Polymer glass transition temperature prediction method and device based on adaptive optimization algorithm and graph neural network, and medium

By combining an improved stochastic gradient optimization algorithm with a graph neural network, dynamically adjusting the learning rate and conducting phased training, the problems of low efficiency and insufficient accuracy in the existing technology for predicting the glass transition temperature of polymers are solved, and efficient and accurate polymer Tg prediction is achieved.

CN120636633APending Publication Date: 2025-09-12TONGJI UNIV
3 Cites 1 Cited by

Patent Information

Application Number
CN202510689376.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-05-27
Publication Date
2025-09-12

AI Technical Summary

Technical Problem

Existing technologies are inefficient, inaccurate, limited in applicability, and have poor model interpretability when predicting the glass transition temperature of polymers, making it difficult to meet the needs of high-throughput material research and development.

Method used

Combining the improved stochastic gradient optimization algorithm (RAdam) with multi-scale molecular feature modeling, by constructing a graph neural network model, dynamically adjusting the learning rate, performing phased training, and using a gradient accumulation strategy and validation set evaluation, the model performance is optimized.

Benefits of technology

It achieves efficient and accurate prediction of the glass transition temperature of polymers, improves the training efficiency and generalization ability of the model, adapts to different polymer systems, reduces computational complexity, and ensures the stability and reliability of training.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention relates to a polymer glass transition temperature prediction method and device based on an adaptive optimization algorithm and a graph neural network, and a medium. The prediction method comprises the following steps: converting polymer molecular structure data into graph structure data containing node features and edge features; acquiring training parameter configuration information; constructing a graph neural network model comprising a graph convolution layer, a graph pooling layer and a full connection layer based on the training parameter configuration information, and training by adopting an improved RAdam optimization algorithm; after multiple batches of gradients are accumulated through a gradient accumulation strategy, model parameter updating is executed, the model performance is dynamically evaluated based on the mean absolute error and the mean square error of the verification set, and optimal model parameters are stored; and predicting the Tg of the polymer by using the optimized model. Compared with the prior art, the polymer Tg prediction precision and the training efficiency are synchronously improved, and the low-flux bottleneck of traditional experimental measurement and the precision-scale contradiction of computational simulation are broken through.
Need to check novelty before this filing date? Find Prior Art