Studentische Ausschreibungen
Wir können Ihnen kontinuierlich interessante Aufgaben in den Bereichen Festigkeit, Tribologie, Gleitlager, (nachhaltige) Produktentwicklung, Optimierung, Nachgiebige Systeme und Transition Engineering anbieten. Wir haben es nur leider noch nicht gechafft, diese hier zu vermerken. Sprechen Sie uns bitte sehr gern an.Art
Kategorie
Recherche
Reverse Engineering of scroll compressors
25.11.2025The task can be modified depending on the individual experience and goals!
In modern electric automobiles electric refrigerant compressors are used both for cooling the traction battery and for interior climate control. Scroll compressors are frequently used for this purpose.
As part of a benchmarking project of the professorship, 3D scan data of scroll profiles are being collected to draw conclusions about stroke and dead volume. For precise volume measurement, it is necessary to convert the acquired scan data into CAD-capable surface models. However, the reconstruction of such models from point clouds or meshes presents a significant technical challenge: the complex geometries of the scroll profiles substantially complicate the surface reconstruction, meaning that classic reverse engineering approaches are often time-consuming and lead to inaccurate results.
Current reverse engineering advances utilize deep learning models to allow the deduction of CAD commands from point clouds. One of these is open-source, the installation and implementation of this model is essential. This approach however, is limited to simple line, arc and circle sketch commands and extrude operations. The core of the scroll compressor is a pair of interlocking spirals, which cannot be constructed by these simple commands. They can however be easily constructed with so called "splines". Current datasets, on which the models are trained, do not contain these splines, thus no model can construct splines. The usage of splines in public CAD repositories is minimal. Therefore a synthetic dataset has to be created, filled with automatically generated examples of spline geometries. The dataset should contain geometries of varying complexity as well as simple commands like line, arc and circle to represent real-life complexity. Using this synthetic dataset, the already existing capabilities of the employed model can be further extended to include spline geometries within sketches.
To summarize: For the accurate reconstruction of scroll compressors, we want to establish and fine-tune a deep learning model capable of reverse engineering with a synthetic dataset filled with splines.
Literature:
GenCAD3D: https://arxiv.org/abs/2509.15246
Art: HiWi, SA, PA, BA, MA, DA
Kategorie: Programmierung, Recherche
Ansprechperson: Leon Josef Stahr, M.Sc. ( leon-josef.stahr@…)
Recherche
Neural Fields for Topology Optimization with Evaluator-based Training
24.10.2025The task can be modified depending on the individual experience and goals!
Neural Fields are a little known type of neural network, that act akin to functions. This makes them interesting for the application in topology optimization, since they do not depend on resolution. Their application could prove to be a pivotal advancement of AI based Topology Optimization, which is inherently limited by the computational effort for either the synthesis of training data or the evaluation of generated structures with FE Analysis.
Literature:
https://arxiv.org/abs/2402.05073
Art: HiWi, SA, PA, BA, MA, DA
Kategorie: Programmierung, Recherche
Ansprechperson: Leon Josef Stahr, M.Sc. ( leon-josef.stahr@…)
Recherche
Bewertungsmethoden von CAD-Konstruktionen für Deep-Learning Anwendungen
23.10.2025Die Anwendung von Deep-Learning (DL) Methoden zur Unterstützung des Konstruktionsprozess‘, beispielsweise bei der Erstellung von CAD-Modellen, verspricht eine Qualitäts- und Effizienzsteigerung, ähnlich zur Produktivitätssteigerung von Programmieren.
Für das Training eines DL Modells werden Unmengen an Daten benötigt. Existierende, adäquat dimensionierte Datensätze enthalten primär Designs von Amateur-Konstrukteuren, da die Arbeit von Experten oft Betriebsgeheimnis ist. Solche Designs variieren in der Folge stark in ihrer Qualität und ignorieren Design-Richtlinien und Prinzipien. Für das Training von CAD generierenden DL Modellen ist es daher unbedingt notwendig, eine Bewertung der Designs vorzunehmen, um letztendlich sinnvolle und nachvollziehbare Designs generieren zu können.
Eine solche Bewertungsmethodik zu finden und zu prüfen ist Kernaufgabe dieser Ausschreibung. Der Umfang kann auf die jeweilige Art der Arbeit angepasst werden. Mit Ihrer Mitarbeit an diesem Thema wirken Sie aktiv an der Weiterentwicklung und dem Erfolg des Forschungsvorhabens SPP2444 mit.
Art: HiWi, SA, PA, BA, MA, DA
Kategorie: Programmierung, Recherche
Ansprechperson: Leon Josef Stahr, M.Sc. ( leon-josef.stahr@…)
