mlsanityData to 7 Oct 2026

Stress field prediction in fiber-reinforced composite materials using a deep learning approach

arXiv 2111.05271 ↗First posted 1 Nov 2021cond-mat.mtrl-sci cs.LGcited by 22

Not on the map. Why?

Abstract (arXiv)

Computational stress analysis is an important step in the design of material systems. Finite element method (FEM) is a standard approach of performing stress analysis of complex material systems. A way to accelerate stress analysis is to replace FEM with a data-driven machine learning based stress analysis approach. In this study, we consider a fiber-reinforced matrix composite material system and we use deep learning tools to find an alternative to the FEM approach for stress field prediction. We first try to predict stress field maps for composite material systems of fixed number of fibers with varying spatial configurations. Specifically, we try to find a mapping between the spatial arrangement of the fibers in the composite material and the corresponding von Mises stress field. This is achieved by using a convolutional neural network (CNN), specifically a U-Net architecture, using true stress maps of systems with same number of fibers as training data. U-Net is a encoder-decoder network which in this study takes in the composite material image as an input and outputs the stress field image which is of the same size as the input image. We perform a robustness analysis by taking different initializations of the training samples to find the sensitivity of the prediction accuracy to the small number of training samples. When the number of fibers in the composite material system is increased for the same volume fraction, a finer finite element mesh discretization is required to represent the geometry accurately. This leads to an increase in the computational cost. Thus, the secondary goal here is to predict the stress field for systems with larger number of fibers with varying spatial configurations using information from the true stress maps of relatively cheaper systems of smaller fiber number.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 7 of its 26 references that are in the map. First posted on arXiv 1 Nov 2021.

Builds on

7 of 26 references.

References · 7

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2018Stress Field Prediction in Cantilevered Structures Using Convolutional Neural Networkscited by 25
  3. 2018A Transfer Learning Approach for Microstructure Reconstruction and Structure-property Predictionscited by 21
  4. 2020Three-dimensional convolutional neural network (3D-CNN) for heterogeneous material homogenizationcited by 20
  5. 2021An efficient optimization based microstructure reconstruction approach with multiple loss functionscited by 6
  6. 2020Predicting Mechanical Properties from Microstructure Images in Fiber-reinforced Polymers using Convolutional Neural Networkscited by 5
  7. 2020Probabilistic modeling of discrete structural response with application to composite plate penetration modelscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 3; 2023: 3; 2024: 4; 2025: 7; 2026: 4.

22 papers.

Sort:

By area:

  1. 2022A mixed formulation for physics-informed neural networks as a potential solver for engineering problems in heterogeneous domains: comparison with finite element methodcited by 33
  2. 2024A finite element-based physics-informed operator learning framework for spatiotemporal partial differential equations on arbitrary domainscited by 15
  3. 2025Solving engineering eigenvalue problems with neural networks using the Rayleigh quotientcited by 8
  4. 2023Challenges and opportunities for machine learning in multiscale computational modelingcited by 6
  5. 2024Bayesian neural networks for predicting uncertainty in full-field material responsecited by 5
  6. 2024Micrometer: Micromechanics Transformer for Predicting Mechanical Responses of Heterogeneous Materialscited by 5
  7. 2024A spatiotemporal deep learning framework for prediction of crack dynamics in heterogeneous solids: efficient mapping of concrete microstructures to its fracture propertiescited by 3
  8. 2021Reinforcement Learning based Sequential Batch-sampling for Bayesian Optimal Experimental Designcited by 1
  9. 2022Linking Properties to Microstructure in Liquid Metal Embedded Elastomers via Machine Learningcited by 1
  10. 2022Image-based Artificial Intelligence empowered surrogate model and shape morpher for real-time blank shape optimisation in the hot stamping processcited by 1
  11. 2025Predicting Stress and Damage in Carbon Fiber-Reinforced Composites Deformation Process using Composite U-Net Surrogate Modelcited by 1
  12. 2025Physics-informed solution reconstruction in elasticity and heat transfer using the explicit constraint force methodcited by 1
10 more
  1. 2026A Hybrid Conditional Diffusion-DeepONet Framework for High-Fidelity Stress Prediction in Hyperelastic Materialscited by 1
  2. 2023Application of probabilistic modeling and automated machine learning framework for high-dimensional stress fieldcited by 0
  3. 2023Crack-Net: Prediction of Crack Propagation in Compositescited by 0
  4. 2025Predicting Stress in Two-phase Random Materials and Super-Resolution Method for Stress Images by Embedding Physical Informationcited by 0
  5. 2025Global Stress Generation and Spatiotemporal Super-Resolution Physics-Informed Operator under Dynamic Loading for Two-Phase Random Materialscited by 0
  6. 2025A Machine Learning Approach to Generate Residual Stress Distributions using Sparse Characterization Data in Friction-Stir Processed Partscited by 0
  7. 2025Deep Micro Solvers for Rough-Wall Stokes Flow in a Heterogeneous Multiscale Methodcited by 0
  8. 2026One-Step Flow Matching for Generative Modeling of Path-Dependent Physical Fieldscited by 0
  9. 2026Appearance-Preserving Refinement of Generated 3D Assets for Monochromatic Fabricationcited by 0
  10. 2026Hybrid Unet-Transformer Model for Generating Stress and Strain Fields from Composite Geometricscited by 0