University of Twente Student Theses


Control of a wing flap using 3D printed flow sensors and reinforcement learning

Hommels, T.C. (2022) Control of a wing flap using 3D printed flow sensors and reinforcement learning.

[img] PDF
Abstract:The field of fluid mechanics has used reinforcement learning (RL) to increase the performance of control on objects moving in a fluid environment. In this research, a 3D printed flow sensor performs the environmental observations, needed for RL, in an experimental setup. RL and a 3D printed flow sensor are combined with the objective of actuating the flaps of an airfoil in such a way that the lift of the airfoil remains constant for changing wind speeds. The performed experiments include looking into the sensing abilities of the flow sensor in the airfoil at different wind speeds, generated by a wind tunnel, and training of the RL algorithm. From the results, it was found that the 3D printed flow sensor worked sufficiently and that the RL algorithm performed successful in the simulated environment, but it lacked accuracy in the real world setup. This could be attributed to the more complex environment, drawbacks of the wind tunnel and that in the real world experiments certain wind speed and action combinations provided almost the same sensor observation. Nevertheless, the experiments did show the possibility of using an RL algorithm in combination with a 3D printed flow sensor.
Item Type:Essay (Master)
Faculty:EEMCS: Electrical Engineering, Mathematics and Computer Science
Subject:50 technical science in general
Programme:Systems and Control MSc (60359)
Link to this item:
Export this item as:BibTeX
HTML Citation
Reference Manager


Repository Staff Only: item control page