Chen WQ, Wang Q, Hesthaven JS, Zhang CH, 2021, Physics-informed machine learning for reduced-order modeling of nonlinear problems, Journal of Computational Physics, 446(11): 110666. https://doi.org/10.1016/j.jcp.2021.110666
As of March/April 2024 , this highly cited paper received enough citations to place it in the top 1% of the academic field of Physics based on a highly cited threshold for the field and publication year.
背景:高保真数值模拟已经成为流体力学领域的重要研究手段,但是对于诸如设计、控制、优化和不确定分析等需要针对大量参数进行重复模拟的问题,高保真数值模拟所需的计算开销十分巨大。
贡献:在深入研究高保真模拟降阶模化理论的前提下,基于正交分解方法和伽辽金投影方法生成降阶空间、降阶方程和降阶数据,结合物理监督机器学习理论,建立了具有离线开销小、在线响应快和鲁棒性好的机器学习降阶模化框架,在一系列定常和非定常经典流动问题中取得了验证。研究成果对于扩展高保真方法的应用范围,开发针对重复模拟类问题的先进模拟方法具有重要学术价值。

