Dragonfly Rotor Optimization using Machine Learning

by Dr. Jason K. Cornelius

Abstract: NASA’s 4th New Frontiers Mission is the Titan Dragonfly relocatable lander. This coaxial quadrotor vehicle will be launched on a rocket to Titan in 2028 with the goal of exploring Titan’s pre-biotic chemistry and habitability. The design has continually evolved since 2016 with the unique constraints imposed by Titan’s cryogenic atmosphere, gravity, and atmospheric density along with the inability to test the entire system under these conditions until the first flight on Titan.

This presentation discusses the rotor design aspects of the Dragonfly lander and introduces a novel framework for multirotor design optimization that leverages machine learning methods and is demonstrated in the context of Dragonfly. A new OVERFLOW Machine Learning Airfoil Performance (PALMO) database is first presented. PALMO is wrapped inside a Bayesian optimization framework and applied to a 4-rotor system (one side of the Dragonfly lander). Training data is generated on each iteration of the optimization using the CAMRAD-II comprehensive analysis software to evaluate successive rotor designs in multiple flight conditions.

An optimal design for the 4-rotor system was found with ~900 rotor designs analyzed in CAMRAD-II, which required 9 million queries of the PALMO surrogate models. This framework evaluated 10,000,000 potential candidate rotor designs in 5.5 hours on 114 CPU cores using uniform inflow, and in 27.8 hours using the prescribed wake model.