# Fast Neural Network Predictions from Constrained Aerodynamics Datasets

## TL;DR

This paper introduces a fast, neural network-based method for predicting aerodynamics that is nearly as accurate as traditional models but significantly faster and easier to implement, using a novel cluster network architecture.

## Contribution

The paper presents a new model-free neural network approach with a specialized architecture for rapid and accurate aerodynamics predictions from constrained datasets.

## Key findings

- Nearly as accurate as state-of-the-art model-based methods
- An order of magnitude faster in predictions
- Outperforms existing model-free approaches

## Abstract

Incorporating computational fluid dynamics in the design process of jets, spacecraft, or gas turbine engines is often challenged by the required computational resources and simulation time, which depend on the chosen physics-based computational models and grid resolutions. An ongoing problem in the field is how to simulate these systems faster but with sufficient accuracy. While many approaches involve simplified models of the underlying physics, others are model-free and make predictions based only on existing simulation data. We present a novel model-free approach in which we reformulate the simulation problem to effectively increase the size of constrained pre-computed datasets and introduce a novel neural network architecture (called a cluster network) with an inductive bias well-suited to highly nonlinear computational fluid dynamics solutions. Compared to the state-of-the-art in model-based approximations, we show that our approach is nearly as accurate, an order of magnitude faster, and easier to apply. Furthermore, we show that our method outperforms other model-free approaches.