Open Access Zeitschriften des Universitätsverlages der Technischen Universität Chemnitz
Not a member yet
466 research outputs found
Sort by
Vision-based Propeller Damage Inspection Using Machine Learning
Get PDFUnmanned Aerial Vehicles (UAVs) play an increasingly pivotal role in day-to-day rescue operations, offering crucial aerial support in challenging terrain and emergencies, such as drowning. Drone hangars are strategically deployed to ensure swift response in remote locations, overcoming range-limiting constraints posed by battery capacity. However, the UAV\u27s airworthiness, typically ensured through conventional inspections by a technical individual, is paramount to guarantee mission safety. Over time, UAVs are prone to degradation through contact with the external environment, with propellers often being the cause of flight instability and potential crashes. This paper presents an innovative approach to automate UAV propeller inspection to avert incidents preemptively. Leveraging visual recordings and deep learning methodologies, we train a Convolutional Neural Network (CNN) model using both passive and active learning strategies. Our approach successfully detects physical damage on propellers with an impressive accuracy of 85.8%, promising a significant improvement in maintaining UAV flight safety and effectiveness in rescue operations
Reliability Supporting of Relay Protection for 110kV Transmission Line with High-load and Short-distance in a Ring Network
Get PDFAs part of its mandate to meet the increasing electricity demands of Ulaanbaatar while ensuring uninterrupted, reliable, and high-quality energy supply, the National Power Transmission Grid (NPTG) takes on the responsibility of expanding, revamping, and maintaining power transmission infrastructure, including lines, substations, and equipment. In order to enhance overall reliability, this expansion necessitates seamless integration of old and new systems. Implementing advanced technical solutions becomes imperative in order to meet these challenges. The city center, newly developed residential areas, and major consumers have been strategically located in close proximity to new transmission and distribution substations. As a result of 110 kV high-load circuit networks connecting these substations, a critical issue relates to the selectivity of short-distance lines. A relay protection solution has been explored for 110 kV high-load short-distance lines in this research, and its impact on the dynamic stability of the power system has been evaluated
Leader-Follower Control and Distributed Communication based UAV Swarm Navigation in GPS-Denied Environment
Get PDFUnmanned Aerial Vehicles (UAVs) have developed rapidly in recent years due to technological advances and UAV technology finds applications in a wide range of fields, including surveillance, search and rescue, and agriculture. The utilization of UAV swarms in these contexts offers numerous advantages, increasing their value across different industries. These advantages include increased efficiency in tasks, enhanced productivity, greater safety, and the higher data quality. The coordination of UAVs becomes particularly crucial during missions in these applications, especially when drones are flying in close proximity as part of a swarm. For instance, if a drone swarm is targeted or needs to navigate through a Global Positioning System (GPS)-denied environment, it may encounter challenges in obtaining the location information typically provided by GPS. This poses a new challenge for the UAV swarms to maintain a reliable formation and successfully complete a given mission. In this article, our objective is to minimize the number of sensors required on each UAV and reduce the amount of information exchanged between UAVs. This approach aims to ensure the reliable maintenance of UAV formations with minimal communication requirements among UAVs while they follow predetermined trajectories during swarm missions. In this paper, we introduce a concept that utilizes extended Kalman filter, leader-follower-based control and a distributed data-sharing scheme to ensure the reliable and safe maintenance of formations and navigation autonomously for UAV swarm missions in GPS-denied environments. The formation control approaches and control strategies for UAV swarms are also discussed
Leuchtendes Löffeln in Leipzig. Design als kulturelle Praxis im öffentlichen Raum
Get PDFZusammenfassung. Der vorliegende Beitrag diskutiert die gesellschaftliche Funktion von Design als öffentlicher wahrnehmbarer Zeichenpraxis und verdeutlicht, inwiefern Designobjekte ihre Funktion und Bedeutung durch Handlungs- und Diskurskontexte erhalten. Ihre Zeichenhaftigkeit wird hierdurch von einer vermeintlichen Deutungsoffenheit auf konkrete Bedeutungspotenziale reduziert. Kulturelle und soziale Kontexte schaffen im interpretativen Zusammenspiel mit Materie, Farbe und Form Identität, die sich auf der Ausdrucksebene in Form von Stil darstellt. Stil stellt sich somit im schöpferischen Akt durch Stil-Praktiken her, die sich als Auswahl, Formung und Komposition von semiotischen Ressourcen bestimmen lassen. Exemplarisch verdeutlicht werden diese Praktiken anhand einer aus den 1970er Jahren stammenden, unter Denkmalschutz stehenden Leuchtreklame, der sogenannten „Leipziger Löffelfamilie“.Summary. The present contribution aims at discussing the social function of design as a sign practice intended for public perception. It argues that design objects construct identity depending on an interplay between cultural and social contexts, materiality, color, and form. These are semiotic resources which express style. Style can be considered as a creative act through style practices, which emerge from the selection, formation, and composition of semiotic resources. These practices are exemplified with reference to an illuminated advertising, the so-called “Leipziger Löffelfamilie”. It was constructed in the GDR in the 1970s and has gained the status as a protected monument
Intelligent Detection of Road Cracks Based on Improved YOLOv5
Get PDFWith the gradual increase of highway coverage, the frequency of road cracks also increases, which brings a series of security risks. It is necessary to detect road cracks, but the traditional detection method is inefficient and unsafe. In this paper, deep learning is used to detect road cracks, and an improved model BiTrans-YOLOv5 is proposed. We add Swin Transformer to YOLOv5s to replace the original C3 module, and explore the performance of Transformer in the field of road crack detection. We also change the original PANet of YOLOv5s into a bidirectional feature pyramid network (BIFPN), which can detect small targets more accurately. Experiments on the data set Road Damage show that BiTrans-YOLOv5 has improved in Precision, Recall, F1 score and [email protected] compared with YOLOv5s, among which [email protected] has improved by 5.4%. It is proved that BiTrans-YOLOv5 has better performance in road detection projects
Fruit Classification Based on Improved YOLOv7 Algorithm
Get PDFWith the rapid development of technology and advancements, unmanned vending machines have emerged as the primary contactless retail method. The efficient and accurate implementation of automated identification technology for agricultural products in their distribution and sales has become an urgent problem that needs to be addressed. This article presents an improved YOLOv7 (You Only Look Once) algorithm for fruit detection in complex environments. By replacing the 3×3 convolutions in the backbone of YOLOv7 with Deformable ConvNet v2(DCNv2), the recognition accuracy and efficiency of fruit classification in YOLOv7 are significantly enhanced. The results indicate that the overall recognition accuracy of this system for ten types of fruits is 98.3%, showcasing its high precision and stability
Was heißt „Vorhandensein“? Die kulturwissenschaftliche Relevanz einer Klärung
Get PDFZusammenfassung. Dieser Beitrag baut auf der Idee auf, Wahrmacher in eine Wahrheitsbedingungen-Semantik zu integrieren. Speziell geht er der Frage nach, Wahrheitsbedingungen welcher Art für Aussagen in Frage kommen, die einer Sache Vorhandensein – im Unterschied dazu, bloßes intentionales Objekt zu sein – zuschreiben. Die adverbiale Theorie der Wahrnehmung behandelt Erleben, zum Beispiel Erscheinungen (visuelles Erleben), als ‚adverbial‘ klassifizierbar. Als weiterer Ansatz zur Charakterisierung des Verhältnisses einer Erscheinung (visuelles Erleben) zu dem jeweils Erscheinenden wird der semantische Externalismus berücksichtigt. Auf dieser Grundlage wird Vorhandensein von y als Disposition zu y-Erleben begriffen: Dass y vorhanden ist, wird als Disposition zu solchem Erleben verstanden, das adverbial als y-Erleben charakterisiert ist. Dieser Ansatz trägt dazu bei, die verschiedenen Perspektiven der Naturwissenschaften und der Kulturwissenschaften verständlicher zu machen. Naturwissenschaften sind auf y gerichtet, während die Kulturwissenschaften vor allem y-Erleben thematisieren.Summary. This contribution builds on the idea of integrating truth-fulfilling entities into a truth-conditional semantics. It asks which kind of truth conditions are to be considered for statements of something being really there – as opposed to just being an intentional object. The adverbial theory of perception treats experiences, for example appearances (visual experiences), as ‘adverbially’ classified. As a further approach towards how an object is related to its appearance (being experienced visually), semantical externalism is considered. On this basis, it is proposed that the notion of existence can be understood as a disposition to be experienced: y being really there is explicated as a disposition to experiences that are adverbially characterized as y-experiences. This approach helps to understand the different perspectives of the natural sciences and the arts and humanities. While the natural sciences are directed towards y, the arts and humanities primarily deal with y-experiences
A Study on the Detection of Protective Helmets for the Safety of Construction Workers
Get PDFIn recent years, with the rapid development of the construction industry, the number of accidents and deaths on construction sites increased, so the prevention of accidents is one of the important issues. Worker safety during construction is a major concern of the construction industry. Wearing helmets can reduce injuries among construction workers, but helmets are not always worn and used correctly for a variety of reasons. Therefore, computer vision-based automatic helmet detection systems are very important. Although many researchers have developed machine and deep learning-based motorcycle helmet detection systems, there is little research on helmet detection for construction workers. Therefore, in this research work, an automatic system for detecting the helmets of construction workers based on real-time computer vision is presented. In this study, machine learning method is used to detect helmets, and a model is trained using 1,500 images. The test results show that the average accuracy is above 95% in laboratory conditions
Learning Styles and Cultural Differences: A comparative study of cultural differences in Austrian and Mongolian Students
Get PDFThis study shows the relationship between the types of cultural differences and learning styles of Kolb\u27s learning model. Although several cross-cultural studies on learning styles suggest that learning styles may differ from one culture to another, the question of which cultures are associated with which learning styles and abilities has been less explored. This study focuses on the empirical findings of comparative studies on past cross-cultural differences in learning styles and considers how the propositions generated by the theory tests may reflect their past empirical findings. This research shows that culture is associated with specific learning styles and abilities
Das Meer der Zeichen. Zur Lesbarkeit urbaner Räume als kollektive Gedächtnis-Texte
Get PDFZusammenfassung. Städte sind Orte einer extrem verdichteten Vielfalt unterschiedlicher, sich teilweise überlappender Zeichensysteme und lassen sich daher als Texte – Gefüge von Bedeutungen – analysieren. Durch die sinnhafte Strukturierung und Markierung durch eine oder mehrere sozio-kulturelle Gruppen wird der physische Raum zur sozialen und kulturellen Räumlichkeit. In einer geschichteten Architektur kollektiver Gedächtnisse stehen nicht selten unterschiedliche Erinnerungskulturen und -gemeinschaften miteinander in Konkurrenz. Dies lässt sich mit Hilfe einer kultursemiotischen Herangehensweise gut analysieren. Eine generelle Systematisierung einer Teildisziplin „Stadtsemiotik“ ist demgegenüber angesichts der Vielfalt unterschiedlicher Zeichensysteme im urbanen Raum weder sinnvoll möglich, noch für empirische Untersuchungen notwendig.Summary. Cities are spaces that are characterized by many different sign-systems which partly overlap; they can be analyzed as complex textures of meanings. Physical space is turned into social and cultural space when different socio-cultural communities structure and mark it. In a layered architecture of collective memories different milieus and communities of commemoration coexist. This can be analyzed with semiotic tools, while a generalizing system of “city-semiotics” seems to be neither possible – because of the multiplicity of diverse sign-systems in the urban space – nor necessary for an empirical approach