behavior of Microstructures (2410.19027v3)

Published 24 Oct 2024 in cond-mat.mtrl-sci, cs.CE, and physics.comp-ph

Abstract: A novel physics-informed operator learning technique based on spectral methods is introduced to model the complex behavior of heterogeneous materials. The Lippmann-Schwinger operator in Fourier space is employed to construct physical constraints with minimal computational overhead, effectively eliminating the need for automatic differentiation. The introduced methodology accelerates the training process by enabling gradient construction on a fixed, finite discretization in Fourier space. Later, the spectral physics-informed finite operator learning (SPiFOL) framework is built based on this discretization and trained to map the arbitrary shape of microstructures to their mechanical responses (strain fields) without relying on labeled data. The training is done by minimizing equilibrium in Fourier space concerning the macroscopic loading condition, which also guarantees the periodicity. SPiFOL, as a physics-informed operator learning method, enables rapid predictions through forward inference after training. To ensure accuracy, we incorporate physical constraints and diversify the training data. However, performance may still degrade for out-of-distribution microstructures. SPiFOL is further enhanced by integrating a Fourier Neural Operator (FNO). Compared to the standard data-driven FNO, SPiFOL shows higher accuracy in predicting stress fields and provides nearly resolution-independent results. Additionally, its zero-shot super-resolution capabilities are explored in heterogeneous domains. Finally, SPiFOL is extended to handle 3D problems and further adapted to finite elasticity, demonstrating the robustness of the framework in handling nonlinear mechanical behavior. The framework shows great potential for efficient and scalable prediction of mechanical responses in complex material systems while also reducing the training time required for training physics-informed neural operators.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (66)
  1. Eighty years of the finite element method: Birth, evolution, and future. Archives of Computational Methods in Engineering, 29(6):4431–4453, 2022.
  2. Gary A Sod. A survey of several finite difference methods for systems of nonlinear hyperbolic conservation laws. Journal of computational physics, 27(1):1–31, 1978.
  3. Spectral methods: algorithms, analysis and applications, volume 41. Springer Science & Business Media, 2011.
  4. Physics-informed machine learning. Nature Reviews Physics, 3(6):422–440, 2021.
  5. Physics-informed deep learning for computational elastodynamics without labeled data. Journal of Engineering Mechanics, 147(8):04021043, 2021.
  6. A mixed formulation for physics-informed neural networks as a potential solver for engineering problems in heterogeneous domains: Comparison with finite element method. Computer Methods in Applied Mechanics and Engineering, 401:115616, 2022.
  7. Mixed formulation of physics-informed neural networks for thermo-mechanically coupled systems and heterogeneous domains. International Journal for Numerical Methods in Engineering, 125(4):e7388, 2024.
  8. Physics-informed neural networks with hard constraints for inverse design. SIAM Journal on Scientific Computing, 43(6):B1105–B1132, 2021a.
  9. Physics-informed neural networks for inverse problems in nano-optics and metamaterials. Opt. Express, 28(8):11618–11633, Apr 2020.
  10. When and why pinns fail to train: A neural tangent kernel perspective. Journal of Computational Physics, 449:110768, 2022a.
  11. Characterizing possible failure modes in physics-informed neural networks. Advances in neural information processing systems, 34:26548–26560, 2021.
  12. Learning nonlinear operators via deeponet based on the universal approximation theorem of operators. Nature Machine Intelligence, 2021b.
  13. Deep learning operator network for plastic deformation with variable loads and material properties. Engineering with Computers, 40(2):917–929, 2024.
  14. Novel deeponet architecture to predict stresses in elastoplastic structures with variable complex geometries and loads. Computer Methods in Applied Mechanics and Engineering, 415:116277, 2023.
  15. A physics-informed variational deeponet for predicting crack path in quasi-brittle materials. Computer Methods in Applied Mechanics and Engineering, 391:114587, 2022. ISSN 0045-7825.
  16. Improved architectures and training algorithms for deep operator networks. Journal of Scientific Computing, 92(2):35, 2022b.
  17. En-deeponet: An enrichment approach for enhancing the expressivity of neural operators with applications to seismology. Computer Methods in Applied Mechanics and Engineering, 420:116681, 2024.
  18. A comprehensive and fair comparison of two neural operators (with practical extensions) based on fair data. Computer Methods in Applied Mechanics and Engineering, 393:114778, 2022.
  19. Learning nonlinear operators in latent spaces for real-time predictions of complex dynamics in physical systems. Nature Communications, 15(1):5101, 2024.
  20. Geom-deeponet: A point-cloud-based deep operator network for field predictions on 3d parameterized geometries. Computer Methods in Applied Mechanics and Engineering, 429:117130, 2024.
  21. A resolution independent neural operator. arXiv preprint arXiv:2407.13010, 2024.
  22. Neural operator: Graph kernel network for partial differential equations. arXiv:2003.03485, 2020a.
  23. Neural operator: Learning maps between function spaces with applications to pdes. Journal of Machine Learning Research, 24(89):1–97, 2023.
  24. Fourier neural operator with learned deformations for pdes on general geometries. Journal of Machine Learning Research, 24(388):1–26, 2023a.
  25. Learning the stress-strain fields in digital composites using fourier neural operator. iScience, 25:105452, 11 2022.
  26. Learning deep implicit fourier neural operators (ifnos) with applications to heterogeneous material modeling. Computer Methods in Applied Mechanics and Engineering, 398:115296, 2022. ISSN 0045-7825.
  27. Homogenius: a foundation model of homogenization for rapid prediction of effective mechanical properties using neural operators. arXiv preprint arXiv:2404.07943, 2024.
  28. Operator learning: Algorithms and analysis. arXiv preprint arXiv:2402.15715, 2024.
  29. Chapter 3 - a mathematical guide to operator learning. In Siddhartha Mishra and Alex Townsend, editors, Numerical Analysis Meets Machine Learning, volume 25 of Handbook of Numerical Analysis, pages 83–125. Elsevier, 2024.
  30. Physics-guided, physics-informed, and physics-encoded neural networks in scientific computing. arXiv preprint arXiv:2211.07377, 2022.
  31. Learning the solution operator of parametric partial differential equations with physics-informed deeponets. Science advances, 7(40):eabi8605, 2021.
  32. Phase-field deeponet: Physics-informed deep operator neural network for fast simulations of pattern formation governed by gradient flows of free-energy functionals. Computer Methods in Applied Mechanics and Engineering, 416:116299, 2023b.
  33. Physics-informed neural operator for learning partial differential equations. arXiv:2111.03794, 2023c.
  34. Divergence-free neural operators for stress field modeling in polycrystalline materials. arXiv preprint arXiv:2408.15408, 2024.
  35. Comparison of two artificial neural networks trained for the surrogate modeling of stress in materially heterogeneous elastoplastic solids. arXiv preprint arXiv:2210.16994, 2022.
  36. Revealing the predictive power of neural operators for strain evolution in digital composites. Journal of the Mechanics and Physics of Solids, 181:105444, 2023.
  37. Transfer learning enhanced physics informed neural network for phase-field modeling of fracture. Theoretical and Applied Fracture Mechanics, 106:102447, 2020.
  38. Applications of physics informed neural operators. Machine Learning: Science and Technology, 4(2):025022, 2023.
  39. Can-pinn: A fast physics-informed neural network based on coupled-automatic–numerical differentiation method. Computer Methods in Applied Mechanics and Engineering, 395:114909, 2022. ISSN 0045-7825.
  40. Phycrnet: Physics-informed convolutional-recurrent network for solving spatiotemporal pdes. Computer Methods in Applied Mechanics and Engineering, 389:114399, 2022.
  41. Physics-informed convolutional neural networks for temperature field prediction of heat source layout without labeled data. Engineering Applications of Artificial Intelligence, 117:105516, 2023.
  42. A physics-informed convolutional neural network for the simulation and prediction of two-phase darcy flows in heterogeneous porous media. Journal of Computational Physics, 477:111919, 2023.
  43. Solving the discretised neutron diffusion equations using neural networks. International Journal for Numerical Methods in Engineering, 124(21):4659–4686, 2023.
  44. A finite operator learning technique for mapping the elastic properties of microstructures to their mechanical deformations, 2024a.
  45. A finite element-based physics-informed operator learning framework for spatiotemporal partial differential equations on arbitrary domains. Engineering with Computers, pages 1–29, 2024.
  46. Finite operator learning: Bridging neural operators and numerical methods for efficient parametric solution and optimization of pdes. arXiv preprint arXiv:2407.04157, 2024b.
  47. A review of the fe 2 method for composites. Multiscale and Multidisciplinary Modeling, Experiments and Design, 4:1–24, 2021.
  48. A review of fe-fft-based two-scale methods for computational modeling of microstructure evolution and macroscopic material behavior. Archives of Computational Methods in Engineering, 29(6):4115–4135, 2022.
  49. Fft based approaches in micromechanics: fundamentals, methods and applications. Modelling and Simulation in Materials Science and Engineering, 30(2):023002, 2021.
  50. Matti Schneider. A review of nonlinear fft-based computational homogenization methods. Acta Mechanica, 232(6):2051–2100, 2021.
  51. A consistent discretization via the finite radon transform for fft-based computational micromechanics. Computational Mechanics, pages 1–20, 2024.
  52. An fft-based crystal plasticity phase-field model for micromechanical fatigue cracking based on the stored energy density. International Journal of Fatigue, 172, 2023.
  53. Fft-based surrogate modeling of auxetic metamaterials with real-time prediction of effective elastic properties and swift inverse design, 2024.
  54. An assessment of numerical techniques to find energy-minimizing microstructures associated with nonconvex potentials. International Journal for Numerical Methods in Engineering, 121(7):1595–1628, 2020.
  55. On polarization-based schemes for the fft-based computational homogenization of inelastic materials. Computational Mechanics, 64:1073–1095, 2019.
  56. A numerical method for computing the overall response of nonlinear composites with complex microstructure. Computer methods in applied mechanics and engineering, 157(1-2):69–94, 1998.
  57. Fourier neural operator for parametric partial differential equations. arXiv preprint arXiv:2010.08895, 2020b.
  58. Neural tangent kernel: Convergence and generalization in neural networks. Advances in neural information processing systems, 31, 2018.
  59. Jax: composable transformations of python+ numpy programs. 2018.
  60. Optuna: A next-generation hyperparameter optimization framework. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2019.
  61. Physics-informed neural operator for learning partial differential equations. ACM/JMS Journal of Data Science, 1(3):1–27, 2024.
  62. Challenges in two-scale computational homogenization of mechanical metamaterials. PAMM, 23(1):e202200139, 2023.
  63. On the effectiveness of neural operators at zero-shot weather downscaling. arXiv preprint arXiv:2409.13955, 2024.
  64. Efficient fixed point and newton–krylov solvers for fft-based homogenization of elasticity at large deformations. Computational Mechanics, 54(6):1497–1514, 2014.
  65. Factorized fourier neural operators. arXiv preprint arXiv:2111.13802, 2021.
  66. A survey of complex-valued neural networks. arXiv preprint arXiv:2101.12249, 2021.

Summary

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

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

Follow-up Questions

We haven't generated follow-up questions for this paper yet.

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