openHSUThe DSpace digital repository system captures, stores, indexes, preserves, and distributes digital research material.https://openhsu.ub.hsu-hh.de:4432024-03-23T16:05:49Z2024-03-23T16:05:49ZSammelband zum Workshop: Entwicklungen und Forschungsergebnisse der Professur für Elektrische Maschinen und Antriebssysteme 2023Benninger, MoritzDreishing, FlorianGreve, DanielKreischer, ChristianKowalski, MatthiasRalf, Patrick AlexanderSteinacker, LucasZellmer, Florianhttps://doi.org/10.24405/153192024-03-21T11:33:54Z2024-03-19T00:00:00ZTitle: Sammelband zum Workshop: Entwicklungen und Forschungsergebnisse der Professur für Elektrische Maschinen und Antriebssysteme 2023
Authors: Benninger, Moritz; Dreishing, Florian; Greve, Daniel; Kreischer, Christian; Kowalski, Matthias; Ralf, Patrick Alexander; Steinacker, Lucas; Zellmer, Florian
Editors: Kreischer, Christian
Abstract: In diesem Sammelband werden die aktuellen Entwicklungen und Forschungsergebnisse der Professur für Elektrische Maschinen und Antriebssysteme im Jahr 2023 vorgestellt.
An der Professur wurden zwei Promotionen abgeschlossen und erfolgreich verteidigt. Das Thema der Dissertation von Herrn Pedram Quseiri Darbandeh lautet „Fault Diagnosis in a Permanent Magnet Synchronous Motor using Deep Learning“. Er untersucht hier sehr strukturiert und umfangreich die Möglichkeiten der datenbasierten Fehlerklassifizierung in Abhängigkeit verschiedener Sensorsignale, Datenaufbereitungsmethoden und verschiedener Trainingsmethoden für neuronale Netze.
Herr Johannes Liebrich hat zum Thema „Entwicklung einer Methode zur Chrakterisierung von Hochtemperatur-Supraleitern” promoviert. Die Arbeit liefert wichtige Erkenntnisse zu Schadensmechanismen und dem Ermüdungsverhalten von Supraleitern. Der entwickelte Versuchsstand kann zudem auch zur mechanischen Untersuchung weiterer Materialproben unter kryogenen Bedingungen verwendet werden. Mit den gewonnenen Erkenntnissen werden in Folgeprojekten supraleitende Spulen erforscht, welche für den Einsatz in Windenergieanlagen geeignet sind.
In diesem Jahr konnten zwei Forschungsprojekte abgeschlossen werden. Zum einen ein ZIM-Projekt, welches die Entwicklung einer mobilen und flexibel einsetzbaren Prüfmethode für entmagnetisierte Bauteile zum Ziel hatte. Hierbei ist es möglich mit einer festen Sensoranordnung auf die globale Magnetisierung eines Prüflings in einer magnetisch geschirmten Kammer zu schließen und das Magnetfeld für unterschiedliche Abstände zu ermitteln. Zum anderen wurde das Verbundprojekt KOBRA abgeschlossen, bei dem die Professur einen deutlich leistungsfähigeren Anodenantrieb auf Basis einer „Flux-Switching-Machine“ erforscht und messtechnisch validiert hat. Zudem wurde ein neues ZIM-Projekt zur Entwicklung eines intelligenten Wellenschwingungs-Torsionssensors eingeworben (AI-Torque).; This anthology presents the current developments and research results of the Professorship of Electrical Machines and Drive Systems in 2023.
Two doctorates were completed and successfully defended at the professorship. The topic of Mr. Pedram Quseiri Darbandeh‘s dissertation is “Fault Diagnosis in a Permanent Magnet Synchronous Motor using Deep Learning”. Here he examines the possibilities of data-based error classification in a very structured and comprehensive manner depending on various sensor signals, data preparation methods and various training methods for neural networks.
Mr. Johannes Liebrich did his doctorate on the development of a method for the characterization of high-temperature superconductors. The work provides important insights into damage mechanisms and the fatigue behavior of superconductors. The developed test stand can also be used for the mechanical examination of other material samples under cryogenic conditions. The knowledge gained will be used in follow-up projects to research superconducting coils that are suitable for use in wind turbines.
Two research projects were completed this year. On the one hand, a ZIM project, which aimed to develop a mobile and flexible testing method for demagnetized components. It is possible to use a fixed sensor arrangement to determine the global magnetization of a test object in a magnetically shielded chamber and to determine the magnetic field for different distances. On the other hand, the joint project KOBRA was completed, in which the professorship researched and validated a significantly more powerful anode drive based on a “flux switching machine”. In addition, a new ZIM project to develop an intelligent shaft vibration torsion sensor was acquired (AITorque).2024-03-19T00:00:00ZLeveraging self-supervised learning for vibration data in industrial separatorsHeuwinkel, TimMerkelbach, SilkeJanssen, NilsEnzberg, Sebastian vonDumitrescu, Romanhttps://doi.org/10.24405/153062024-03-19T09:00:47Z2024-03-01T00:00:00ZTitle: Leveraging self-supervised learning for vibration data in industrial separators
Authors: Heuwinkel, Tim; Merkelbach, Silke; Janssen, Nils; Enzberg, Sebastian von; Dumitrescu, Roman
Abstract: Industrial separators play a pivotal role in production processes of various sectors such as chemical, pharmaceutical, biotechnology, oil extraction and food industries, with over 3000 distinct applications. Operating these separators involves managing several process parameters as well as discharge and cleaning cycles, which are hard to control mainly due to deficiencies of current physical sensor technology. Recent studies have shown that machine learning can be utilized to detect faults and particle presence in separators via vibration data. However, traditional machine learning methods require domain expertise or vast amounts of labeled data. We propose the use of self-supervised learning to resolve this issue by learning useful representations from unlabeled data, which is significantly easier and cheaper to obtain. An empirical validation on data from a disk stack separator shows that self-supervised learning can improve upon manual feature engineering and supervised approaches in terms of cost, accuracy and data efficiency.2024-03-01T00:00:00ZMachine learning pipeline for application in manufacturingFitzner, AntjeHülsmann, TomAckermann, ThomasPouls, KevinKrauß, JonathanMende, FelixLeyendecker, LarsSchmitt, Robert H.https://doi.org/10.24405/153092024-03-19T09:00:44Z2024-03-01T00:00:00ZTitle: Machine learning pipeline for application in manufacturing
Authors: Fitzner, Antje; Hülsmann, Tom; Ackermann, Thomas; Pouls, Kevin; Krauß, Jonathan; Mende, Felix; Leyendecker, Lars; Schmitt, Robert H.
Abstract: The integration of machine learning (ML) into manufacturing processes is crucial for optimizing efficiency, reducing costs, and enhancing overall productivity. This paper proposes a comprehensive ML pipeline tailored for manufacturing applications, leveraging the widely recognized Cross-Industry Standard Process for Data Mining (CRISP-DM) as its foundational framework. The proposed pipeline consists of key phases, namely business understanding, use case selection and specification, data integration, data preparation, modelling, deployment, and certification. These are designed to meet the unique requirements and challenges associated with
ML implementation in manufacturing settings. Within each phase, sub-topics are defined to provide a granular understanding of the workflow. Responsibilities are clearly outlined to ensure a structured and efficient execution, promoting collaboration among stakeholders. Further, the input and output of each phase are defined. The methodology outlined in this research not only enhances the applicability of CRISP-DM in the manufacturing domain but also serves as a guide for practitioners seeking to implement ML solutions in a systematic and well-defined manner. The proposed pipeline aims to streamline the integration of ML technologies into manufacturing processes, facilitating informed decision-making and fostering the development of intelligent and adaptive manufacturing systems.2024-03-01T00:00:00ZData acqusition challenges in AI-driven surface inspection: a proven solution proposal on coated sheet metal partsHunger, SebastianBreiter, MichaelKlein, Claudiahttps://doi.org/10.24405/153102024-03-19T09:00:43Z2024-03-01T00:00:00ZTitle: Data acqusition challenges in AI-driven surface inspection: a proven solution proposal on coated sheet metal parts
Authors: Hunger, Sebastian; Breiter, Michael; Klein, Claudia
Abstract: This paper introduces an advanced AI-based automated surface inspection system for enhanced quality control in the manufacturing of white-coated sheet metal parts. The study emphasizes overcoming the challenges in AI-driven inspection, such as the need for large datasets corresponding to numerous physical components, which presents storage and logistical issues. By integrating Convolutional Neural Networks (CNNs) and a novel annotation process, the system can be trained effectively on various surface defects. The paper discusses three big data acquisition challenges and provides a solution approach, including large data volumes equivalent to numerous physical components, a novel division of the training process to reduce the workload for domain experts and the relevance of previously clearly defined defect classes.2024-03-01T00:00:00Z