PulseExploreJournal ClubResearchersJournals
Instagram
HomeJournal ClubExplore
Synapse
⌘+K
Synapse
July 16, 2026Micro and Nano Systems LettersOpen Access

Machine learning-assisted design acceleration framework for energy absorbing re-entrant honeycomb auxetic structures

View Full Paper
Ask AI
Bookmark
Share

Authors

GCGeonho ChoiDLDonghyun LeeMKMinyoung Kim

Discussion

Loading...

Member takes

Overview

Randomized trial demonstrates enhanced energy absorption in auxetic structures, suggesting improved design efficiency.

Key Points

  • This study aims to accelerate the design of energy-absorbing auxetic structures using machine learning techniques.
  • Developed an end-to-end machine learning framework integrating PyAnsys Geometry and PyMechanical.
  • Conducted automated geometry generation and finite element analysis to build a dataset (n = 40).
  • Applied surrogate modeling and covariance matrix adaptation evolution strategy for optimization.
  • Achieved an optimal design increasing energy absorption density by 63.6% (EAD from 90.015 to 147.304 kJ/m³).
  • Surrogate model demonstrated best performance with R² = 0.729 through 5-fold cross-validation.
  • Under a strain limit of ε = 0.15, energy absorption increased by 83.96% (EAD from 37.96 to 69.83 kJ/m³).

Cite This Study

Choi et al. (2026) studied this question.

synapsesocial.com/papers/6a58752d2b46c88ba9ad0f5ahttps://doi.org/10.1186/s40486-026-00262-8
View Full Paper
Ask AI
Bookmark
Share