Refine
Year of publication
- 2021 (74) (remove)
Document Type
- Article (reviewed) (74) (remove)
Is part of the Bibliography
- yes (74) (remove)
Keywords
- Corporate Governance (3)
- Blockchain (2)
- Götz von Berlichingen (2)
- Handprothese (2)
- Predictive maintenance (2)
- Surface acoustic waves (2)
- 3D CAD (1)
- 3D computer-aided design (1)
- 3D print (1)
- 3D printed (1)
Institute
- Fakultät Elektrotechnik, Medizintechnik und Informatik (EMI) (ab 04/2019) (31)
- Fakultät Maschinenbau und Verfahrenstechnik (M+V) (28)
- POIM - Peter Osypka Institute of Medical Engineering (12)
- Fakultät Wirtschaft (W) (11)
- INES - Institut für nachhaltige Energiesysteme (9)
- ivESK - Institut für verlässliche Embedded Systems und Kommunikationselektronik (7)
- Fakultät Medien (M) (ab 22.04.2021) (4)
- ACI - Affective and Cognitive Institute (2)
- WLRI - Work-Life Robotics Institute (2)
- Zentrale Einrichtungen (2)
Open Access
- Open Access (44)
- Closed Access (30)
It is important to minimize the unscheduled downtime of machines caused by outages of machine components in highly automated production lines. Considering machine tools such as, grinding machines, the bearing inside of spindles is one of the most critical components. In the last decade, research has increasingly focused on fault detection of bearings. In addition, the rise of machine learning concepts has also intensified interest in this area. However, up to date, there is no single one-fits-all solution for predictive maintenance of bearings. Most research so far has only looked at individual bearing types at a time.
This paper gives an overview of the most important approaches for bearing-fault analysis in grinding machines. There are two main parts of the analysis presented in this paper. The first part presents the classification of bearing faults, which includes the detection of unhealthy conditions, the position of the error (e.g. at the inner or at the outer ring of the bearing) and the severity, which detects the size of the fault. The second part presents the prediction of remaining useful life, which is important for estimating the productive use of a component before a potential failure, optimizing the replacement costs and minimizing downtime.
In the last decade, deep learning models for condition monitoring of mechanical systems increasingly gained importance. Most of the previous works use data of the same domain (e.g., bearing type) or of a large amount of (labeled) samples. This approach is not valid for many real-world scenarios from industrial use-cases where only a small amount of data, often unlabeled, is available.
In this paper, we propose, evaluate, and compare a novel technique based on an intermediate domain, which creates a new representation of the features in the data and abstracts the defects of rotating elements such as bearings. The results based on an intermediate domain related to characteristic frequencies show an improved accuracy of up to 32 % on small labeled datasets compared to the current state-of-the-art in the time-frequency domain.
Furthermore, a Convolutional Neural Network (CNN) architecture is proposed for transfer learning. We also propose and evaluate a new approach for transfer learning, which we call Layered Maximum Mean Discrepancy (LMMD). This approach is based on the Maximum Mean Discrepancy (MMD) but extends it by considering the special characteristics of the proposed intermediate domain. The presented approach outperforms the traditional combination of Hilbert–Huang Transform (HHT) and S-Transform with MMD on all datasets for unsupervised as well as for semi-supervised learning. In most of our test cases, it also outperforms other state-of-the-art techniques.
This approach is capable of using different types of bearings in the source and target domain under a wide variation of the rotation speed.
In recent years, physically unclonable functions (PUFs) have gained significant attraction in IoT security applications, such as cryptographic key generation and entity authentication. PUFs extract the uncontrollable production characteristics of different devices to generate unique fingerprints for security applications. When generating PUF-based secret keys, the reliability and entropy of the keys are vital factors. This study proposes a novel method for generating PUF-based keys from a set of measurements. Firstly, it formulates the group-based key generation problem as an optimization problem and solves it using integer linear programming (ILP), which guarantees finding the optimum solution. Then, a novel scheme for the extraction of keys from groups is proposed, which we call positioning syndrome coding (PSC). The use of ILP as well as the introduction of PSC facilitates the generation of high-entropy keys with low error correction costs. These new methods have been tested by applying them on the output of a capacitor network PUF. The results confirm the application of ILP and PSC in generating high-quality keys.
This article presents a study of cultural differences affecting the acceptance and design preferences of social robots. Based on a survey with 794 participants from Germany and the three Arab countries of Egypt, Jordan, and Saudi Arabia, we discuss how culture influences the preferences for certain attributes. We look at social roles, abilities and appearance, emotional awareness and interactivity of social robots, as well as the attitude toward automation. Preferences were found to differ not only across cultures, but also within countries with similar cultural backgrounds. Our findings also show a nuanced picture of the impact of previously identified culturally variable factors, such as attitudes toward traditions and innovations. While the participants’ perspectives toward traditions and innovations varied, these factors did not fully account for the cultural variations in their perceptions of social robots. In conclusion, we believe that more real-life practices emerging from the situated use of robots should be investigated. Besides focusing on the impact of broader cultural values such as those associated with religion and traditions, future studies should examine how users interact, or avoid interaction, with robots within specific contexts of use.
Mit zunehmender Datenverfügbarkeit wird der Einsatz Maschinellen Lernens zur Steuerung und Optimierung von Supply Chains attraktiver, da die Qualität der Datenauswertung erhöht und gleichzeitig der Aufwand gesenkt werden kann. Anhand des SCOR-Modells werden exemplarische Ansätze als Orientierungshilfe eingeordnet und dazu passende Verfahren des Maschinellen Lernens vorgestellt.
IoT-Plattformen stellen ein zentrales Element für die Vernetzung von physischen Objekten und die Bereitstellung deren Daten für digitale Zwillinge dar. Der Markt für solche Plattformen ist in den vergangenen Jahren stark gewachsen. Bei inzwischen über 600 Anbietern ist die Wahl der „richtigen“ Plattform für das eigene Unternehmen keine triviale Aufgabe mehr. Dieser Beitrag soll Unternehmen im Auswahlprozess unterstützen, indem gängige Funktionen von IoT-Plattformen und Kriterien für die Auswahl von IoT-Plattformen aufgezeigt werden.
Evaluation of Deep Learning-Based Neural Network Methods for Cloud Detection and Segmentation
(2021)
This paper presents a systematic approach for accurate short-time cloud coverage prediction based on a machine learning (ML) approach. Based on a newly built omnidirectional ground-based sky camera system, local training and evaluation data sets were created. These were used to train several state-of-the-art deep neural networks for object detection and segmentation. For this purpose, the camera-generated a full hemispherical image every 30 min over two months in daylight conditions with a fish-eye lens. From this data set, a subset of images was selected for training and evaluation according to various criteria. Deep neural networks, based on the two-stage R-CNN architecture, were trained and compared with a U-net segmentation approach implemented by CloudSegNet. All chosen deep networks were then evaluated and compared according to the local situation.
Wood juice, a liquid produced during wood processing, is a harmful waste that requires utilization. To achieve a circular economy, biowastes should be recycled, reducing fossil carbon usage. Therefore, the objective of this work was to examine the potential of wood juice as a feedstock for bioplastic synthesis by Bacillus sp. G8_19. Polyhydroxyalkanoate (PHA) syntheses using wood juice from Douglas fir trees and that from a mixture of spruce/fir trees were compared. It was found that the PHA content was higher after using wood juice from spruce/fir trees than that from Douglas fir trees (18.0% vs 6.1% of cell dry mass). Gas chromatography analysis showed that, with both wood juices, Bacillus sp. G8_19 accumulated poly(3-hydroxybutyrate-co-3-hydroxyvalerate). The content of 3-hydroxyvalerate (3HV) monomers was higher when spruce/fir wood juice was used (10.7% vs 1.9%). The C/N ratio did not have a statistically significant effect on the copolymer content in biomass, but it did significantly influence the 3HV content. The proposed concept may serve as an approach to wood waste valorization via production of biodegradable materials.
Human–robot collaborative applications have been receiving increasing attention in industrial applications. The efficiency of the applications is often quite low compared to traditional robotic applications without human interaction. Especially for applications that use speed and separation monitoring, there is potential to increase the efficiency with a cost-effective and easy to implement method. In this paper, we proposed to add human–machine differentiation to the speed and separation monitoring in human–robot collaborative applications. The formula for the protective separation distance was extended with a variable for the kind of object that approaches the robot. Different sensors for differentiation of human and non-human objects are presented. Thermal cameras are used to take measurements in a proof of concept. Through differentiation of human and non-human objects, it is possible to decrease the protective separation distance between the robot and the object and therefore increase the overall efficiency of the collaborative application.
A Review on Kinetic Energy Harvesting with Focus on 3D Printed Electromagnetic Vibration Harvesters
(2021)
The increasing amount of Internet of Things (IoT) devices and wearables require a reliable energy source. Energy harvesting can power these devices without changing batteries. Three-dimensional printing allows us to manufacture tailored harvesting devices in an easy and fast way. This paper presents the development of hybrid and non-hybrid 3D printed electromagnetic vibration energy harvesters. Various harvesting approaches, their utilised geometry, functional principle, power output and the applied printing processes are shown. The gathered harvesters are analysed, challenges examined and research gaps in the field identified. The advantages and challenges of 3D printing harvesters are discussed. Reported applications and strategies to improve the performance of printed harvesting devices are presented.