Vortex gust mitigation from onboard measurements using deep reinforcement learning
This paper proposes to solve the vortex gust mitigation problem on a 2D, thin flat plate using onboard measurements. The objective is to solve the discrete-time optimal control problem of finding the pitch rate sequence that minimizes the lift perturbation, that is, the criterion where is the lift...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Cambridge University Press
2024-01-01
|
| Series: | Data-Centric Engineering |
| Subjects: | |
| Online Access: | https://www.cambridge.org/core/product/identifier/S2632673624000388/type/journal_article |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841526532352245760 |
|---|---|
| author | Brice Martin Thierry Jardin Emmanuel Rachelson Michael Bauerheim |
| author_facet | Brice Martin Thierry Jardin Emmanuel Rachelson Michael Bauerheim |
| author_sort | Brice Martin |
| collection | DOAJ |
| description | This paper proposes to solve the vortex gust mitigation problem on a 2D, thin flat plate using onboard measurements. The objective is to solve the discrete-time optimal control problem of finding the pitch rate sequence that minimizes the lift perturbation, that is, the criterion where is the lift coefficient obtained by the unsteady vortex lattice method. The controller is modeled as an artificial neural network, and it is trained to minimize using deep reinforcement learning (DRL). To be optimal, we show that the controller must take as inputs the locations and circulations of the gust vortices, but these quantities are not directly observable from the onboard sensors. We therefore propose to use a Kalman particle filter (KPF) to estimate the gust vortices online from the onboard measurements. The reconstructed input is then used by the controller to calculate the appropriate pitch rate. We evaluate the performance of this method for gusts composed of one to five vortices. Our results show that (i) controllers deployed with full knowledge of the vortices are able to mitigate efficiently the lift disturbance induced by the gusts, (ii) the KPF performs well in reconstructing gusts composed of less than three vortices, but shows more contrasted results in the reconstruction of gusts composed of more vortices, and (iii) adding a KPF to the controller recovers a significant part of the performance loss due to the unobservable gust vortices. |
| format | Article |
| id | doaj-art-db78b9f39d054ccd83cf8b3b6221e45a |
| institution | Kabale University |
| issn | 2632-6736 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | Cambridge University Press |
| record_format | Article |
| series | Data-Centric Engineering |
| spelling | doaj-art-db78b9f39d054ccd83cf8b3b6221e45a2025-01-16T21:47:41ZengCambridge University PressData-Centric Engineering2632-67362024-01-01510.1017/dce.2024.38Vortex gust mitigation from onboard measurements using deep reinforcement learningBrice Martin0https://orcid.org/0009-0007-4418-4912Thierry Jardin1Emmanuel Rachelson2Michael Bauerheim3https://orcid.org/0000-0001-9550-9077ISAE-SUPAERO, Université de Toulouse, FranceISAE-SUPAERO, Université de Toulouse, FranceISAE-SUPAERO, Université de Toulouse, FranceISAE-SUPAERO, Université de Toulouse, FranceThis paper proposes to solve the vortex gust mitigation problem on a 2D, thin flat plate using onboard measurements. The objective is to solve the discrete-time optimal control problem of finding the pitch rate sequence that minimizes the lift perturbation, that is, the criterion where is the lift coefficient obtained by the unsteady vortex lattice method. The controller is modeled as an artificial neural network, and it is trained to minimize using deep reinforcement learning (DRL). To be optimal, we show that the controller must take as inputs the locations and circulations of the gust vortices, but these quantities are not directly observable from the onboard sensors. We therefore propose to use a Kalman particle filter (KPF) to estimate the gust vortices online from the onboard measurements. The reconstructed input is then used by the controller to calculate the appropriate pitch rate. We evaluate the performance of this method for gusts composed of one to five vortices. Our results show that (i) controllers deployed with full knowledge of the vortices are able to mitigate efficiently the lift disturbance induced by the gusts, (ii) the KPF performs well in reconstructing gusts composed of less than three vortices, but shows more contrasted results in the reconstruction of gusts composed of more vortices, and (iii) adding a KPF to the controller recovers a significant part of the performance loss due to the unobservable gust vortices.https://www.cambridge.org/core/product/identifier/S2632673624000388/type/journal_articlevortex gust mitigationdeep reinforcement learningKalman filteraerodynamicsobservability |
| spellingShingle | Brice Martin Thierry Jardin Emmanuel Rachelson Michael Bauerheim Vortex gust mitigation from onboard measurements using deep reinforcement learning Data-Centric Engineering vortex gust mitigation deep reinforcement learning Kalman filter aerodynamics observability |
| title | Vortex gust mitigation from onboard measurements using deep reinforcement learning |
| title_full | Vortex gust mitigation from onboard measurements using deep reinforcement learning |
| title_fullStr | Vortex gust mitigation from onboard measurements using deep reinforcement learning |
| title_full_unstemmed | Vortex gust mitigation from onboard measurements using deep reinforcement learning |
| title_short | Vortex gust mitigation from onboard measurements using deep reinforcement learning |
| title_sort | vortex gust mitigation from onboard measurements using deep reinforcement learning |
| topic | vortex gust mitigation deep reinforcement learning Kalman filter aerodynamics observability |
| url | https://www.cambridge.org/core/product/identifier/S2632673624000388/type/journal_article |
| work_keys_str_mv | AT bricemartin vortexgustmitigationfromonboardmeasurementsusingdeepreinforcementlearning AT thierryjardin vortexgustmitigationfromonboardmeasurementsusingdeepreinforcementlearning AT emmanuelrachelson vortexgustmitigationfromonboardmeasurementsusingdeepreinforcementlearning AT michaelbauerheim vortexgustmitigationfromonboardmeasurementsusingdeepreinforcementlearning |