Zhang Songyang, He Xiaojie, Xia Xuejian, Xiao Peng, Wu Qi, Zheng Feng, Lu Qinghua
School of Chemical Science and Engineering, Tongji University, Shanghai 200092, China.
Shanghai Key Lab of Electrical & Thermal Aging, School of Chemistry and Chemical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China.
ACS Appl Mater Interfaces. 2023 Aug 9;15(31):37893-37902. doi: 10.1021/acsami.3c05376. Epub 2023 Jul 25.
Great and continuous efforts have been made to discover high-performance engineering plastics with specific properties to replace traditional engineering materials in many fields. The utilization of machine learning (ML) has brought more opportunities for the discovery of high-performing engineering plastics. However, hindered by either the relatively small database or a lack of accurate structure descriptors with clear physical and chemical meanings relating to polymer properties, the current ML studies show some flaws in the accuracy and efficiency in polymer development. Herein, we collected a dataset of 878 polyimides (PI), one of the best engineering plastics, with experimentally measured glass-transition temperature () values, and developed a rapid and accurate ML approach to design PI candidates with the desired value. After the conversion from PI structures into "mechanically identifiable" SMILES (Simplified molecular input line entry system) language, the eight most critical descriptors were ultimately obtained by multiple analysis methods. The physiochemical meaning of the key descriptors was further analyzed carefully to translate the implicit "machine language" to chemical knowledge. The artificial neural network (ANN)-based model gave the most accurate results with a root-mean-square error of ∼11 K among the studied ML methods. More importantly, three potential PI candidates with desired (DPIs) were designed according to the chemical insight of the key descriptors, which were then verified by experiments. The experimental and predicted values of DPIs have an acceptable average deviation of ca. 3.66%. This accuracy has reached the level of the traditional molecular simulation, but the time consumption and hold-up computing resource are tremendously reduced. Furthermore, the current ML approach could offer a scalable and adaptable framework in future engineer plastics innovation.
人们一直在付出巨大且持续的努力，以发现具有特定性能的高性能工程塑料，从而在许多领域取代传统工程材料。机器学习（ML）的应用为高性能工程塑料的发现带来了更多机遇。然而，由于数据库相对较小，或者缺乏与聚合物性能相关的具有明确物理和化学意义的准确结构描述符，当前的机器学习研究在聚合物开发的准确性和效率方面存在一些缺陷。在此，我们收集了一个包含878种聚酰亚胺（PI，最佳工程塑料之一）的数据集，并通过实验测量了其玻璃化转变温度（ ）值，同时开发了一种快速且准确的机器学习方法，用于设计具有所需 值的PI候选物。在将PI结构转换为“机器可识别”的SMILES（简化分子输入线性输入系统）语言后，通过多种分析方法最终获得了八个最关键的描述符。对关键描述符的物理化学意义进行了进一步仔细分析，以便将隐含的“机器语言”转化为化学知识。在所研究的机器学习方法中，基于人工神经网络（ANN）的模型给出了最准确的结果，均方根误差约为11 K。更重要的是，根据关键描述符的化学见解设计了三种具有所需 （DPI）的潜在PI候选物，然后通过实验进行了验证。DPI的实验值和预测值的平均偏差约为3.66%，这是可以接受的。这种准确性已达到传统分子模拟的水平，但时间消耗和计算资源占用大幅减少。此外，当前的机器学习方法可为未来工程塑料创新提供一个可扩展且适应性强的框架。
