Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
117 tokens/sec
GPT-4o
8 tokens/sec
Gemini 2.5 Pro Pro
47 tokens/sec
o3 Pro
5 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Self-supervised feature distillation and design of experiments for efficient training of micromechanical deep learning surrogates (2405.10135v1)

Published 16 May 2024 in cs.CE and cond-mat.mtrl-sci

Abstract: Machine learning surrogate emulators are needed in engineering design and optimization tasks to rapidly emulate computationally expensive physics-based models. In micromechanics problems the local full-field response variables are desired at microstructural length scales. While there has been a great deal of work on establishing architectures for these tasks there has been relatively little work on establishing microstructural experimental design strategies. This work demonstrates that intelligent selection of microstructural volume elements for subsequent physics simulations enables the establishment of more accurate surrogate models. There exist two key challenges towards establishing a suitable framework: (1) microstructural feature quantification and (2) establishment of a criteria which encourages construction of a diverse training data set. Three feature extraction strategies are used as well as three design criteria. A novel contrastive feature extraction approach is established for automated self-supervised extraction of microstructural summary statistics. Results indicate that for the problem considered up to a 8\% improvement in surrogate performance may be achieved using the proposed design and training strategy. Trends indicate this approach may be even more beneficial when scaled towards larger problems. These results demonstrate that the selection of an efficient experimental design is an important consideration when establishing machine learning based surrogate models.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (53)
  1. The materials genome initiative, the interplay of experiment, theory and computation. Current Opinion in Solid State and Materials Science, 18(2):99–117, 2014.
  2. Random heterogeneous materials: microstructure and macroscopic properties. Appl. Mech. Rev., 55(4):B62–B63, 2002.
  3. Digital polycrystalline microstructure generation using diffusion probabilistic models. Materialia, 33:101976, 2024.
  4. Statistically conditioned polycrystal generation using denoising diffusion models. Acta Materialia, page 119746, 2024.
  5. Local–global decompositions for conditional microstructure generation. Acta Materialia, 253:118966, 2023.
  6. Microstructure reconstruction using diffusion-based generative models. Mechanics of Advanced Materials and Structures, pages 1–19, 2023.
  7. Mattergen: a generative model for inorganic materials design. arXiv preprint arXiv:2312.03687, 2023.
  8. Scalable diffusion for materials generation. arXiv preprint arXiv:2311.09235, 2023.
  9. Designs for computer experiments. Technometrics, 31(1):41–47, 1989.
  10. Bayesian calibration of computer models. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 63(3):425–464, 2001.
  11. Robert B Gramacy. Surrogates: Gaussian process modeling, design, and optimization for the applied sciences. Chapman and Hall/CRC, 2020.
  12. An efficient surrogate model for emulation and physics extraction of large eddy simulations. Journal of the American Statistical Association, 113(524):1443–1456, 2018.
  13. Function-on-function kriging, with applications to three-dimensional printing of aortic tissues. Technometrics, 63(3):384–395, 2021.
  14. Deep gaussian processes. In Artificial intelligence and statistics, pages 207–215. PMLR, 2013.
  15. Variational auto-encoded deep gaussian processes. arXiv preprint arXiv:1511.06455, 2015.
  16. Solving stochastic inverse problems for property–structure linkages using data-consistent inversion and machine learning. JOM, 73(1):72–89, 2021.
  17. A deep learning approach to estimate stress distribution: a fast and accurate surrogate of finite-element analysis. Journal of The Royal Society Interface, 15(138):20170844, 2018.
  18. 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.
  19. Convolutional neural networks for the localization of plastic velocity gradient tensor in polycrystalline microstructures. Journal of Engineering Materials and Technology, 144(1):011004, 2022a.
  20. Calibrated localization relationships for elastic response of polycrystalline aggregates. Acta Materialia, 81:151–160, 2014.
  21. An artificial neural network for surrogate modeling of stress fields in viscoplastic polycrystalline materials. npj Computational Materials, 9(1):37, 2023.
  22. Stressnet-deep learning to predict stress with fracture propagation in brittle materials. Npj Materials Degradation, 5(1):6, 2021.
  23. Physics-informed data-driven surrogate modeling for full-field 3d microstructure and micromechanical field evolution of polycrystalline materials. JOM, 73(11):3371–3382, 2021.
  24. Machine learning based surrogate modeling approach for mapping crystal deformation in three dimensions. Scripta Materialia, 193:1–5, 2021.
  25. Experiments: planning, analysis, and optimization. John Wiley & Sons, 2011.
  26. V Roshan Joseph. Space-filling designs for computer experiments: A review. Quality Engineering, 28(1):28–35, 2016.
  27. A framework for data-driven analysis of materials under uncertainty: Countering the curse of dimensionality. Computer Methods in Applied Mechanics and Engineering, 320:633–667, 2017.
  28. Reduced-order structure-property linkages for polycrystalline microstructures based on 2-point statistics. Acta Materialia, 129:428–438, 2017.
  29. Material-response-informed deeponet and its application to polycrystal stress-strain prediction in crystal plasticity. arXiv preprint arXiv:2401.09977, 2024.
  30. Training data selection for accuracy and transferability of interatomic potentials. npj Computational Materials, 8(1):189, 2022b.
  31. Molecular geometry impact on deep learning predictions of inverted singlet–triplet gaps. The Journal of Physical Chemistry A, 2024.
  32. Active learning for convolutional neural networks: A core-set approach. arXiv preprint arXiv:1708.00489, 2017.
  33. Maximum projection designs for computer experiments. Biometrika, 102(2):371–380, 2015.
  34. Data twinning. Statistical Analysis and Data Mining: The ASA Data Science Journal, 15(5):598–610, 2022.
  35. Prisms-plasticity: An open-source crystal plasticity finite element software. Computational Materials Science, 169:109078, 2019.
  36. Creep anisotropy modeling and uncertainty quantification of an additively manufactured ni-based superalloy. International Journal of Plasticity, 151:103177, 2022.
  37. The neper/fepx project: free/open-source polycrystal generation, deformation simulation, and post-processing. In IOP Conference Series: Materials Science and Engineering, volume 1249, page 012021. IOP Publishing, 2022.
  38. H-J Bunge. Texture analysis in materials science: mathematical methods. Elsevier, 2013.
  39. Deep learning. MIT press, 2016.
  40. beta-vae: Learning basic visual concepts with a constrained variational framework. ICLR (Poster), 3, 2017.
  41. Toward learning latent-variable representations of microstructures by optimizing in spatial statistics space. arXiv preprint arXiv:2402.11103, 2024.
  42. Texture analysis in magnetic resonance imaging: review and considerations for future applications. Assessment of cellular and organ function and dysfunction using direct and derived MRI methodologies, pages 75–106, 2016.
  43. Statistical convolutional neural network for land-cover classification from sar images. IEEE Geoscience and Remote Sensing Letters, 17(9):1548–1552, 2019.
  44. Correlation clustering of organoid images. arXiv preprint arXiv:2403.13376, 2024.
  45. Learning a similarity metric discriminatively, with application to face verification. In 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR’05), volume 1, pages 539–546. IEEE, 2005.
  46. Neighbourhood components analysis. Advances in neural information processing systems, 17, 2004.
  47. Signature verification using a” siamese” time delay neural network. Advances in neural information processing systems, 6, 1993.
  48. Contrastive and non-contrastive self-supervised learning recover global and local spectral embedding methods. Advances in Neural Information Processing Systems, 35:26671–26685, 2022.
  49. Dimensionality reduction by learning an invariant mapping. In 2006 IEEE computer society conference on computer vision and pattern recognition (CVPR’06), volume 2, pages 1735–1742. IEEE, 2006.
  50. Minimax and maximin distance designs. Journal of statistical planning and inference, 26(2):131–148, 1990.
  51. Support points. 2018.
  52. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016.
  53. Tensorflow: A system for large-scale machine learning. In 12th {{\{{USENIX}}\}} symposium on operating systems design and implementation ({{\{{OSDI}}\}} 16), pages 265–283, 2016.

Summary

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

X Twitter Logo Streamline Icon: https://streamlinehq.com