Machine learning-driven multi-objective optimisation of shape-memory programming parameters in 4D-printed PLA

doi:10.1016/j.matdes.2026.117160

Machine learning-driven multi-objective optimisation of shape-memory programming parameters in 4D-printed PLA

2026-09-29

0

OA

AI

DOI：10.1016/j.matdes.2026.117160

Original

Original request for help

Save

Abstract

En 中文

• A validated surrogate framework enables systematic selection of shape-memory programming conditions. • Recovery temperature dominates recovery speed and final shape recovery. • Surrogate models capture nonlinear responses despite replicate-level variability. • Selected knee predicts 3.14 s recovery time, 99.72% shape fixity and 91.70% shape recovery.

Keywords:

Additive manufacturing

4D printing

Shape-memory polymer

Multi-objective optimisation

Design of experiments

Machine learning surrogate model

Machine learning-driven multi-objective optimisation of shape-memory programming parameters in 4D-printed PLA

Abstract

Journal

Organization

Cited Papers