<div class="csl-bib-body">
<div class="csl-entry">Binder, M. (2021). <i>Shape optimization based on reinforcement learning</i> [Diploma Thesis, Technische Universität Wien]. reposiTUm. https://doi.org/10.34726/hss.2021.86842</div>
</div>
-
dc.identifier.uri
https://doi.org/10.34726/hss.2021.86842
-
dc.identifier.uri
http://hdl.handle.net/20.500.12708/19212
-
dc.description
Abweichender Titel nach Übersetzung der Verfasserin/des Verfassers
-
dc.description.abstract
The main focus of this thesis is to explore the feasibility of learning-based algorithms such as Reinforcement Learning (RL) as a data-driven alternative to classical optimization algorithms. For this, a simple geometry T-shaped geometry, which can be seen as an abstraction of the flow channel inside a profile extruder, is optimized with two different RL algorithms. First, a test function for optimization is introduced to establish if the RL algorithm works and if the training of the algorithm can be improved. Based on this test function, a reward function is shaped, and a hyperparameter study is performed. The results show, that a dynamic reward function is most suitable for this task and show that the standard hyperparameter are good enough and do not need to be changed. For the shape optimization task, a specific mass flow ratio between the two outflows of the geometry has to be configured. The flow channel geometry is parameterized by two different methods — one changes the corner points of the geometry directly, while the other one applies Free-Form Deformation (FFD). FFD deforms a box surrounding the object to change its shape. The experiments are carried out in order of increasing Degrees Of Freedom (DOF), as this turns out to be a measurement of the difficulty of the tasks. The RL algorithms are trained for a specific number of episodes and are evaluated if they can achieve the pre-defined goal of a specific mass flow ratio and if the learning decreases the number of time steps needed per episode.The RL algorithms tested, namely Advantage Actor Critic (A2C) and Proximal Policy Optimization (PPO), can both achieve the pre-defined goals most of the time. In the tasks with the direct change of coordinates, the algorithms can improve their policy while their performance stays fairly constant for the task with the FFD, probably because it has too many DOF. In the test cases where the agents can improve their policy, the A2C agents outperforms the PPO agent. The methods for shape optimization introduced in this thesis look very promising and, if further improved, could become a new standard for shape optimization tasks.
en
dc.language
English
-
dc.language.iso
en
-
dc.rights.uri
http://rightsstatements.org/vocab/InC/1.0/
-
dc.subject
Simulation
de
dc.subject
Numerische Methoden
de
dc.subject
Finite Elemente Methoden
de
dc.subject
simulation
en
dc.subject
numerical methods
en
dc.subject
numerical design
en
dc.subject
optimization
en
dc.subject
finite element method
en
dc.subject
programming
en
dc.subject
machine learning
en
dc.subject
reinforcement learning
en
dc.title
Shape optimization based on reinforcement learning
en
dc.title.alternative
Formoptimierung mittels Reinforcement Learning
de
dc.type
Thesis
en
dc.type
Hochschulschrift
de
dc.rights.license
In Copyright
en
dc.rights.license
Urheberrechtsschutz
de
dc.identifier.doi
10.34726/hss.2021.86842
-
dc.contributor.affiliation
TU Wien, Österreich
-
dc.rights.holder
Michael Binder
-
dc.publisher.place
Wien
-
tuw.version
vor
-
tuw.thesisinformation
Technische Universität Wien
-
dc.contributor.assistant
Edelmann, Johannes
-
tuw.publication.orgunit
E317 - Institut für Leichtbau und Struktur-Biomechanik