In this work convolutional-fully connected neural networks were designed and trained to predict the glass transition temperature of polymers based only on their chemical structure. This approach has shown to successfully predict the T_g of unknown polymers with average relative errors as low as 6%. Several networks with different architecture or hiperparameters were successfully trained using a previously studied glass transition temperatures dataset for validation, and then the same method was employed for an extended dataset, with larger T_g dispersion and polymer's structure variability. This approach has shown to be accurate and reliable, and does not require any time consuming or expensive measurements and calculations as inputs. Furthermore, it is expected that this method can be easily extended to predict other properties. The possibility of predicting the properties of polymers not even synthesized will save time and resources for industrial development as well as accelerate the scientific understanding of structure-properties relationships in polymer science.

在这项工作中，设计并训练了卷积完全连接的神经网络，以仅基于其化学结构来预测聚合物的玻璃化转变温度。该方法已显示成功预测了未知聚合物的T _g，平均相对误差低至6％。使用先前研究的玻璃化转变温度数据集成功地训练了具有不同架构或hierparameters的几个网络，然后对扩展的数据集使用相同的方法，具有更大的T _g分散度和聚合物的结构变异性。这种方法已经证明是准确和可靠的，不需要任何耗时或昂贵的测量和计算作为输入。此外，期望该方法可以容易地扩展以预测其他性质。预测甚至不合成的聚合物的性能的可能性将节省工业开发的时间和资源，并加快对聚合物科学中结构-性能关系的科学理解。