用自适应重训让深度学习预测流体更准更省时
An Adaptive Framework for Autoregressive Forecasting in CFD Using Hybrid Modal Decomposition and Deep Learning
- 先用训练好的模型预测流场，再根据稳定性差时新生成的数据动态更新模型
- 在层流到湍流三种场景下，计算成本降低30%至95%，且保持物理一致性
- 全数据驱动，适合各类随时间变化的仿真问题，代码开源可复用
本文提出一种全新的通用、完全数据驱动的自适应框架，旨在稳定深度学习（DL）自回归预测模型在长时间尺度下的表现，以降低计算流体动力学（CFD）模拟的计算开销。该方法交替执行两个阶段：(i) 使用训练好的DL模型预测选定时间区间内的流场演化；(ii) 当预测稳定性下降时，利用新生成的CFD数据对模型进行自适应重训，从而避免自回归模型中常见的误差累积。该框架在从层流到湍流的三种日益复杂的流动场景中进行了验证，实现了30%至95%的计算成本降低，同时保持了物理一致性和预测精度。其完全数据驱动的特性使其可广泛应用于多种时变仿真问题。相关代码已作为开源实现，并将集成至ModelFLOWs-app的下一版本。
原文摘要 · Abstract (English)
This work presents, to the best of the authors' knowledge, the first generalizable and fully data-driven adaptive framework designed to stabilize deep learning (DL) autoregressive forecasting models over long time horizons, with the goal of reducing the computational cost required in computational fluid dynamics (CFD) simulations.The proposed methodology alternates between two phases: (i) predicting the evolution of the flow field over a selected time interval using a trained DL model, and (ii) updating the model with newly generated CFD data when stability degrades, thus maintaining accurate long-term forecasting. This adaptive retraining strategy ensures robustness while avoiding the accumulation of predictive errors typical in autoregressive models. The framework is validated across three increasingly complex flow regimes, from laminar to turbulent, demonstrating from 30 \% to 95 \% reduction in computational cost without compromising physical consistency or accuracy. Its entirely data-driven nature makes it easily adaptable to a wide range of time-dependent simulation problems. The code implementing this methodology is available as open-source and it will be integrated into the upcoming release of the ModelFLOWs-app.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。