Vorarlberg University of Applied Sciences
Online Publication Server University of Applied Science VorarlbergNot a member yet
2106 research outputs found
Sort by
Digitalisierung einer Siebdruckfertigung
Get PDFDiese Masterarbeit untersucht die Herausforderung von Schatten-IT und Brownfield-Umgebungen in der Siebdruckfertigung. Hierzu wurden die Zusammenhänge von Technologien der Industrie 4.0 bis hin zur menschenzentrierten Industrie 5.0 analysiert. Auf dieser Grundlage wurden in Fokusgruppen mit Fachexpert:innen Problemfelder, wie Prozesssteuerung, Einarbeitung und dynamische Vorgaben, erörtert und praxisnahe Industrie 4.0 Anwendungsszenarien entwickelt. Durch die Synthese dieser Erkenntnisse mit der Theorie wurden detaillierte Use-Cases abgeleitet. Diese bilden eine Roadmap für eine schrittweise digitale Transformation. Die Roadmap reicht von der Einführung einer Datenplattform über digitale Assistenzsysteme und Wissensassistenten bis hin zur KI-gestützten Prozessoptimierung. Die Arbeit schließt mit einem generalistischen Prozessmodell ab, das Unternehmen als Leitfaden für vergleichbare Transformationsprojekte nutzen können.This master´s thesis investigates the challenges within a screen printing production environment in an industrial company characterised by a brownfield setting and an evolved landscape of shadow IT. The analysis includes technologies from Industry 4.0 to the human-centred principles of Industry 5.0. In focus groups with subject-matter experts, key problem areas such as process control, employee onboarding, and dynamic specifications were discussed. Based on these discussions, pracitcal Industry 4.0 application scenarios were developed. Through the synthesis of these insights with theoretical foundations, detailed use cases were derived. These use cases form a roadmap for a step-by-step digital transformation, ranging from the implemenation of a data platform, through digital assistance systems and knowledge assistants, to AI-driven process optimisation. The thesis concludes with a generalist process model that serves as a guide for companies untertaking similar transformation projects
Preprocessing pipelines for OT network traffic capture data in AI cybersecurity applications
No full textDigitalisation is driving a new level of focus on Cybersecurity in Industrial Internet of Things (IIoT) and Operationsal Technology (OT) environments. Various techniques to detect malicious activity in OT networks based on network traffic monitoring have been developed. These often use Aritficial Intelligence (AI), or rather Machine Learning (ML), algorithms to identify and classify the traffic as potentially malicious. Training and testing of these algorithms requires data in ML-processable formats; however, network traffic capture files are typically not ML-ready, i.e., they are usually not readily usable for the training of ML classifiers. This paper reviews the procedures for building current state-of-the-art OT network traffic datasets. By considering 17 different datasets, we discuss approaches used for dataset creation, attack simulation, and labelling, respectively. On this basis, this work proposes a new pipeline for processing PCAP files into ML-ready formats. The pipeline leverages currently available open source tools and includes a set of options to enable the pipeline to be tailored to specific ML/AI algorithms, OT protocols and attack types. While PCAP files can capture malicious traffic, there are no inherent labels present in PCAPs. Thus, a particular focus is on the different types of labelling strategies available for the pipeline. The pipeline provides a useful overview of the available network traffic data preprocessing options. It also supports a broader range of ML and cybersecurity practitioners when using raw network traffic datasets for ML learning purposes in OT environments. The practicability of the proposed pipeline is demonstrated by relabeling network traffic capture data of a publicly available PCAP dataset in two ways and by comparing the results to original labels
Impact of visual presentation of atherosclerotic carotid plaque on cardiovascular risk profile using mHealth technologies
No full textThis randomized, controlled trial evaluated the impact of plaque visualization combined with daily tasks on cardiovascular risk profile and included 240 participants with coronary arterial disease. The intervention group received the PreventiPlaque app during the 12-month study period in addition to standard care. The app contained daily tasks that promoted lifestyle modifications and adherence to prescribed medication. It included ultrasound images of participants´ individual carotid plaque, which were updated regularly. The impact of plaque visualization and personalized app usage was evaluated, using a change in the SCORE2 as a primary endpoint. In the intervention group, the SCORE2 was significantly lower after the study period (t(120) = 6.43, padj < 0.001, dRM = 0.58). This demonstrates the efficacy of the PreventiPlaque app in supporting lifestyle modifications and medication adherence. These findings suggest that personalized mHealth interventions in combination with visual risk communication are valuable tools in secondary prevention. Trial Registration: The study was registered at ClinicalTrials.gov under the identifier NCT05096637 on 27 October 2021 and was approved by the local ethics committee of the University of Duisburg-Essen (20-9157-BO)
Algorithms for peak power reduction in a battery electric bus depot
Get PDFThe electrification of public transport introduces significant challenges for battery electric bus (BEB) fleet operators and power grid operators. This paper investigates the potential of two charging optimization strategies to reduce peak power demand in a BEB depot in Vorarlberg, Austria. A heuristic algorithm and Mixed-Integer Linear Programming (MILP) are analyzed and
compared to a reference strategy representing uncoordinated charging. The study aims to minimize peak power demand while ensuring efficient use of charging infrastructure. The results demonstrate the effectiveness of intelligent charging management in addressing the challenges posed by BEB operations
Klimarisiken sichtbar machen: Modulare Dashboards für Klimawandelanpassung und Katastrophenschutz
Get PDFEnergy cost and emission optimization in food industry using deep reinforcement learning and Transformer-based load forecasting
Get PDFGiven the substantial energy demands of the food industry, this study introduces a data-driven demand response strategy for industrial refrigeration in the food-processing sector, targeting reductions in electricity costs and equivalent CO2 emissions. To this end, the thermal flexibility of a warehouse is quantified using real measurement data, resulting in an estimated thermal capacity of 182 kWh/K. A temperature bandwidth of 5 K as flexibility corresponds to an equivalent electrical energy storage of 445 kWh. To enable predictive control, a Transformer-Encoder architecture is used for short-term thermal load forecasting. By pretraining the Transformer on historical electrical load data from the entire factory, the model captures broader operational patterns, improving the forecast accuracy despite a limited amount of thermal data. Based on these forecasts, a deep reinforcement learning agent is trained to optimize the set point of a proportional–integral controller within predefined temperature limits. The agent successfully balances conflicting objectives, achieving up to 15.50% cost savings and 9.80% emission reductions compared to a baseline scenario. A Pareto front illustrates the trade-offs between cost and emission minimization. The results demonstrate the effectiveness of combining deep reinforcement learning with Transformer-based load forecasting to simultaneously reduce energy costs and equivalent CO2 emissions, offering a valuable contribution to the path toward a net-zero industry
Method to analyze driving dynamics during faults in the electric drivetrain on a vehicle-in-the-loop test bench
No full textThe mechanical components of drive systems for electric vehicles are less complex than those of conventional drives and are therefore generally less prone to faults. On the other hand, a challenge lies in the relatively limited experience in dealing with faults in the electric drivetrain and their effects on driving dynamics compared to conventional drives.
To meet these challenges, this paper presents a method to simulate faults in the electric powertrain of a real demonstrator vehicle on a full vehicle test bench and to evaluate the influence on driving dynamics. For this purpose, the demonstrator vehicle was modeled in detail in a co-simulation between the driving dynamics simulation software CarMaker and the real-time solution for simulating and testing electrical components Typhoon HIL. This enabled the investigation of the vehicle’s behavior in the event of a fault. Subsequently, tests with the vehicle were performed on the Vehicle-in-the-Loop full vehicle test bench and the behavior of the vehicle in the event of a fault was reproduced.
The results of this approach show the transferability from simulation to reality and that the drivability of vehicles in the event of a fault can be investigated on the test bench. In addition, it is shown that even in the event of a fault the demonstrator vehicle used does not get into any critical driving situations and therefore remains drivable
Emotionen und Macht im Kontext von Teilhabeprozessen in der Kinder- und Jugendhilfe
No full textIn der Frage nach Hindernissen und Gelingensbedingungen von Beteiligungsprozessen in Kinder- und Jugendhilfediensten findet die Rolle von Emotionen und Macht nur selten eine explizite Berücksichtigung. Dies gilt insbesondere für einen systematischen Blick auf die Perspektive von Nutzer*innen. Über die Analyse von Interviews und Workshops mit Jugendlichen in Österreich argumentiert der Beitrag, dass strukturell erzeugte emotionale Teilhabebarrieren partizipative Bestrebungen erschweren oder verhindern. In direkten Interaktionen mit den Fachkräften zeigt sich ein über unterschiedliche Machtmechanismen hergestelltes Abhängigkeitsfeld, in dem vertrauensvolle oder angstbesetzte Beziehungen als teilhabefördernde oder -blockierende Praktiken auftreten. In stärker organisationalen Zusammenhängen werden vor allem eine fehlende Zugänglichkeit und zu starke Formalisierung als systemische Probleme deutlich gemacht. Beispiele von schriftlichen Anfragen, Fallakten und Haussitzungen illustrieren, wie ein enger Partizipationsrahmen und ein normativ gesetztes Expert*innen-Wissen als emotionale Hemmschwellen wirksam werden und Frustrations‑, Enttäuschungs- oder Resignationserscheinungen evozieren. Auf dieser Basis skizziert der Artikel abschließend einige Möglichkeiten und Vorschläge, diese Hindernisse im Sinne einer responsiven Kinder- und Jugendhilfe abzubauen
E-textiles through a combination of laser-induced forward transfer and electroless copper deposition
No full textElectronic textiles (e-textiles) offer promising capabilities in communication, energy storage, safety, comfort, and sensing. A key requirement for e-textiles is the development of conductive patterns with high design flexibility, high electrical conductivity, and strong adhesion to the textile substrates. In this study, a simple approach combining laser-induced forward transfer (LIFT) and electroless copper (Cu) deposition to create high-resolution, highly conductive patterns on textiles is presented. LIFT is used to deposit microsized silver (Ag) seeds onto textiles, offering significant design flexibility for conductive patterns due to the precise control provided by the automated laser system. The silver seeds act as catalysts for subsequent electroless Cu deposition, leading to localized continuous copper tracks with high conductivity. An appropriate spatial distribution of the Ag particles is essential for achieving uniform copper deposition. This was attained through an appropriate design of the donor for the LIFT process. To enhance the adhesion of the Cu coating to the textile, a siloxane-based intermediate layer was introduced between the textile and silver seeds, which significantly improved the adhesion of the copper deposits. As a proof of concept, the methodology was employed for the preparation of inductive antennas on textiles. The combination of LIFT and electroless deposition demonstrates an effective approach for the production of e-textiles