Papers
Topics
Authors
Recent
Search
2000 character limit reached

Physics-Constrained Neural Network for Design and Feature-Based Optimization of Weave Architectures

Published 19 Sep 2022 in physics.app-ph and cs.LG | (2209.09154v2)

Abstract: Woven fabrics play an essential role in everyday textiles for clothing/sportswear, water filtration, and retaining walls, to reinforcements in stiff composites for lightweight structures like aerospace, sporting, automotive, and marine industries. Several possible combinations of weave patterns and material choices, which comprise weave architecture, present a challenging question about how they could influence the physical and mechanical properties of woven fabrics and reinforced structures. In this paper, we present a novel Physics-Constrained Neural Network (PCNN) to predict the mechanical properties like the modulus of weave architectures and the inverse problem of predicting pattern/material sequence for a design/target modulus value. The inverse problem is particularly challenging as it usually requires many iterations to find the appropriate architecture using traditional optimization approaches. We show that the proposed PCNN can effectively predict weave architecture for the desired modulus with higher accuracy than several baseline models considered. We present a feature-based optimization strategy to improve the predictions using features in the Grey Level Co-occurrence Matrix (GLCM) space. We combine PCNN with this feature-based optimization to discover near-optimal weave architectures to facilitate the initial design of weave architecture. The proposed frameworks will primarily enable the woven composite analysis and optimization process, and be a starting point to introduce Knowledge-guided Neural Networks into the complex structural analysis.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (56)
  1. Review of applications for advanced three-dimensional fibre textile composites. Composites Part A: applied science and manufacturing, 30(12):1445–1461, 1999.
  2. Structural integrity of aerospace textile composites under fatigue loading. Materials Science and Engineering: B, 132(1-2):79–84, 2006.
  3. Introduction to braided composite material behavior. In Handbook of Advances in Braided Composite Materials, pages 207–237. Elsevier, 2017.
  4. Textile composite electrodes for flexible batteries and supercapacitors: opportunities and challenges. Advanced Energy Materials, 11(3):2002838, 2021.
  5. AC Long. Design and manufacture of textile composites. Elsevier, 2005.
  6. NK Naik and VK Ganesh. Prediction of on-axes elastic properties of plain weave fabric composites. Composites Science and Technology, 45(2):135–152, 1992.
  7. Investigation of the three-dimensional micromechanical behavior of woven-fabric composites. Mechanics of Composite Materials, 42(2):141–150, 2006.
  8. Finite element analysis of mechanical properties of woven composites through a micromechanics model. Science and Engineering of Composite Materials, 24(1):87–99, 2017.
  9. T Ishikawa and TW Chou. One-dimensional micromechanical analysis of woven fabric composites. AIAA journal, 21(12):1714–1721, 1983.
  10. JD Whitcomb. Three-dimensional stress analysis of plain weave composites. Composite materials: Fatigue and fracture., 3:417–438, 1991.
  11. Macro finite element for analysis of textile composites. Journal of composite materials, 28(7):607–618, 1994.
  12. Boundary effects in woven composites. Journal of composite materials, 29(4):507–524, 1995.
  13. Y Gowayed. Types of fiber and fiber arrangement in fiber-reinforced polymer (frp) composites. In Developments in Fiber-Reinforced Polymer (FRP) Composites for Civil Engineering, pages 3–17. Elsevier, 2013.
  14. Experimental and numerical analyses on the thermal conductive behaviors of carbon fiber/epoxy plain woven composites. International Journal of Heat and Mass Transfer, 102:501–517, 2016.
  15. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, 25, 2012.
  16. Generative adversarial networks: An overview. IEEE Signal Processing Magazine, 35(1):53–65, 2018.
  17. Graph convolutional neural networks for web-scale recommender systems. In Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining, pages 974–983, 2018.
  18. Deep convolutional neural networks for multi-modality isointense infant brain image segmentation. NeuroImage, 108:214–224, 2015.
  19. Very deep convolutional networks for natural language processing. arXiv preprint arXiv:1606.01781, 2(1), 2016.
  20. Unsupervised anomaly detection with generative adversarial networks to guide marker discovery. In International conference on information processing in medical imaging, pages 146–157. Springer, 2017.
  21. Unsupervised pixel-level domain adaptation with generative adversarial networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 3722–3731, 2017.
  22. Semi supervised semantic segmentation using generative adversarial network. In Proceedings of the IEEE international conference on computer vision, pages 5688–5696, 2017.
  23. Energy-based generative adversarial network. arXiv preprint arXiv:1609.03126, 2016.
  24. Seqgan: Sequence generative adversarial nets with policy gradient. In Proceedings of the AAAI conference on artificial intelligence, volume 31, 2017.
  25. Predicting the effective thermal conductivities of composite materials and porous media by machine learning methods. International Journal of Heat and Mass Transfer, 127:908–916, 2018.
  26. CT Chen and GX Gu. Machine learning for composite materials. MRS Communications, 9(2):556–566, 2019.
  27. H Feng and P Prabhakar. Difference-based deep learning framework for stress predictions in heterogeneous media. Composite Structures, 269:113957, 2021.
  28. Defect identification in composite materials via thermography and deep learning techniques. Composite Structures, 246:112405, 2020.
  29. Initial failure strength prediction of woven composites using a new yarn failure criterion constructed by deep learning. Composite Structures, 230:111505, 2019.
  30. D Nardi and J Sinke. Design analysis for thermoforming of thermoplastic composites: Prediction and machine learning-based optimization. Composites Part C: Open Access, 5:100126, 2021.
  31. A data-driven approach to full-field damage and failure pattern prediction in microstructure-dependent composites using deep learning. arXiv preprint arXiv:2104.04485, 2021.
  32. Bioinspired hierarchical composite design using machine learning: simulation, additive manufacturing, and experiment. Materials Horizons, 5(5):939–945, 2018.
  33. Prediction and optimization of mechanical properties of composites using convolutional neural networks. Composite Structures, 227:111264, 2019.
  34. Deep learning framework for woven composite analysis. In Proceedings of the American Society for Composites—Thirty-Sixth Technical Conference on Composite Materials, 2021.
  35. CT Chen and GX Gu. Generative deep neural networks for inverse materials design using backpropagation and active learning. Advanced Science, 7(5):1902607, 2020.
  36. Physics-informed neural networks for high-speed flows. Computer Methods in Applied Mechanics and Engineering, 360:112789, 2020.
  37. SJ Pan and Q Yang. A survey on transfer learning. IEEE Transactions on knowledge and data engineering, 22(10):1345–1359, 2009.
  38. A survey of transfer learning. Journal of Big data, 3(1):1–40, 2016.
  39. Segnet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE transactions on pattern analysis and machine intelligence, 39(12):2481–2495, 2017.
  40. Gray level co-occurrence matrices: generalisation and some new features. arXiv preprint arXiv:1205.4831, 2012.
  41. N Zulpe and V Pawar. Glcm textural features for brain tumor classification. International Journal of Computer Science Issues (IJCSI), 9(3):354, 2012.
  42. D Singh and K Kaur. Classification of abnormalities in brain mri images using glcm, pca and svm. International Journal of Engineering and Advanced Technology (IJEAT), 1(6):243–248, 2012.
  43. M Hall-Beyer. Glcm texture: A tutorial v. 3.0 march 2017. 2017.
  44. Fabric defect detection based on glcm and gabor filter: A comparison. Optik, 124(23):6469–6474, 2013.
  45. Textural features for image classification. IEEE Transactions on systems, man, and cybernetics, (6):610–621, 1973.
  46. ABAQUS (2011) Dassualt Systèmes. Abaqus documentation. 2011.
  47. Modelling and simulating textile structures using TexGen. Advanced Materials Research, 331:44–47, 2011.
  48. CC Chamis. Mechanics of composite materials: Past, present, and future. Journal of Composites Technology and Research, 11(1):3–14, 1989.
  49. S Li and A Wongsto. Unit cells for micromechanical analyses of particle-reinforced composites. Mechanics of Materials, 36(7):543–572, 2004.
  50. T Ishikawa and T W Chou. Stiffness and strength behaviour of woven fabric composites. Journal of Materials Science, 17:3211–3220, 1982.
  51. Dislocation density–based model and stacked auto-encoder model for ti-55511 alloy with basket-weave microstructures deformed in α𝛼\alphaitalic_α+ β𝛽\betaitalic_β region. Advanced Engineering Materials, 23(4):2001307, 2021.
  52. Stressgan: A generative deep learning model for two-dimensional stress distribution prediction. Journal of Applied Mechanics, 88(5), 2021.
  53. D Whitley. A genetic algorithm tutorial. Statistics and computing, 4(2):65–85, 1994.
  54. RM Haralick and LG Shapiro. Computer and robot vision, volume 1. Addison-wesley Reading, 1992.
  55. M Bevk and I Kononenko. A statistical approach to texture description of medical images: a preliminary study. In Proceedings of 15th IEEE Symposium on Computer-Based Medical Systems (CBMS 2002), pages 239–244. IEEE, 2002.
  56. Initial fracture behavior of satin woven fabric composites. Composite structures, 61(4):333–339, 2003.
Citations (3)
View on Semantic Scholar

Summary

No one has generated a summary of this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Sign Up to Summarize

Paper to Video (Beta)

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

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

Continue Learning

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

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

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up