用物理结构约束神经网络，精准预测漂浮物水动力特性。
Floating-Body Hydrodynamic Neural Networks
- 基于流体力学方程设计可解释的神经网络架构
- 在合成涡流数据上误差比神经微分方程低一个数量级
- 适合需要可解释性与稳定预测的工程仿真场景
流固耦合在工程与自然系统中普遍存在，漂浮体运动受附加质量、阻力及背景流影响。传统黑箱神经模型虽能回归状态导数，但可解释性差且长期预测不稳定。本文提出浮体水动力神经网络（FHNN），通过物理结构化框架预测方向性附加质量、阻力系数及基于流函数的流场，并与解析运动方程耦合。该设计限制假设空间，提升可解释性并稳定积分过程。在合成涡流数据集上，FHNN误差较神经微分方程降低一个数量级，恢复了物理一致的流场。相比哈密顿与拉格朗日神经网络，FHNN更有效处理耗散动力学，同时保持可解释性，弥合了黑箱学习与透明系统辨识之间的差距。
原文摘要 · Abstract (English)
Fluid-structure interaction is common in engineering and natural systems, where floating-body motion is governed by added mass, drag, and background flows. Modeling these dissipative dynamics is difficult: black-box neural models regress state derivatives with limited interpretability and unstable long-horizon predictions. We propose Floating-Body Hydrodynamic Neural Networks (FHNN), a physics-structured framework that predicts interpretable hydrodynamic parameters such as directional added masses, drag coefficients, and a streamfunction-based flow, and couples them with analytic equations of motion. This design constrains the hypothesis space, enhances interpretability, and stabilizes integration. On synthetic vortex datasets, FHNN achieves up to an order-of-magnitude lower error than Neural ODEs, recovers physically consistent flow fields. Compared with Hamiltonian and Lagrangian neural networks, FHNN more effectively handles dissipative dynamics while preserving interpretability, which bridges the gap between black-box learning and transparent system identification.
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。