A Graph Neural Network based deep learning framework for predicting the thermomechanical behavior of thermoset shape memory polymers

Khan Raqib Mahmud, Lingxiao Wang, Jinyuan Chen, Sunzid Hassan · Elsevier BV · 2025

A graph neural network deep learning framework is proposed for predicting the thermomechanical behavior of thermoset shape-memory polymers.

Moderate AI ConfidenceStrong SourceUnknownReadiness Unknown

Plain English summary

The record describes a deep learning approach using a graph neural network to predict how thermoset shape-memory polymers behave under thermomechanical conditions. The provided information does not include an abstract, so details such as the specific inputs/outputs, training data, model architecture, or validation method are not available here. As a result, the scope is limited to the stated goal in the title: prediction of thermomechanical behavior for thermoset shape-memory polymers.

Why this matters

Not stated in the provided text (no abstract content). No evidence is provided about prototyping, deployment, or performance sufficient for commercialization.

Key findings

  • Graph neural network based deep learning framework for predicting thermomechanical behavior of thermoset shape memory polymers.

Limitations

No abstract is provided, so the record does not specify methods, results, validation, accuracy, or comparisons to prior work.

Publication

Publisher
Elsevier BV
Publication date
September 1, 2025
Research type
Paper
License
https://www.elsevier.com/tdm/userlicense/1.0/

Tags

More on Shape-Memory Polymers

See all →
Shape-Memory Polymerspaper· Aug 1, 2026

Modelling the thermo-mechanical responses and shape recovery performance of particle-reinforced shape memory polymer composites in cold and hot programming

A study focused on modeling thermo-mechanical behavior and shape recovery of particle-reinforced shape-memory polymer composites when programmed in cold versus hot conditions.

Wencheng Pan, Lili Wan +3 · Elsevier BVSimulation
Shape-Memory Polymerspaper· Jul 7, 2026

Mobility-Driven Design of PDMS-Modified Glassy Polymer Networks for Thermally Activated Shape Memory in Vat Photopolymerization

By tuning PDMS-MMA mobility segments and switching monomer chemistry in photocurable networks, the study achieves thermally activated shape-memory behavior suitable for vat photopolymerization 4D printing.

Yura Choi, Namchul Cho · MDPI AGLaboratory Research
Shape-Memory Polymerspaper· May 25, 2026

In Situ Scanning Electron Microscopy Investigation of Flexural and Interlaminar Failure Mechanisms in Carbon Nanotube‐Reinforced Shape Memory Polymer Composites

In situ SEM shows that CNT-reinforced shape memory polymer composites fail via distinct, architecture-dependent mechanisms, with buckypaper interleaves improving Mode II interlaminar fracture toughness.

Jose Roman, Mohamed H. Hamza +1 · WileyLaboratory Research
Shape-Memory Polymerspaper· Apr 27, 2026

Solvent‐Responsive Shape Memory Porous Semicrystalline Thermoplastic Polyurethane

Porous semicrystalline TPU made by salt-leaching can recover shape in ethyl acetate, with solvent-driven changes in amorphous mobility and partial crystalline dissolution improving recovery while preserving mechanical properties.

Jizhong Huang, Meiqing Wang +3 · WileyLaboratory Research
Shape-Memory Polymerspaper· Mar 6, 2026

Shape Memory Polymers: An Overview

This review systematically surveys shape-memory polymer composites and their thermally, solvent, light, electrically, and magnetically induced response mechanisms, highlighting key design strategies and remaining challenges.

Wen Xin, Zihan Yang +2 · WileyUnknown
Shape-Memory Polymerspaper· Feb 10, 2026

Fluorescent Shape Memory Polymer with Dynamic Aggregation-Induced Emission Cross-Linking: Visualization and Prediction of Shape Memory Performance

A fluorescent shape-memory polymer is designed with dynamic aggregation-induced emission cross-linking to enable visualization and prediction of its shape-memory performance.

Yangfei Wu, Haotian Ma +7 · American Chemical Society (ACS)Unknown
Method note: Summaries and ratings on this page are generated by AI from the abstract only. Read the original paper for full context. · Model: gpt-5.4-nano-2026-03-17