Department of Mechanical & Industrial Engineering, Louisiana State University, Baton Rouge, Louisiana 70803, United States.
ACS Appl Mater Interfaces. 2021 Dec 22;13(50):60508-60521. doi: 10.1021/acsami.1c20947. Epub 2021 Dec 8.
Ultraviolet (UV)-curable thermoset shape memory polymers (TSMPs) with high recovery stress but mild glass transition temperature () are highly desired for 3D/4D printing lightweight load-bearing structures and devices. However, a bottleneck is that high recovery stress usually means high . For a few TSMPs with high recovery stress, their values are close to the decomposition temperature, and thus, the shape memory effect cannot be triggered safely and effectively. While machine learning (ML) has served as a useful tool to discover new materials and drugs, the grand challenge of using ML to discover new TSMPs persists in the very limited data available. Here, we report an enhanced ML approach by combining the transfer learning-variational autoencoder with a weighted-vector combination method. By learning a large data set with drug molecules in a pretraining process, we were able to effectively map the TSMPs to a hidden space that is much closer to a Gaussian distribution. Through this approach, we created a large compositional space and were able to discover five new types of UV-curable TSMPs with desired properties, one of which was validated by the experiments. Our contribution includes (1) representing the features of TSMPs by drug molecules to overcome the barrier of a limited training data set and (2) developing a ML framework that is able to overcome the barrier of mapping the molar ratio information. It is shown that this approach can effectively learn TSMP features by utilizing the relatedness between the data-scarce (and biased) TSMP target and data-abundant drug source, and the result is much more accurate and more robust than the benchmark set by the support vector machine method using direct label encoding and Morgan encoding. Therefore, it is believed that this framework is a state-of-the-art study in the TSMP field. This study opens new opportunities for discovering not only new TSMPs but also other thermoset polymers.
具有高回复应力但玻璃化转变温度（Tg）较低的紫外（UV）可固化热固性形状记忆聚合物（TSMP）是 3D/4D 打印轻质承重结构和器件的理想选择。然而，一个瓶颈是高回复应力通常意味着高。对于少数具有高回复应力的 TSMP，其Tg 值接近分解温度，因此无法安全有效地触发形状记忆效应。虽然机器学习（ML）已成为发现新材料和药物的有用工具，但在非常有限的数据可用的情况下，利用 ML 发现新的 TSMP 仍然是一个巨大的挑战。在这里，我们通过结合转移学习-变分自动编码器和加权向量组合方法，报告了一种增强的 ML 方法。通过在预训练过程中使用药物分子学习大数据集，我们能够有效地将 TSMP 映射到更接近高斯分布的隐藏空间。通过这种方法，我们创建了一个大的组成空间，并能够发现五种具有所需性能的新型 UV 可固化 TSMP，其中一种通过实验得到了验证。我们的贡献包括（1）通过药物分子来表示 TSMP 的特征，以克服训练数据集有限的障碍，（2）开发了一种 ML 框架，能够克服映射摩尔比信息的障碍。结果表明，这种方法可以通过利用数据稀缺（和有偏差）的 TSMP 目标与数据丰富的药物源之间的相关性来有效地学习 TSMP 特征，并且结果比使用直接标签编码和 Morgan 编码的支持向量机方法的基准集更准确和更稳健。因此，相信该框架是 TSMP 领域的一项前沿研究。这项研究为发现不仅新的 TSMP，而且还为发现其他热固性聚合物开辟了新的机会。
