TY - GEN
T1 - A Survey of Machine Learning in Rocket Propulsion Applications
AU - Maicke, Brian A.
N1 - Publisher Copyright:
© 2023, American Institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.
PY - 2023
Y1 - 2023
N2 - This paper examines the current state of machine learning and related techniques with regard to their application to propulsion applications with an emphasis on rockets. A survey of the current research literature will be provided, examining the different machine learning tools and how they are applied to propulsive applications. In addition to this review, challenges to adoption of machine learning tools will be examined both in general and in propulsion specific contexts. The availability of high-fidelity data is a challenge of critical importance, especially in the area of propulsionrelated research, as machine learning algorithms require extensive training data to be effective. Finally, a review of potential areas for expansion will also be evaluated for their suitability for machine learning and related tools. Of particular interest are the areas of generative design and physics-informed machine learning which may provide increased propulsion system performance due to alternate designs that may not have been considered and additional physical insight into the complex physics of propulsive flows.
AB - This paper examines the current state of machine learning and related techniques with regard to their application to propulsion applications with an emphasis on rockets. A survey of the current research literature will be provided, examining the different machine learning tools and how they are applied to propulsive applications. In addition to this review, challenges to adoption of machine learning tools will be examined both in general and in propulsion specific contexts. The availability of high-fidelity data is a challenge of critical importance, especially in the area of propulsionrelated research, as machine learning algorithms require extensive training data to be effective. Finally, a review of potential areas for expansion will also be evaluated for their suitability for machine learning and related tools. Of particular interest are the areas of generative design and physics-informed machine learning which may provide increased propulsion system performance due to alternate designs that may not have been considered and additional physical insight into the complex physics of propulsive flows.
UR - http://www.scopus.com/inward/record.url?scp=85199891577&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85199891577&partnerID=8YFLogxK
U2 - 10.2514/6.2023-4033
DO - 10.2514/6.2023-4033
M3 - Conference contribution
AN - SCOPUS:85199891577
SN - 9781624107047
T3 - AIAA Aviation and Aeronautics Forum and Exposition, AIAA AVIATION Forum 2023
BT - AIAA Aviation and Aeronautics Forum and Exposition, AIAA AVIATION Forum 2023
PB - American Institute of Aeronautics and Astronautics Inc, AIAA
T2 - AIAA Aviation and Aeronautics Forum and Exposition, AIAA AVIATION Forum 2023
Y2 - 12 June 2023 through 16 June 2023
ER -