EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Fast Reverse Design of 4D‐Printed Voxelized Composite Structures Using Deep Learning and Evolutionary Algorithm

Mengtao Wang, Zaiyang Liu, Hidemitsu Furukawa, Zhuo Li, Yifei Ge, Yifan Xu, Zhe Qiu, Yang Tian, Zhongkui Wang iD, Ren Xu, Lin Meng iD

Advanced Science · 2025-03 · 12 (12)

DOI: 10.1002/advs.202407825 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advanced Science, online erschienen am 01.02.2025. Verfasst von Mengtao Wang und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electronic and Computer Engineering, Ritsumeikan University, Shiga, 525-8577, Japan. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: New Energy and Industrial Technology Development Organization.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Designing voxelized composite structures via 4D printing involves creating voxel units with distinct material properties that transform in response to stimuli; however, optimally distributing these properties to achieve specific target shapes remains a significant challenge. This study introduces an optimization method combining deep learning (DL) and an evolutionary algorithm, focusing on a solvent‐responsive hydrogel as the target material. A sequence‐enhanced parallel convolutional neural network is developed and generated a dataset through finite element simulations. This DL model enables high‐precision prediction of hydrogel deformation. Furthermore, a progressive evolutionary algorithm (PEA) is proposed by integrating the DL model to construct a DL‐PEA framework. This framework supports rapid reverse engineering of the desired shape, and the average design time for specified target shapes is reduced to ≈3.04 s. The present findings illustrate how 4D printing of optimized hydrogel designs can effectively transform in response to environmental stimuli. This work provides a new perspective on the application of hydrogels in 4D printing and presents an efficient tool for optimizing 4D‐printed voxelized composite structures.

Schlagwörter

Stichwörter der Autor:innen

4D printingdeep learningevolutionary algorithmhydrogelvoxel assembly

Autor:innen und Institutionen

  • Department of Electronic and Computer Engineering, Ritsumeikan University, Shiga, 525-8577, Japan.
  • Department of Robotics, Ritsumeikan University, Shiga, 525-8577, Japan.
  • Department of Mechanical Systems Engineering, Yamagata University, Yonezawa, 992-8510, Japan.
  • School of Medicine, Xiamen University, Xiamen, Fujian, 361100, China.

ORCID-Profile: Zhongkui Wang, Lin Meng

Förderung

  • New Energy and Industrial Technology Development Organization

Zitieren

APA

Wang, M., Liu, Z., Furukawa, H., Li, Z., Ge, Y., Xu, Y., Qiu, Z., Tian, Y., Wang, Z., Xu, R., & Meng, L. (2025). Fast Reverse Design of 4D‐Printed Voxelized Composite Structures Using Deep Learning and Evolutionary Algorithm. Advanced Science, 12(12). https://doi.org/10.1002/advs.202407825

Vancouver

Wang M, Liu Z, Furukawa H, Li Z, Ge Y, Xu Y, et al. Fast Reverse Design of 4D‐Printed Voxelized Composite Structures Using Deep Learning and Evolutionary Algorithm. Advanced Science. 2025;12(12). doi:10.1002/advs.202407825

BibTeX
@article{Wang2025,
  author = {Wang, Mengtao and Liu, Zaiyang and Furukawa, Hidemitsu and Li, Zhuo and Ge, Yifei and Xu, Yifan and Qiu, Zhe and Tian, Yang and Wang, Zhongkui and Xu, Ren and Meng, Lin},
  title = {Fast Reverse Design of 4D‐Printed Voxelized Composite Structures Using Deep Learning and Evolutionary Algorithm},
  journal = {Advanced Science},
  year = {2025},
  volume = {12},
  number = {12},
  doi = {10.1002/advs.202407825}
}
Kostenlos starten →