.png){kind=icon}
.png){kind=icon}
Return
Interpretable Machine Learning Models for Geometry - Property Correlation of Nested Lattice Structures Fabricated Through Additive Manufacturing Process
.png){kind=icon}
PRE
AI
V
C
C
D
P
DOI：10.1016/j.tws.2026.115079.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Modulus dependency of nested lattices on design parameters was established • Prediction of elastic modulus through machine learning models: MLP, GBR, and GPR • ML models were trained and tested using an experimentally validated FEA dataset • Gradient boosting showed highest accuracy, while GPR provided uncertainty estimates • SHAP analysis identified shell thickness and truss diameter as dominant parameters
Keywords:
nested lattices
elastic modulus
machine learning
additive manufacturing
parameter sensitivity
Journal
T
IF:
6.6
Papers:
1.1W
Citations:
4.0W
Organization
Cited Papers