FG Automatisierungstechnik
Refine
Year of publication
Document Type
- Conference Proceeding (106)
- Part of a book (chapter) (21)
- Scientific journal article peer-reviewed (19)
- Conference publication peer-reviewed (18)
- Doctoral thesis (15)
- Article (11)
- Scientific journal article not peer-reviewed (4)
- Book (1)
- Book (publisher) (1)
- Conference publication not peer-reviewed (1)
Way of publication
- Open Access (3)
Keywords
- Human-Robot-Collaboration (3)
- SME (3)
- Industry 4.0 (2)
- Lebenszyklus (2)
- Robot Farming (2)
- milling (2)
- Asset-to-Go (1)
- Augmented reality (1)
- Automotive (1)
- Brandenburg (1)
Institute
As Convolutional Neural Network based models become reliable and efficient, two questions arise in relation to their applications for industrial purposes. The usefulness of these models in industrial environments and their implementation in these settings. This paper describes the autonomous generation of Region based CNN models trained on images from rendered CAD models and examines their applicability and performance for part handling application. The development of the automated synthetic data generation is detailed and two CNN models are trained with the aim to detect a car component and differentiate it against another similar looking part. The performance of these models is tested on real images and it was found that the proposed approach can be easily adopted for detecting a range of parts in arbitrary backgrounds. Moreover, the use of syntheic images for training CNNs automates the process of generating a detector.
Industry 4.0 is still in its development phase and it promises to bring remarkable benefits to the manufacturing industry around the world when employing the Smart Factory application in large organizations and their supply chains. However, there is a risk of a miss-match when trying to introduce Industry 4.0 to Small and Medium Enterprises (SME) as the concept is mainly being developed around large manufacturing companies. The purpose of this research is to analyze the readiness level and feasibility of implementing Industry 4.0 technologies for SME’s in the federal state of Brandenburg (Germany). The work is based on the survey of 20 SME’s assessing their current problems emphasizing on automation, Enterprise Resource Planning (ERP), CAD/CAM, factory layout planning and logistics. Five SME’s from different domains out of the 20 surveyed are taken as case studies to evaluate the potential benefits, trade-offs and barriers from an implementation of these integrated technologies. The findings revealed that the companies are still coping with the issues relating to planning, logistics and automation. It was also found that all the concepts of i4.0 may not be necessary or even beneficial to an enterprise in the current scenario and new strategies need to be developed for its realization in SME’s.
Feature selection (FS) represents an essential step for many machine learning-based predictive maintenance (PdM) applications, including various industrial processes, components, and monitoring tasks. The selected features not only serve as inputs to the learning models but also can influence further decisions and analysis, e.g., sensor selection and understandability of the PdM system. Hence, before deploying the PdM system, it is crucial to examine the reproducibility and robustness of the selected features under variations in the input data. This is particularly critical for real-world datasets with a low sample-to-dimension ratio (SDR). However, to the best of our knowledge, stability of the FS methods under data variations has not been considered yet in the field of PdM. This paper addresses this issue with an application to tool condition monitoring in milling, where classifiers based on support vector machines and random forest were employed. We used a five-fold cross-validation to evaluate three popular filter-based FS methods, namely Fisher score, minimum redundancy maximum relevance (mRMR), and ReliefF, in terms of both stability and macro-F1. Further, for each method, we investigated the impact of the homogeneous FS ensemble on both performance indicators. To gain broad insights, we used four (2:2) milling datasets obtained from our experiments and NASA’s repository, which differ in the operating conditions, sensors, SDR, number of classes, etc. For each dataset, the study was conducted for two individual sensors and their fusion. Among the conclusions: (1) Different FS methods can yield comparable macro-F1 yet considerably different FS stability values. (2) Fisher score (single and/or ensemble) is superior in most of the cases. (3) mRMR’s stability is overall the lowest, the most variable over different settings (e.g., sensor(s), subset cardinality), and the one that benefits the most from the ensemble.
Die in diesem Artikel beschriebene, praktische, Verwendung einer Augmented Reality Umgebung findet statt für die Fehlerbeseitigung und Fehlerkorrektur bei der Arbeit in einer Laboranlage, die verschiedene Fehler simuliert kann. Innerhalb der Anlage sind alle wesentlichen Komponenten mit Sensorik ausgestattet, so dass jederzeit Informationen über
den Zustand des Systems in Echtzeit bereitliegen. Sobald sich einen Fehler innerhalb der Anlage befindet, kann das Steuerungssystem durch die vorliegenden Sensordaten dieses
Problem identifizieren. Die verschiedenen Teile der Anlage sind mit Positions-Markern zur Identifizierung eines
Anlagenbereiches ausgerüstet. Wird die Anlage durch einen Fehler gestoppt ist, muss der Mitarbeiter die Anlage mit Hilfe des Kamerasystems eines mobilen Endgerätes (mit dem
Tablet) erfassen. Die erfassten Daten aus diesem Scan werden mit Hilfe der Software verarbeitet. Durch die visuelle Rückmeldung (z.B., auf dem Tablet) erhält der Anwender die Information über den aufgetretenen Fehler innerhalb der Anlage und zur Behebung des Zustandes. Auf
Grundlager der erkannten Marker können positionsgenau Objekte eingeblendet werden die dem Anwender den Ort des Fehlers anzeigen und Hinweise zur Bedienerführung zur
Aufnahme des ordnungsgemäßen Betriebs der Anlage geben. Der Anlagenführer wird in die Lage versetzt, die Fehlerbeseitigung und Fehlerkorrektur schnell und erfolgreich zu realisieren. Ein Einsatz des Systems für Schulungsprozesse ist vorgesehen, da sich dies
positiv auf die Verringerung von Stillstandszeiten auswirkt. So demonstriert das beschriebene, realisierte Verfahren wie die praktische Verwendung der
AR zur Reduzierung des zeitlichen Aufwandes für die Fehlerbeseitigung und die Fehlerkorrektur der Maschinenumgebung bei der Mensch-Maschinen-Integration in Industrie 4.0 Umgebungen beiträgt und den gesamten Integrationsprozess zwischen Mensch und Maschine vertiefet.
In this paper the use of a mobile lightweight robot is evaluated to perform an assembly task while simultaneously moving. The motion of the mobile platform results into a variable end effector position in space. The paper assesses
the existing method of placing a screw in an assembly where the location of placement is variable due to end effector movement. Experiments have been conducted to evaluate the task performance by monitoring the applied force on the
end effector, the position data and the task time. The results show that with impedance configuration, a moveable compliant robot is a possible solution for use in assembly operation.
This paper presents a novel approach for automated smart factory based on the ideas of Internet of Things (IoT) and the usage of mobile technology of the german „Industry 4.0“ [6]. IoT enables the achievement of greater value and service by exchanging data between different devices and the manufacturer. The data collected from all devices will be exchanged via wireless networks. Mobile technology can be used to cover non value-added processes [3] i.e. transportation in the manufacturing. By combining transportation tasks and value adding production steps, waste of production time, cost and effort can be reduced. This paper presents the first step toward this approach [7]: the mobile robot moves alongside the moving object and executes the manufacturing tasks during its transportation. For the demonstration of the developed solution a mobile
platform and an optical measurement system was used. The synchronization between the mobile platform and the object will be experimentally tested. Consequently the results will demonstrate how the mobile robot is able to follow the moving object.
This paper focuses on the systematic methodology for
incorporating intelligence and development methodology for
knowledge acquisition system in an automated manufacturing
environment. The intelligence is incorporated in the shape of
technology data catalogue that contains the knowledge about
production system as a whole. The knowledge acquisition system is
implemented in the form of a multiuser scalable interface into remote
human machine interface devices (e.g. Personal Digital Assistants)
with a purpose of extracting concrete and precise information and
knowledge about manufacturing systems and processes in highly
automated manufacturing environment. The extraction of precise
knowledge as well as organized access to the knowledge will
facilitates the operators, technicians and engineers for making faster,
safer and simpler on-process modifications and parameters
optimization.
Intelligente Assistenzsysteme unterstützen die Mitarbeiter in der Produktion und erhöhen die Effizienz durch das Einblenden von situationsbasierten Aufgabeninformationen. Im Projekt Advanced Robot Assistance Solution (ARAS) im Rahmen des Kuka Innovation Awards 2021 wurde eine Assistenztechnologie entwickelt, um automatisiert Roboterprogramme für Montageabläufe zu generieren. Durch innovative Mensch-Maschine-Schnittstellen werden Montageschritte per maschinellem Lernen erkannt und in ausführbare Programme für Industrieroboter übersetzt. Dadurch können roboterbasierte Montageprozesse innerhalb von Minuten auf neue Produkte angepasst werden, ohne dass die Mitarbeiter über Kenntnisse des Programmierens oder der Robotik verfügen müssen. Ein Mitarbeiter muss den Montageprozess nur einmal vormachen. Das ARAS-System ermöglicht die kosten- und zeiteffiziente Integration und Adaption von Industrierobotern in der Montage für große und mittelständische Unternehmen.
This chapter will introduce the second part of the book. This part contains a collection of chapters aimed at supporting the SMEs in the transformation toward the Smart Production vision. In this part, different approaches are presented, which can assist SMEs in the formulation of a smart production vision and in the identification and prioritization of relevant initiatives, guiding the outline of a project roadmap. Furthermore, the part will introduce different regional innovation platforms in Denmark and Germany which support the SME transformations. Finally, it will be discussed how subscription-based methods could be used by SMEs to cut upfront investments and reduce requirements for digital competencies.
Produktionswissenschaft sowie Technologie- und Innovationsforschung sind sehr dynamische Gebiete. Sie setzen sich mit den Forderungen nach robusten und wandlungsfähigen Produktionssystemen sowie innovativen Technologien auseinander, schaffen theoretische Modelle und praxistaugliche Instrumente zur Entscheidungsunterstützung in einem dynamischen, internationalen und zunehmend vernetzten Umfeld. Das Buch beinhaltet Beiträge namhafter Autoren, gibt einen Überblick zum aktuellen Forschungsstand und würdigt als Festschrift für Professor Dieter Specht dessen interdisziplinär angelegtes wissenschaftliches Wirken. Der Band versammelt unter anderen Beiträge von Daniel Baier, Klaus Bellmann, Ulrich Berger, Udo Buscher, Jörg M. Elsenbach, Wolf Fichtner, Joachim Fischer, Jürgen Gausemeier, Georg Gemünden, Torsten J. Gerpott, Horst Geschka, Uwe Götze, Diana Grosse, Andreas Größler, Evi Hartmann, Hans H. Hinterhuber, Christopher Jahns, Bernd Kaluza, Joachim Käschel, Wolfgang Kersten, Klaus-Peter Kistner, Bernd Kortschak, Herbert Kotzab, Rudolf O. Large, Peter Lethmathe, Peter Loos, Horst Meier, Barbara Mikus, Peter Milling, Magdalena Mißler-Behr, Martin G. Möhrle, Theodor Nebl, Joachim Reese, Bernd Rieper, Gerhard Schewe, Hans-Horst Schröder, Günther Seliger, Marion Steven, Oliver Thomas, Meike Tilebein, Bernd Viehweger, Kai-Ingo Voigt, Marion A. Weissenberger-Eibl, Horst Wildemann, Herwig Winkler, Stephan Zelewski.
In addition to the already required functionality, future production systems should consider the requirements of flexible and demand-oriented resource utilization. Those are not only related on fields of energy, but also material-efficient and time-efficient use of available means of production. Modular system architectures and modular solutions facilitate the planning and implementation of these requirements. Using service-oriented architectures in automation allow an approach for new or modified system components that can be integrated in the available plant environment without a high additional investment of project engineering. This aspect is interesting for companies with manageable machinery, which are able to react immediately and flexible to changes. Service-oriented solutions include among other things the identification, classification and synchronization of possible services. The paper will show general prerequisites for an implementation of a service-oriented architecture in a module-based test field.