TY - JOUR A1 - Khayyam, Hamid A1 - Jamali, Ali A1 - Bab-Hadiashar, Alireza A1 - Esch, Thomas A1 - Ramakrishna, Seeram A1 - Jalil, Mahdi A1 - Naebe, Minoo T1 - A Novel Hybrid Machine Learning Algorithm for Limited and Big Data Modelling with Application in Industry 4.0 JF - IEEE Access N2 - To meet the challenges of manufacturing smart products, the manufacturing plants have been radically changed to become smart factories underpinned by industry 4.0 technologies. The transformation is assisted by employment of machine learning techniques that can deal with modeling both big or limited data. This manuscript reviews these concepts and present a case study that demonstrates the use of a novel intelligent hybrid algorithms for Industry 4.0 applications with limited data. In particular, an intelligent algorithm is proposed for robust data modeling of nonlinear systems based on input-output data. In our approach, a novel hybrid data-driven combining the Group-Method of Data-Handling and Singular-Value Decomposition is adapted to find an offline deterministic model combined with Pareto multi-objective optimization to overcome the overfitting issue. An Unscented-Kalman-Filter is also incorporated to update the coefficient of the deterministic model and increase its robustness against data uncertainties. The effectiveness of the proposed method is examined on a set of real industrial measurements. Y1 - 2020 SN - 2169-3536 U6 - https://doi.org/10.1109/ACCESS.2020.2999898 SP - 1 EP - 12 PB - IEEE CY - New York, NY ER - TY - CHAP A1 - Nikolovski, Gjorgji A1 - Reke, Michael A1 - Elsen, Ingo A1 - Schiffer, Stefan T1 - Machine learning based 3D object detection for navigation in unstructured environments T2 - 2021 IEEE Intelligent Vehicles Symposium Workshops (IV Workshops) N2 - In this paper we investigate the use of deep neural networks for 3D object detection in uncommon, unstructured environments such as in an open-pit mine. While neural nets are frequently used for object detection in regular autonomous driving applications, more unusual driving scenarios aside street traffic pose additional challenges. For one, the collection of appropriate data sets to train the networks is an issue. For another, testing the performance of trained networks often requires tailored integration with the particular domain as well. While there exist different solutions for these problems in regular autonomous driving, there are only very few approaches that work for special domains just as well. We address both the challenges above in this work. First, we discuss two possible ways of acquiring data for training and evaluation. That is, we evaluate a semi-automated annotation of recorded LIDAR data and we examine synthetic data generation. Using these datasets we train and test different deep neural network for the task of object detection. Second, we propose a possible integration of a ROS2 detector module for an autonomous driving platform. Finally, we present the performance of three state-of-the-art deep neural networks in the domain of 3D object detection on a synthetic dataset and a smaller one containing a characteristic object from an open-pit mine. KW - 3D object detection KW - LiDAR KW - autonomous driving KW - Deep learning KW - Three-dimensional displays Y1 - 2021 SN - 978-1-6654-7921-9 U6 - https://doi.org/10.1109/IVWorkshops54471.2021.9669218 N1 - 2021 IEEE Intelligent Vehicles Symposium Workshops (IV Workshops), 11-17 July 2021, Nagoya, Japan. SP - 236 EP - 242 PB - IEEE ER - TY - CHAP A1 - Fiedler, Gerda A1 - Gottschlich-Müller, Birgit A1 - Melcher, Karin ED - Liu-Henke, Xiaobo ED - Durak, Umut T1 - Online-Prüfungen mit STACK Aufgaben T2 - Tagungsband ASIM Workshop STS/GMMS/EDU 2021 N2 - Wir stellen hier exemplarisch STACK Aufgaben vor, die frei von der Problematik sind, welche sich durch diverse Kommunikationswege und (webbasierte) Computer Algebra Systeme (CAS) ergibt. Daher sind sie insbesondere für eine Open-Book Online Prüfung geeignet, da eine faire Prüfungssituation gewährleistet werden kann. Y1 - 2021 SN - 978-3-901608-69-8 U6 - https://doi.org/10.11128/arep.45 N1 - Virtueller Workshop, ASIM STS/GMMS & EDU 2021, 11.-12. März 2021 SP - 173 EP - 178 PB - ARGESIM Verlag CY - Wien ER - TY - JOUR A1 - Hahn, Geogr W. A1 - Hebel, Christoph A1 - Manz, W. T1 - Die neuen Empfehlungen für Verkehrsnachfragemodellierung im Personenverkehr JF - Straßenverkehrstechnik N2 - Die neu erschienenen „Empfehlungen zum Einsatz von Verkehrsnachfragemodellen für den Personenverkehr“ liefern erstmals als Empfehlungspapier der Forschungsgesellschaft für Straßen- und Verkehrswesen einen umfassenden Überblick zu den verschiedenen Aspekten der Modellierung und geben dem Fachplaner konkrete Hilfestellung für die Konzeption von Nachfragemodellen. Das Empfehlungspapier zielt unter anderem darauf ab, die Erwartungen und das Anspruchsniveau in Hinblick auf Sachgerechtigkeit der Modelle, die erzielbare Modellqualität und den Detaillierungsgrad der Modellaussagen zu harmonisieren. Y1 - 2022 U6 - https://doi.org/10.53184/SVT10-2022-1 SN - 0039-2219 VL - 66 IS - 10 SP - 721 EP - 726 PB - Kirschbaum Verlag GmbH CY - Bonn ER - TY - JOUR A1 - Emig, J. A1 - Hebel, Christoph A1 - Schwark, A. T1 - Einsatzbereiche für Verkehrsnachfragemodelle JF - Straßenverkehrstechnik N2 - In der Praxis bestehen vielfältige Einsatzbereiche für Verkehrsnachfragemodelle. Mit ihnen können Kenngrößen des Verkehrsangebots und der Verkehrsnachfrage für den heutigen Zustand wie auch für zukünftige Zustände bereitgestellt werden, um so die Grundlagen für verkehrsplanerische Entscheidungen zu liefern. Die neuen „Empfehlungen zum Einsatz von Verkehrsnachfragemodellen für den Personenverkehr“ (EVNM-PV) (FGSV 2022) veranschaulichen anhand von typischen Planungsaufgaben, welche differenzierten Anforderungen daraus für die Modellkonzeption und -erstellung resultieren. Vor dem Hintergrund der konkreten Aufgabenstellung sowie deren spezifischer planerischer Anforderungen bildet die abzuleitende Modellspezifikation die verabredete Grundlage zwischen Auftraggeber und Modellersteller für die konkrete inhaltliche, fachliche Ausgestaltung des Verkehrsmodells. Y1 - 2022 U6 - https://doi.org/10.53184/SVT10-2022-2 SN - 0039-2219 VL - 66 IS - 10 SP - 727 EP - 736 PB - Kirschbaum Verlag GmbH CY - Bonn ER - TY - JOUR A1 - Hoeveler, B. A1 - Bauknecht, André A1 - Wolf, C. Christian A1 - Janser, Frank T1 - Wind-Tunnel Study of a Wing-Embedded Lifting Fan Remaining Open in Cruise Flight JF - Journal of Aircraft N2 - It is investigated whether a nonrotating lifting fan remaining uncovered during cruise flight, as opposed to being covered by a shutter system, can be realized with limited additional drag and loss of lift during cruise flight. A wind-tunnel study of a wing-embedded lifting fan has been conducted at the Side Wind Test Facility Göttingen of DLR, German Aerospace Center in Göttingen using force, pressure, and stereoscopic particle image velocimetry techniques. The study showed that a step on the lower side of the wing in front of the lifting fan duct increases the lift-to-drag ratio of the whole model by up to 25% for all positive angles of attack. Different sizes and inclinations of the step had limited influence on the surface pressure distribution. The data indicate that these parameters can be optimized to maximize the lift-to-drag ratio. A doubling of the curvature radius of the lifting fan duct inlet lip on the upper side of the wing affected the lift-to-drag ratio by less than 1%. The lifting fan duct inlet curvature can therefore be optimized to maximize the vertical fan thrust of the rotating lifting fan during hovering without affecting the cruise flight performance with a nonrotating fan. Y1 - 2020 U6 - https://doi.org/10.2514/1.C035422 SN - 1533-3868 VL - 57 IS - 4 PB - AIAA CY - Reston, Va. ER - TY - JOUR A1 - Khayyam, Hamid A1 - Jamali, Ali A1 - Bab-Hadiashar, Alireza A1 - Esch, Thomas A1 - Ramakrishna, Seeram A1 - Jalili, Mahdi A1 - Naebe, Minoo T1 - A Novel Hybrid Machine Learning Algorithm for Limited and Big Data Modeling with Application in Industry 4.0 JF - IEEE Access N2 - To meet the challenges of manufacturing smart products, the manufacturing plants have been radically changed to become smart factories underpinned by industry 4.0 technologies. The transformation is assisted by employment of machine learning techniques that can deal with modeling both big or limited data. This manuscript reviews these concepts and present a case study that demonstrates the use of a novel intelligent hybrid algorithms for Industry 4.0 applications with limited data. In particular, an intelligent algorithm is proposed for robust data modeling of nonlinear systems based on input-output data. In our approach, a novel hybrid data-driven combining the Group-Method of Data-Handling and Singular-Value Decomposition is adapted to find an offline deterministic model combined with Pareto multi-objective optimization to overcome the overfitting issue. An Unscented-Kalman-Filter is also incorporated to update the coefficient of the deterministic model and increase its robustness against data uncertainties. The effectiveness of the proposed method is examined on a set of real industrial measurements. Y1 - 2020 U6 - https://doi.org/10.1109/ACCESS.2020.2999898 SN - 2169-3536 VL - 8 IS - Art. 9108222 SP - 111381 EP - 111393 PB - IEEE CY - New York, NY ER - TY - JOUR A1 - Neu, Eugen A1 - Janser, Frank A1 - Khatibi, Akbar A. A1 - Orifici, Adrian C. T1 - Fully Automated Operational Modal Analysis using multi-stage clustering JF - Mechanical Systems and Signal Processing Y1 - 2017 U6 - https://doi.org/10.1016/j.ymssp.2016.07.031 SN - 0888-3270 VL - Vol. 84, Part A SP - 308 EP - 323 PB - Elsevier CY - Amsterdam ER - TY - JOUR A1 - Neu, Eugen A1 - Janser, Frank A1 - Khatibi, Akbar A. A1 - Orifici, Adrian C. T1 - Automated modal parameter-based anomaly detection under varying wind excitation JF - Structural Health Monitoring N2 - Wind-induced operational variability is one of the major challenges for structural health monitoring of slender engineering structures like aircraft wings or wind turbine blades. Damage sensitive features often show an even bigger sensitivity to operational variability. In this study a composite cantilever was subjected to multiple mass configurations, velocities and angles of attack in a controlled wind tunnel environment. A small-scale impact damage was introduced to the specimen and the structural response measurements were repeated. The proposed damage detection methodology is based on automated operational modal analysis. A novel baseline preparation procedure is described that reduces the amount of user interaction to the provision of a single consistency threshold. The procedure starts with an indeterminate number of operational modal analysis identifications from a large number of datasets and returns a complete baseline matrix of natural frequencies and damping ratios that is suitable for subsequent anomaly detection. Mahalanobis distance-based anomaly detection is then applied to successfully detect the damage under varying severities of operational variability and with various degrees of knowledge about the present operational conditions. The damage detection capabilities of the proposed methodology were found to be excellent under varying velocities and angles of attack. Damage detection was less successful under joint mass and wind variability but could be significantly improved through the provision of the currently encountered operational conditions. Y1 - 2016 U6 - https://doi.org/10.1177/1475921716665803 SN - 1475-9217 VL - 15 IS - 6 SP - 1 EP - 20 PB - Sage CY - London ER - TY - JOUR A1 - Rupp, Matthias A1 - Schulze, Sven A1 - Kuperjans, Isabel T1 - Comparative life cycle analysis of conventional and hybrid heavy-duty trucks JF - World electric vehicle journal N2 - Heavy-duty trucks are one of the main contributors to greenhouse gas emissions in German traffic. Drivetrain electrification is an option to reduce tailpipe emissions by increasing energy conversion efficiency. To evaluate the vehicle’s environmental impacts, it is necessary to consider the entire life cycle. In addition to the daily use, it is also necessary to include the impact of production and disposal. This study presents the comparative life cycle analysis of a parallel hybrid and a conventional heavy-duty truck in long-haul operation. Assuming a uniform vehicle glider, only the differing parts of both drivetrains are taken into account to calculate the environmental burdens of the production. The use phase is modeled by a backward simulation in MATLAB/Simulink considering a characteristic driving cycle. A break-even analysis is conducted to show at what mileage the larger CO2eq emissions due to the production of the electric drivetrain are compensated. The effect of parameter variation on the break-even mileage is investigated by a sensitivity analysis. The results of this analysis show the difference in CO2eq/t km is negative, indicating that the hybrid vehicle releases 4.34 g CO2eq/t km over a lifetime fewer emissions compared to the diesel truck. The break-even analysis also emphasizes the advantages of the electrified drivetrain, compensating the larger emissions generated during production after already a distance of 15,800 km (approx. 1.5 months of operation time). The intersection coordinates, distance, and CO2eq, strongly depend on fuel, emissions for battery production and the driving profile, which lead to nearly all parameter variations showing an increase in break-even distance. Y1 - 2018 U6 - https://doi.org/10.3390/wevj9020033 SN - 2032-6653 VL - 9 IS - 2 SP - Article No. 33 PB - MDPI CY - Basel ER -