Fachbereich - Elektro- & Informationstechnik
Refine
Year of publication
Document Type
- Announcement (75)
- Article (60)
- Conference Proceeding (44)
- Bachelor Thesis (9)
- Preprint (9)
- Study Thesis (9)
- Article trade magazine (4)
- Book (3)
- Doctoral Thesis (2)
- Master's Thesis (2)
Keywords
- Amtliche Mitteilungen (73)
- Prüfungsrecht (52)
- Prüfungsordnung (51)
- Bachelor (42)
- EI (30)
- Änderung (25)
- Elektrotechnik (20)
- Satzung (19)
- FHD (18)
- Master (16)
Department/institution
- Fachbereich - Elektro- & Informationstechnik (224)
- Hochschulverwaltung (75)
- Fachbereich - Wirtschaftswissenschaften (5)
- Fachbereich - Architektur (4)
- Fachbereich - Design (4)
- Fachbereich - Medien (4)
- Fachbereich - Maschinenbau und Verfahrenstechnik (3)
- Fachbereich - Sozial- & Kulturwissenschaften (1)
- Hochschulbibliothek (1)
Examining the Impact of Optical Aberrations to Image Classification and Object Detection Models
(2025)
Die digitale Transformation der Gesellschaft betrifft auch und in besonderem Maße Hochschulen, die Studierende auf eine digitale Gesellschaft vorbereiten, Digitalisierung zum Gegenstand von Forschung und Transfer machen und einen wesentlichen Beitrag zur kritischen Reflexion von Digitalität leisten. Vor diesem Hintergrund möchte die Hochschule Düsseldorf (HSD) Chancen ergreifen, die sich für unsere Mitglieder und Angehörigen und für Hochschule als Organisation ergeben. Gleichzeitig will die HSD Risiken vermeiden, die aus einer undifferenzierten Adaption technischer Möglichkeiten folgen. Zu den Risiken gehören die sozialen, politischen und ökologischen Effekte des flächendeckenden Einsatzes von Technologie. Im Zuge der Entwicklung der Digitalstrategie haben sich Mitglieder und Angehörige der HSD aus allen Statusgruppen intensiv mit den Chancen und Risiken der Digitalisierung auseinandergesetzt, um einen Beitrag zur erfolgreichen Gestaltung der digitalen Transformation an der HSD zu leisten.
Dieser Beitrag beschreibt die Umsetzung und experimentelle Validierung einer dezentralen, agenten-basierten Aufgabenverteilung für Multi-Roboter-Systeme auf Basis des Contract Net Protocol. Die dabei untersuchte Problemstellung ist die effiziente Durchführung einer Vielzahl von Transportaufträgen durch eine mobile Roboterflotte. Hierzu wurden dezidierte Änderungen am Contract Net Protocol eingeführt, mit dem Ziel die Optimalität der Auftragsverteilung zu verbessern. Die Umsetzung des entwickleten Algorithmus erfolgte in ROS2, die experimentellen Untersuchungen wurden mit Hilfe einer Flotte an TurtleBot3-Robotern durchgeführt.
This paper presents a novel method for enhancing the adaptability of Proportional-Integral-Derivative (PID) controllers in industrial systems using event-based dynamic game theory, which enables the PID controllers to self-learn, optimize, and fine-tune themselves. In contrast to conventional self-learning approaches, our proposed framework offers an event-driven control strategy and game-theoretic learning algorithms. The players collaborate with the PID controllers to dynamically adjust their gains in response to set point changes and disturbances. We provide a theoretical analysis showing sound convergence guarantees for the game given suitable stability ranges of the PID controlled loop. We further introduce an automatic boundary detection mechanism, which helps the players to find an optimal initialization of action spaces and significantly reduces the exploration time. The efficacy of this novel methodology is validated through its implementation in the temperature control loop of a printing press machine. Eventually, the outcomes of the proposed intelligent self-tuning PID controllers are highly promising, particularly in terms of reducing overshoot and settling time.
Examining the Impact of Optical Aberrations to Image Classification and Object Detection Models
(2025)
Deep neural networks (DNNs) have proven to be successful in various computer vision applications such that models even infer in safety-critical situations. Therefore, vision models have to behave in a robust way to disturbances such as noise or blur. While seminal benchmarks exist to evaluate model robustness to diverse corruptions, blur is often approximated in an overly simplistic way to model defocus, while ignoring the different blur kernel shapes that result from optical systems. To study model robustness against realistic optical blur effects, this paper proposes two datasets of blur corruptions, which we denote OpticsBench and LensCorruptions. OpticsBench examines primary aberrations such as coma, defocus, and astigmatism, i.e. aberrations that can be represented by varying a single parameter of Zernike polynomials. To go beyond the principled but synthetic setting of primary aberrations, LensCorruptions samples linear combinations in the vector space spanned by Zernike polynomials, corresponding to 100 real lenses. Evaluations for image classification and object detection on ImageNet and MSCOCO show that for a variety of different pre-trained models, the performance on OpticsBench and LensCorruptions varies significantly, indicating the need to consider realistic image corruptions to evaluate a model's robustness against blur.
Self-optimization in distributed manufacturing systems using Modular State-based Stackelberg games
(2025)
In this study, we introduce Modular State-based Stackelberg Games (Mod-SbSG), a novel game structure developed for distributed self-learning in modular manufacturing systems. Mod-SbSG enhances cooperative decision-making among self-learning agents within production systems by integrating State-based Potential Games (SbPG) with Stackelberg games. This hierarchical structure assigns more important modules of the manufacturing system a first-mover advantage, while less important modules respond optimally to the leaders’ decisions. This decision-making process differs from typical multi-agent learning algorithms in manufacturing systems, where decisions are made simultaneously. We provide convergence guarantees for the novel game structure and design learning algorithms to account for the hierarchical game structure. We further analyse the effects of single-leader/multiple-follower and multiple-leader/multiple-follower scenarios within a Mod-SbSG. To assess its effectiveness, we implement and test Mod-SbSG in an industrial control setting using two laboratory-scale testbeds featuring sequential and serial parallel processes. The proposed approach delivers promising results compared to the vanilla SbPG, which reduces overflow by 97.1%, and in some cases, prevents overflow entirely. Additionally, it decreases power consumption by 5%–13% while satisfying the production demand, which significantly improves potential (global objective) values.