Especially in manufacturing systems with small batches or customized products, as well as in remanufacturing and recycling facilities, there is a wide variety of part types that may be previously unseen. It is crucial to accurately identify these parts based on their type for traceability or sorting purposes. One approach that has shown promising results for this task is deep learning–based image classification, which can classify a part based on its visual appearance in camera images. However, this approach relies on large labeled datasets of real-world images, which can be challenging to obtain, especially for parts manufactured for the first time or whose appearance is unknown. To overcome this challenge, we propose generating highly realistic synthetic images based on photo-realistically rendered computer-aided design (CAD) data. Using this commonly available source, we aim to reduce the manual effort required for data generation and preparation and improve the classification performance of deep learning models using transfer learning. In this approach, we demonstrate the creation of a parametric rendering pipeline and show how it can be used to train models for a 30-class classification problem with typical engineering parts in an industrial use case. We also demonstrate how our method’s entropy gain improves the classification performance in various deep image classification models.
Bei der Ermittlung von Vorgangsfolgen innerhalb der Arbeitsplanung wird auf Erfahrungswissen von Fachkräften und weitere Hilfsmittel wie Unterlagen, Richtlinien und Arbeitspläne ähnlicher Produkte zurückgegriffen. Demzufolge enthalten erstellte Arbeitspläne implizites Wissen, dessen Extraktion und Nutzung das Potenzial zur Beschleunigung der Vorgangsfolgeermittlung bietet. Für derartige Aufgaben können künstliche neuronale Netze des Deep Learning eingesetzt werden, die durch Training das implizite Wissen erfassen und über Vorhersagen nutzbar machen. Daher wird in diesem Beitrag ein Konzept für die Ermittlung von Vorgangsfolgen durch künstliche neuronale Netze vorgestellt.
Neural Radiance Fields (NeRF) bieten eine kostengünstige und effiziente Alternative im Vergleich zu herkömmlichen Verfahren, um 3D-Modelle aus realen Objekten zu generieren. Dementsprechend bieten NeRF große Potenziale zur Nutzung in diversen Anwendungsfällen, wie der Fabrikplanung. In diesem Beitrag wird die NeRF-Technologie an einem Beispiel aus der Fabrikplanung angewendet und daran aktuelle Herausforderungen sowie Möglichkeiten zur Nutzung der Technologie diskutiert.
Campared to conventional methods, Neural Radiance Fields (NeRF) offer a cost-effective and efficient alternative for generating 3D models from real objects. Therefore, NeRF has great potential for use in diverse applications, such as factory planning. Accordingly, this paper applies the NeRF technology to an exemple use case from factory planning and discusses current challenges and possibilities for using the technology.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.