当前位置: X-MOL 学术J. Mech. Phys. Solids › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
ViscoNet: A lightweight FEA surrogate model for polymer nanocomposites viscoelastic response prediction
Journal of the Mechanics and Physics of Solids ( IF 5.0 ) Pub Date : 2024-10-19 , DOI: 10.1016/j.jmps.2024.105915
Anqi Lin, Richard J․ Sheridan, Bingyin Hu, L. Catherine Brinson

Polymer-based nanocomposites (PNCs) are formed by dispersing nanoparticles (NPs) within a polymer matrix, which creates polymer interphase regions that drive property enhancement. However, data-driven PNC design is challenging due to limited data. To address the challenge, we present ViscoNet, a surrogate model for finite element analysis (FEA) simulations of PNC viscoelastic (VE) response. ViscoNet leverages pre-training and finetuning to accelerate predicting VE response of a new PNC system. By predicting the entire VE response, ViscoNet surpasses previous scalar-based surrogate models for FEA simulation, offering better fidelity and efficiency. We explore ViscoNet's effectiveness through generalization tasks, both within thermoplastics and from thermoplastics to thermosets, reporting a mean absolute percentage error (MAPE) of < 5 % for rubbery modulus and < 1 % for glassy modulus in all cases and 1.22 % on tan δ peak height prediction. With only 500 FEA simulations for finetuning, ViscoNet can generate over 20k VE responses within 2 min with 1 CPU, compared to 97 days with 4 CPUs via FEA simulations.

中文翻译:


ViscoNet:用于聚合物纳米复合材料粘弹性响应预测的轻量级 FEA 代理模型



聚合物基纳米复合材料 (PNC) 是通过在聚合物基质中分散纳米颗粒 (NP) 而形成的,从而形成推动性能增强的聚合物界面区域。然而,由于数据有限,数据驱动的 PNC 设计具有挑战性。为了应对这一挑战,我们提出了 ViscoNet,这是一种用于 PNC 粘弹性 (VE) 响应有限元分析 (FEA) 仿真的代理模型。ViscoNet 利用预训练和微调来加速预测新 PNC 系统的 VE 响应。通过预测整个 VE 响应,ViscoNet 超越了以前用于 FEA 仿真的基于标量的代理模型,从而提供了更好的保真度和效率。我们通过热塑性塑料以及从热塑性塑料到热固性塑料的泛化任务来探索 ViscoNet 的有效性,报告在所有情况下,橡胶模量的平均绝对百分比误差 (MAPE) 为 < 5%,玻璃模量为 < 1%,tan δ峰值预测为 1.22%。只需 500 次 FEA 模拟进行微调,ViscoNet 就可以在 2 分钟内使用 1 个 CPU 生成超过 20k 的 VE 响应,而通过 FEA 模拟使用 4 个 CPU 需要 97 天。
更新日期:2024-10-19
down
wechat
bug