Implicit Neural Representation For Accurate CFD Flow Field Prediction

TL;DR

This paper introduces a neural network framework that accurately predicts 3D flow fields around complex geometries like turbine blades, overcoming limitations of existing methods by being discretization-agnostic and geometry-aware.

Contribution

The authors propose a novel coordinate-based neural network system combining backbone-net and hyper-net for accurate, resolution-independent flow prediction directly from geometry.

Findings

Accurately models boundary layers, wakes, and shock waves in 3D flow simulations.

Predicts flow fields directly from blade geometry, generalizing to unseen shapes.

Achieves high accuracy and efficiency compared to traditional CFD methods.

Abstract

Despite the plethora of deep learning frameworks for flow field prediction, most of them deal with flow fields on regular domains, and although the best ones can cope with irregular domains, they mostly rely on graph networks, so that real industrial applications remain currently elusive. We present a deep learning framework for 3D flow field prediction applied to blades of aircraft engine turbines and compressors. Crucially, we view any 3D field as a function from coordinates that is modeled by a neural network we call the backbone-net. It inherits the property of coordinate-based MLPs, namely the discretization-agnostic representation of flow fields in domains of arbitrary topology at infinite resolution. First, we demonstrate the performance of the backbone-net solo in regressing 3D steady simulations of single blade rows in various flow regimes: it can accurately render important flow characteristics such as boundary layers, wakes and shock waves. Second, we introduce a hyper-net that maps the surface mesh of a blade to the parameters of the backbone-net. By doing so, the flow solution can be directly predicted from the blade geometry, irrespective of its parameterization. Together, backbone-net and hyper-net form a highly-accurate memory-efficient data-driven proxy to CFD solvers with good generalization on unseen geometries.