ViscNet：预测脆性指数和粘度温度依赖性的神经网络
ViscNet: Neural network for predicting the fragility index and the temperature-dependency of viscosity
摘要：
粘度（$η$）是无序物质最重要的性质之一。粘度的温度依赖性用于调整玻璃制造的工艺变量，从熔化到退火。这项工作的目的是开发一个物理信息的机器学习模型，能够预测氧化物液体的$η(T)$。NN预测MYEGA粘度方程的参数，而不是预测粘度本身：液体的脆性指数，玻璃化转变温度和渐近粘度。利用这些参数，可以在任何感兴趣的温度下计算$η$，具有MYEGA方程固有的良好外推能力的优点。该数据集是从SciGlass数据库中收集的;仅选择在高粘度和低粘度区域具有足够数据点的氧化物液体，导致最终数据集具有17，584个数据点，包含847种不同的液体。大约600个特征是从液体的化学成分中设计出来的，其中35个特征是使用特征选择协议选择的。超参数（HP）调整的NN进行了一组实验，使用随机搜索和贝叶斯策略，其中共700 HP集进行了测试。使用10倍交叉验证进一步测试最成功的HP集，并且选择具有最低平均验证损失的HP集作为最佳集。最终训练的NN用85种液体的测试数据集进行测试，这些液体具有与用于训练和验证NN的液体不同的组成。测试数据集预测的$R^2$为0.97。这项工作介绍了三个优点：该模型可以预测粘度以及液体的玻璃化转变温度和脆性指数;该模型的设计和训练重点是外推;最后，该模型是根据GPL 3许可的免费开源软件。
英文摘要：
Viscosity ($η$) is one of the most important properties of disordered matter. The temperature-dependence of viscosity is used to adjust process variables for glass-making, from melting to annealing. The aim of this work was to develop a physics-informed machine learning model capable of predicting $η(T)$ of oxide liquids. Instead of predicting the viscosity itself, the NN predicts the parameters of the MYEGA viscosity equation: the liquid's fragility index, the glass transition temperature, and the asymptotic viscosity. With these parameters, $η$ can be computed at any temperature of interest, with the advantage of good extrapolation capabilities inherent to the MYEGA equation. The dataset was collected from the SciGlass database; only oxide liquids with enough data points in the high and low viscosity regions were selected, resulting in a final dataset with 17,584 data points containing 847 different liquids. About 600 features were engineered from the liquids' chemical composition and 35 of these features were selected using a feature selection protocol. The hyperparameter (HP) tuning of the NN was performed in a set of experiments using both random search and Bayesian strategies, where a total of 700 HP sets were tested. The most successful HP sets were further tested using 10-fold cross-validation, and the one with the lowest average validation loss was selected as the best set. The final trained NN was tested with a test dataset of 85 liquids with different compositions than those used for training and validating the NN. The $R^2$ for the test dataset's prediction was 0.97. This work introduces three advantages: the model can predict viscosity as well as the liquids' glass transition temperature and fragility index; the model is designed and trained with a focus on extrapolation; finally, the model is available as free and open-source software licensed under the GPL3.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
