Descriptive Modeling of Textiles using FE Simulations and Deep Learning

TL;DR

This paper introduces an automated method combining deep learning and finite element simulations to directly model textile yarn geometries from CT images, improving accuracy and robustness over previous voxel-based approaches.

Contribution

The novel integration of FE simulations with deep neural networks enables direct textile modeling and reduces manual annotation, advancing textile analysis techniques.

Findings

Accurate yarn segmentation in CT images achieved

Synthetic data generation via U-Net improves training efficiency

Method outperforms previous voxel-based approaches

Abstract

In this work we propose a novel and fully automated method for extracting the yarn geometrical features in woven composites so that a direct parametrization of the textile reinforcement is achieved (e.g., FE mesh). Thus, our aim is not only to perform yarn segmentation from tomographic images but rather to provide a complete descriptive modeling of the fabric. As such, this direct approach improves on previous methods that use voxel-wise masks as intermediate representations followed by re-meshing operations (yarn envelope estimation). The proposed approach employs two deep neural network architectures (U-Net and Mask RCNN). First, we train the U-Net to generate synthetic CT images from the corresponding FE simulations. This allows to generate large quantities of annotated data without requiring costly manual annotations. This data is then used to train the Mask R-CNN, which is focused on predicting contour points around each of the yarns in the image. Experimental results show that our method is accurate and robust for performing yarn instance segmentation on CT images, this is further validated by quantitative and qualitative analyses.