Back to Search
Start Over
A deep learning approach for predicting the architecture of 3D textile fabrics.
- Source :
-
Materials & Design . Mar2024, Vol. 239, pN.PAG-N.PAG. 1p. - Publication Year :
- 2024
-
Abstract
- [Display omitted] • The proposed system solves a high-dimensional problem by reconstructing a 3D domain in a series of timesteps. • Average stiffness properties of the predicted 3D unit cell were within 10% error margin. • Different neural network architectures were explored demonstrating the validity of the proposed approach. • The variety of possible neural networks makes the proposed approach available to setups with lesser computational resources. • The prediction speed was higher in comparison with conventional approaches allowing to explore various weaving architectures. In this paper, a deep learning approach to 3D textile geometry simulations is presented. Two different network architectures with convolutional and recurrent properties are explored. The deep neural networks were trained to generate a fully compacted 3D textile unit cell based on the weave initial architecture. The AI training was conducted on a set of precomputed weaving case studies generated by digital element based weaving simulation software. The proposed strategy demonstrated effectiveness in estimation of 3D textile architectures. The designed system was able to operate within 10% error for stiffness properties prediction. The main benefit of the proposed approach over conventional modelling is its computational efficiency. Rapid weaving simulations provide an opportunity to explore the effects of different yarn architectures, matrix materials, and manufacturing techniques on the mechanical properties of woven composites, leading to a better understanding of their behaviour and their potential for use in new applications. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 02641275
- Volume :
- 239
- Database :
- Academic Search Index
- Journal :
- Materials & Design
- Publication Type :
- Academic Journal
- Accession number :
- 176100721
- Full Text :
- https://doi.org/10.1016/j.matdes.2024.112803