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

Experimental and Simulative Evaluation of a Reinforcement Learning Based Cold Gas Thrust Chamber Pressure Controller

Hörger, Till and Werling, Lukas and Dresia, Kai and Waxenegger-Wilfing, Günther and Schlechtriem, Stefan (2023) Experimental and Simulative Evaluation of a Reinforcement Learning Based Cold Gas Thrust Chamber Pressure Controller. Aerospace Europe Conference 2023 – 10ᵀᴴ EUCASS – 9ᵀᴴ CEAS, 2023-07-09 - 2023-07-13, Lausanne, Schweitz. doi: 10.13009/EUCASS2023-639.

[img] PDF
1MB

Official URL: file:///C:/Users/hanke/Downloads/EUCASS2023-639.pdf

Abstract

At DLR neural networks, as potential future controller for rocket engines, are studied. A neural network-based chamber pressure controller for a simplified cold gas thruster is presented and analyzed in simulation and experiment. The goal of the controller is twofold: It can track a trajectory with different changes of setpoints and it allows to set and control a wide variety of steady state chamber pressures. The neural network gets feeding line pressure measurement data as input and calculates valve positions as output values. The training phase of the controller is done with a reinforcement learning algorithm in an Ecosim-Pro/ESPSS simulation, that is validated with data from the corresponding experimental set up. To increase the robustness and to allow a transfer from the simulation directly to the test facility domain randomization is applied. The controller is evaluated in simulations and experiment. It was found that - in the range of physically possible operation points - the controller achieves a constantly high reward which corresponds to a low error and a good control performance. In the simulation the controller was able to adjust all required set points with a steady state error of less than 0.1 bar while retaining a small overshoot and an optimal settling time. It is found that the controller is also able to regulate all desired set points in the real experiment. A reference trajectory with different steps, linear and sinus changes in target pressure is tested in simulation and experiment. The controller was in both cases able to successfully follow the given trajectory

Item URL in elib:https://elib.dlr.de/197950/
Document Type:Conference or Workshop Item (Speech)
Title:Experimental and Simulative Evaluation of a Reinforcement Learning Based Cold Gas Thrust Chamber Pressure Controller
Authors:
AuthorsInstitution or Email of AuthorsAuthor's ORCID iDORCID Put Code
Hörger, TillUNSPECIFIEDhttps://orcid.org/0000-0001-5859-9907UNSPECIFIED
Werling, LukasUNSPECIFIEDhttps://orcid.org/0000-0003-4353-2931UNSPECIFIED
Dresia, KaiUNSPECIFIEDhttps://orcid.org/0000-0003-3229-5184UNSPECIFIED
Waxenegger-Wilfing, GüntherUNSPECIFIEDhttps://orcid.org/0000-0001-5381-6431UNSPECIFIED
Schlechtriem, StefanUNSPECIFIEDhttps://orcid.org/0000-0002-3714-9664UNSPECIFIED
Date:2023
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In SCOPUS:No
In ISI Web of Science:No
DOI:10.13009/EUCASS2023-639
Status:Published
Keywords:Machine Learning, Engine Controller
Event Title:Aerospace Europe Conference 2023 – 10ᵀᴴ EUCASS – 9ᵀᴴ CEAS
Event Location:Lausanne, Schweitz
Event Type:international Conference
Event Start Date:9 July 2023
Event End Date:13 July 2023
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 > Spacecraft and Orbital Propulsion
Deposited By: Hörger, Till
Deposited On:28 Nov 2023 15:17
Last Modified:24 Apr 2024 20:58

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Website and database design: Copyright © German Aerospace Center (DLR). All rights reserved.