文献类型：期刊文献

英文题名：Applications of physics-informed deep-learning in polymer rheology: Prediction and optimization for rheological molding process through integrated physical and data-driven learning

作者：Qi, Jihao[1];Yin, Wei[1];Pang, Zhiwei[1];Lin, Zeng[1];Wang, Chaoyuan[1];Zhu, Wujun[1];Chen, Xin[1];Sha, Jin[1];Bai, Zhishan[1]

机构：[1]East China Univ Sci & Technol, Shanghai 200237, Peoples R China

年份：2026

卷号：38

期号：5

外文期刊名：PHYSICS OF FLUIDS

收录：;EI(收录号：20262220805416);WOS:【SCI-EXPANDED(收录号:WOS:001778323700001)】；

基金：The work is supported by the National Science Fund for Distinguished Young Scholars, China (No. 22225804), the National Natural Science Foundation of China, China (No. 22408101), the Natural Science Foundation of Shanghai, China (No. 25ZR1401085), Shanghai Leading Talent Project (No. BJKJ2025035), and the Guizhou Provincial Science and Technology Support Program (Qiankehezhi [2025] General 091).

语种：英文

外文关键词：Behavioral research - Data accuracy - Data quality - Data reliability - Deep learning - Forecasting - Optimization - Problem solving

摘要：The review explores the application of Physics-Informed Deep Learning (PIDL) in polymer rheology, highlighting its potential to address limitations of traditional rheological models. By integrating physical prior knowledge with data-driven methods, PIDL enhances the accuracy and reliability of fluid behavior predictions, fostering a more refined, intelligent, and interdisciplinary development in rheological research. The article outlines the fundamental principles, common architectures, and evaluation methods of PIDL, and presents practical examples of its applications in polymer rheology, including constitutive relationship modeling, fluid behavior prediction, experimental data analysis, multiscale simulation and optimization, and process parameter optimization. Challenges faced by PIDL in polymer rheology, such as data quality, model generalization capabilities, and multiscale problem-solving, are also discussed, along with current solutions.