计算力学学报2026，Vol.43Issue(1)：139-144,6.DOI:10.7511/jslx20250117001
数据驱动的高分辨率CCWENO-ANN算法
Data-driven high-resolution CCWENO-ANN algorithm
摘要
Abstract
To accurately solve hyperbolic conservation laws and obtain high-resolution numerical results,this paper combined data-driven with the third-order CCWENO(Compact Central Weighted Essentially Non-Oscillatory)scheme,and proposed a data-driven CCWENO-ANN high-resolution scheme for hyperbolic conservation laws.By constructing the normalized calibration layer and sparse layer of an artificial neural network,the appropriate prior knowledge is introduced to accelerate the convergence speed.At the same time,the loss function dynamically adjusts the deviation between the outputs of the neural network and the ideal weights,and uses the supervised learning strategy to train the neural network offline on the appropriate data set to improve the performance of the neural network.By solving one-dimensional inviscid Burgers equation,one-dimensional Euler equation,two-dimensional inviscid Burgers equation and two-dimensional Euler equation,the performance of the algorithm is evaluated.The results show that the proposed CCWENO-ANN inherits the convergence of the traditional CCWENO scheme and can accurately capture shock waves and contact discontinuities,and has the advantages of robustness,low dissipation and high resolution.关键词
双曲守恒律/数据驱动/CCWENO重构/神经网络/机器学习Key words
hyperbolic conservation law/data-driven/CCWENO reconstruction/neural network/machine learning分类
数理科学引用本文复制引用
徐豆豆,郑素佩,高普阳,崔晓楚..数据驱动的高分辨率CCWENO-ANN算法[J].计算力学学报,2026,43(1):139-144,6.基金项目
陕西省自然科学基础研究计划(2024JC-ZDXM-23 （）
2025JC-YBMS-070)资助项目. （）
