DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Preliminary Investigation of Robust Reinforcement Learning for Control of an Existing Green Propellant Thruster

Hörger, Till and Dresia, Kai and Waxenegger-Wilfing, Günther and Werling, Lukas and Schlechtriem, Stefan (2020) Preliminary Investigation of Robust Reinforcement Learning for Control of an Existing Green Propellant Thruster. AIAA Propulsion and Energy Forum, 09.-11.08. 2020, Denver, online.

[img] PDF - Only accessible within DLR


Advanced engine control is an important requirement for the efficient operation of future reusable engines, facilitating a safer and more economical engine operation. For this reason, modern control strategies are extensively studied in recent years, mainly through the use of simulation environments. An important development step is to test the performance and robustness of the control algorithm at real test benches. The present paper describes the first steps towards the use of an reinforcement learning based controller on a N2O / C2H6 22 N green propellant thruster. The control objectives are given by regulating the mixture ratio and combustion pressure. The existing test bench is modelled in EcosimPro / ESPSS. Based on the simulation model deep reinforcement learning is used to train the controller and domain randomization is used to increase the robustness. The overall goal is to transfer the controller from the simulation model to the real test bench. Finally, preliminary experiments demonstrate the basic functionality of reinforcement learning based controllers for real rocket propulsion systems.

Item URL in elib:https://elib.dlr.de/143555/
Document Type:Conference or Workshop Item (Speech)
Title:Preliminary Investigation of Robust Reinforcement Learning for Control of an Existing Green Propellant Thruster
AuthorsInstitution or Email of AuthorsAuthor's ORCID iD
Hörger, TillDLR Lampoldshausen, Institut für Raumfahrtantriebehttps://orcid.org/0000-0001-5859-9907
Dresia, KaiDLR Lampoldshausen, Institut für Raumfahrtantriebehttps://orcid.org/0000-0003-3229-5184
Waxenegger-Wilfing, GüntherDLR Lampoldshausen, Institut für Raumfahrtantriebehttps://orcid.org/0000-0001-5381-6431
Werling, LukasDLR Lampoldshausen, Institut für Raumfahrtantriebehttps://orcid.org/0000-0003-4353-2931
Schlechtriem, StefanDLR Lampoldshausen, Institut für Raumfahrtantriebehttps://orcid.org/0000-0002-3714-9664
Date:August 2020
Refereed publication:Yes
Open Access:No
Gold Open Access:No
In ISI Web of Science:No
Keywords:Reinforcement Learning, Thruster Control
Event Title:AIAA Propulsion and Energy Forum
Event Location:Denver, online
Event Type:international Conference
Event Dates:09.-11.08. 2020
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Space Transportation
DLR - Research area:Raumfahrt
DLR - Program:R RP - Space Transportation
DLR - Research theme (Project):R - Agile development of advanced rocket propulsion systems
Location: Lampoldshausen
Institutes and Institutions:Institute of Space Propulsion
Deposited By: Hörger, Till
Deposited On:23 Aug 2021 10:34
Last Modified:23 Aug 2021 10:34

Repository Staff Only: item control page

Help & Contact
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.