Fakultät für Maschinenbau

Permanent URI for this collection

https://repo.uni-hannover.de/handle/123456789/6

Browse

Now showing 1 - 5 of 1973

Investigation of the influence of the forming process and finishing processes on the properties of the surface and subsurface of hybrid components
(London : Springer, 2021) Budde, Laura; Prasanthan, Vannila; Kruse, Jens; Faqiri, Mohamad Yusuf; Lammers, Marius; Hermsdorf, Jörg; Stonis, Malte; Hassel, Thomas; Breidenstein, Bernd; Behrens, Bernd-Arno; Denkena, Berend; Overmeyer, Ludger
Due to the increased integration of functions, many components have to meet high and sometimes contradictory requirements. One way to solve this problem is Tailored Forming. Here, hybrid semi-finished products are manufactured by a joining or cladding process, which are then hot-formed and finished. For the design of hybrid components for a possible later industrial application, knowledge about properties of hybrid components is required. In this paper it is investigated how the respective process steps of the Tailored Forming process chain change the surface and subsurface properties of the applied cladding layer. For this purpose, shafts made of unalloyed steel are provided with a high-alloy austenitic steel X2CrNiMo19-12 cladding by laser hot-wire cladding. Subsequently, hot forming is carried out by cross-wedge rolling and the finishing by turning and deep rolling. After each process step, the subsurface properties of the cladding such as microstructure, hardness and residual stress state are examined. Thus, the influence of different process steps on the subsurface properties in the process chain of manufacturing hybrid shafts can be analyzed. This knowledge is necessary for the specific adjustment of defined properties for a required application behavior.
Hyper-Parameter Optimization of Stacked Asymmetric Auto-Encoders for Automatic Personality Traits Perception
(Basel : MDPI, 2022) Jalaeian Zaferani, Effat; Teshnehlab, Mohammad; Khodadadian, Amirreza; Heitzinger, Clemens; Vali, Mansour; Noii, Nima; Wick, Thomas
In this work, a method for automatic hyper-parameter tuning of the stacked asymmetric auto-encoder is proposed. In previous work, the deep learning ability to extract personality perception from speech was shown, but hyper-parameter tuning was attained by trial-and-error, which is time-consuming and requires machine learning knowledge. Therefore, obtaining hyper-parameter values is challenging and places limits on deep learning usage. To address this challenge, researchers have applied optimization methods. Although there were successes, the search space is very large due to the large number of deep learning hyper-parameters, which increases the probability of getting stuck in local optima. Researchers have also focused on improving global optimization methods. In this regard, we suggest a novel global optimization method based on the cultural algorithm, multi-island and the concept of parallelism to search this large space smartly. At first, we evaluated our method on three well-known optimization benchmarks and compared the results with recently published papers. Results indicate that the convergence of the proposed method speeds up due to the ability to escape from local optima, and the precision of the results improves dramatically. Afterward, we applied our method to optimize five hyper-parameters of an asymmetric auto-encoder for automatic personality perception. Since inappropriate hyper-parameters lead the network to over-fitting and under-fitting, we used a novel cost function to prevent over-fitting and under-fitting. As observed, the unweighted average recall (accuracy) was improved by 6.52% (9.54%) compared to our previous work and had remarkable outcomes compared to other published personality perception works.
Ecological Planning of Manufacturing Process Chains
(Basel : MDPI, 2022) Denkena, Berend; Wichmann, Marcel; Kettelmann, Simon; Matthies, Jonas; Reuter, Leon
Production planning is a critical step for the implementation of sustainable production. It is necessary to consider energy and resource efficiency in all planning phases to promote sustainable production. In this paper, an approach for environmental impact assessment in all phases of process chain planning supported by process models is presented. The level of detail of the assessment is determined based on the level of detail of the planning phase. During the assessment, consumption of energy and resources is considered. This approach aims to align planning phases with the objective of sustainable production. In rough planning, the approach allows the selection of an ecologically favorable process chain. In detailed planning, process parameters can be selected based on their ecological sustainability. The approach can be integrated into the planning of process chains in order to consider ecological factors throughout all planning phases. The approach is evaluated by using an exemplary use case. The results indicate that rough planning under the consideration of uncertainties can form a reasonable prediction about resource efficiency for possible manufacturing routes. By systematically selecting a resource-efficient process chain, energy savings of up to 21% can be achieved for the presented use case.
Methodik zur Ökobilanzierung im Flugzeugvorentwurf
(München : Verlag Dr. Hut, 2017) Johanning, Andreas; Scholz, Dieter
In dieser Arbeit wird eine Methodik zur Ökobilanzierung im Flugzeugvorentwurf entwickelt. Mithilfe der Methodik kann die Umweltwirkung der entworfenen Flugzeuge bestimmt werden. Außerdem können treibende In- und Outputs, Prozesse, Lebenszyklusphasen, Wirkungskategorien und Entwurfsparameter für die Umweltwirkung von Flugzeugen ermittelt werden. Ein Turbopropflugzeug dient als Anwendungsbeispiel für die Methodik. Dieses wird für minimale Umweltwirkung optimiert und die Ergebnisse werden mit denen eines Referenzflugzeugs verglichen. Zusätzlich wird die Methodik auf zukünftige Flugzeugkonzepte angewandt und auch deren Umweltwirkung mit der des Referenzflugzeugs verglichen. Die Untersuchungen für das Turbopropflugzeug zeigen, dass grundsätzlich ein hohes Potential zur Reduzierung der Umweltwirkung vorhanden ist. Die Verringerung des Kraftstoffverbrauchs und die Anpassung der Flughöhe stellen hierbei entscheidende Kriterien dar. Bei den untersuchten zukünftigen Flugzeugkonzepten verlagert sich die Umweltwirkung tendenziell vom Flug auf die Herstellung des jeweiligen Energieträgers. Die erforderliche elektrische Energie sollte hierbei zu einem möglichst hohen Anteil aus erneuerbaren Energien bereitgestellt werden, um eine möglichst geringe Umweltwirkung erreichen zu können. Durch Integration der entwickelten Ökobilanz-Methodik in den Flugzeugvorentwurf wird es möglich, die zukünftigen Umweltauswirkungen von Flugzeugen im frühen Entwurfsprozess zu erfassen und gezielt zu beeinflussen.
Creepage Distance Estimation of Hairpin Stators Using 3D Feature Extraction
(Basel, Switzerland : MDPI, 2023) Grambow, Niklas; Hinz, Lennart; Bonk, Christian; Krüger, Jörg; Reithmeier, Eduard
The increasing demand for electric drives challenges conventional powertrain designs and requires new technologies to increase production efficiency. Hairpin stator manufacturing technology enables full automation, and quality control within the process is particularly important for increasing the process capacity, avoiding rejects and for safety-related aspects. Due to the complex, free-form geometries of hairpin stators and the required short inspection times, inline reconstruction and accurate quantification of relevant features is of particular importance. In this study, we propose a novel method to estimate the creepage distance, a feature that is crucial regarding the safety standards of hairpin stators and that could be determined neither automatically nor accurately until now. The data acquisition is based on fringe projection profilometry and a robot positioning system for a highly complete surface reconstruction. After alignment, the wire pairs are density-based clustered so that computations can be parallelized for each cluster, and an analysis of partial geometries is enabled. In several further steps, stripping edges are segmented automatically using a novel approach of spatially asymmetric windowed local surface normal variation, and the creepage distances are subsequently estimated using a geodesic path algorithm. Finally, the approach is examined and discussed for an entire stator, and a methodology is presented that enables the identification of implausible estimated creepage distances.

Browse

Recent Submissions