用深度算子网络预测复杂形状的时变流场，速度快千倍且精度高。
Predicting Time-Dependent Flow Over Complex Geometries Using Operator Networks
- 通过符号距离场和卷积网络融合几何与历史信息，实现时变流场预测。
- 在未见几何上误差约5%，比传统计算流体力学快1000倍。
- 适合需要快速模拟复杂流动的工程设计与实时控制场景。
快速、泛化能力强的非定常流场代理模型仍具挑战。本文提出一种时变、几何感知的深度算子网络，可预测参数化与非参数化形状周围中等雷诺数流动的瞬时速度场。模型通过符号距离场（SDF）编码几何结构，利用卷积神经网络分支捕捉流场历史，基于841组高保真仿真数据训练。在未见几何上，单步相对L2误差约为5%，相比传统计算流体力学（CFD）提速高达1000倍。我们提供以物理为中心的滚动诊断工具，包括探点相位误差和散度范数，用于评估长时程预测精度。结果显示近场瞬态预测准确，但细小尾迹区域存在误差累积，尤其在尖角几何上更为显著。我们分析了模型失效模式并提出实用缓解策略。代码、数据划分与脚本已开源：https://github.com/baskargroup/TimeDependent-DeepONet，支持可复现性与基准测试。
原文摘要 · Abstract (English)
Fast, geometry-generalizing surrogates for unsteady flow remain challenging. We present a time-dependent, geometry-aware Deep Operator Network that predicts velocity fields for moderate-Re flows around parametric and non-parametric shapes. The model encodes geometry via a signed distance field (SDF) trunk and flow history via a CNN branch, trained on 841 high-fidelity simulations. On held-out shapes, it attains $\sim 5\%$ relative L2 single-step error and up to 1000X speedups over CFD. We provide physics-centric rollout diagnostics, including phase error at probes and divergence norms, to quantify long-horizon fidelity. These reveal accurate near-term transients but error accumulation in fine-scale wakes, most pronounced for sharp-cornered geometries. We analyze failure modes and outline practical mitigations. Code, splits, and scripts are openly released at: https://github.com/baskargroup/TimeDependent-DeepONet to support reproducibility and benchmarking.
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。