Designing Non-periodic 3D Woven Composite Preforms Using LSTM Deep Learning Networks

Page view(s)
10
Checked on Feb 08, 2025
Designing Non-periodic 3D Woven Composite Preforms Using LSTM Deep Learning Networks
Title:
Designing Non-periodic 3D Woven Composite Preforms Using LSTM Deep Learning Networks
Journal Title:
Mechanisms and Machine Science
Publication Date:
22 August 2024
Citation:
Kuehsamy, S. J., Zhou, H., Wang, Z.-P., & Rosen, D. W. (2024). Designing Non-periodic 3D Woven Composite Preforms Using LSTM Deep Learning Networks. In Computational and Experimental Simulations in Engineering (pp. 540–550). Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-68775-4_42
Abstract:
Advanced 3D woven composites show significant promise for use in high-performance applications. Nonetheless, automating the design process for customized non-periodic woven architectures presents challenges due to the complexities arising from large-scale combinatorial design issues. This often leads to inefficient utilization of the tow reinforcement. In this work, by treating the woven design problem as a multi-agent system, we leverage an integrated framework combining the Hungarian Algorithm and Long Short-Term Memory (LSTM) networks. This allows for effective alignment of woven tows along loading paths, while enabling considerations of through-thickness reinforcement.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the Agency for Science, Technology and Research (A*STAR) - Career Development Fund
Grant Reference no. : C210112026

This research / project is supported by the Agency for Science, Technology and Research (A*STAR) - Start-up Fund
Grant Reference no. :
Description:
ISSN:
9783031687754
ISBN:
9783031687747
Files uploaded:

File Size Format Action
12451-designing-non-periodic-3d-woven-composite-preforms-using-lstm-deep-learning-networks-finalr2.pdf 764.36 KB PDF Request a copy