Fakultät Maschinenbau
Refine
Year of publication
Document Type
- Article (140)
- conference proceeding (article) (76)
- conference proceeding (presentation) (18)
- Part of a Book (11)
- Preprint (7)
- Book (5)
- conference proceeding (volume) (4)
- Doctoral Thesis (4)
- Other (4)
- Handout (3)
Language
- English (187)
- German (88)
- Multiple languages (3)
Publication reviewed
- begutachtet (239)
- nicht begutachtet (38)
Keywords
- Maschinelles Lernen (13)
- Fernwärme (12)
- Lastprognose (12)
- automated driving (12)
- deepDHC (11)
- KWK-Flex (10)
- advanced driver assistance systems (9)
- human factor (8)
- workload (8)
- KLEVERTEC / Vorlaufforschung (7)
Institute
- Fakultät Maschinenbau (278)
- IEAT - Institut für Energie- und Antriebstechnik (54)
- IFM - Institut für Fahrerassistenz und vernetzte Mobilität (25)
- KLEVERTEC (10)
- EPT – Institut für Effiziente Produktionstechnik (7)
- ECC-ProBell - Europäisches Kompetenzzentrum für Glocken (5)
- Fakultät Informatik (4)
- IFA – Institut für Innovative Fahrzeugantriebe (3)
- IMS - Institut für Maschinelles Sehen (2)
- Fakultät Elektrotechnik (1)
Using a Machine Learning Regression Approach to Predict the Aroma Partitioning in Dairy Matrices
(2024)
Aroma partitioning in food is a challenging area of research due to the contribution of several physical and chemical factors that affect the binding and release of aroma in food matrices. The partition coefficient measured by the Kmg value refers to the partition coefficient that describes how aroma compounds distribute themselves between matrices and a gas phase, such as between different components of a food matrix and air. This study introduces a regression approach to predict the Kmg value of aroma compounds of a wide range of physicochemical properties in dairy matrices representing products of different compositions and/or processing. The approach consists of data cleaning, grouping based on the temperature of Kmg analysis, pre-processing (log transformation and normalization), and, finally, the development and evaluation of prediction models with regression methods. We compared regression analysis with linear regression (LR) to five machine-learning-based regression algorithms: Random Forest Regressor (RFR), Gradient Boosting Regression (GBR), Extreme Gradient Boosting (XGBoost, XGB), Support Vector Regression (SVR), and Artificial Neural Network Regression (NNR). Explainable AI (XAI) was used to calculate feature importance and therefore identify the features that mainly contribute to the prediction. The top three features that were identified are log P, specific gravity, and molecular weight. For the prediction of the Kmg in dairy matrices, R2 scores of up to 0.99 were reached. For 37.0 °C, which resembles the temperature of the mouth, RFR delivered the best results, and, at lower temperatures of 7.0 °C, typical for a household fridge, XGB performed best. The results from the models work as a proof of concept and show the applicability of a data-driven approach with machine learning to predict the Kmg value of aroma compounds in different dairy matrices.
Effiziente Kühlung und Schmierung für Fräsprozesse: Frästechnologie und Hochdruckkühlschmierstoff
(2024)
Insbesondere bei der 5-achsigen Fräsbearbeitung existiert noch kein System, das die optimale bzw. minimale Hochdruckkühlschmierstoffmenge bei jeweils gegebenen Bearbeitungszuständen beschreibt.
Die Entwicklung, Umsetzung und Potentiale eines seriennah einsetzbaren, externen und vom Werkzeugmaschinenhersteller unabhängigen Systems zur optimierten Bereitstellung von Hochdruckkühlschmierstoff werden gezeigt.
Bisher existiert noch kein System, das die optimale bzw. minimale Kühlschmierstoffmenge bei jeweils gegebenen Bearbeitungssituationen unter besonderer Berücksichtigung der zu verarbeitenden Werkstoffe und deren signifikantem Verschleißverhalten beschreibt.
Die Entwicklung eines seriennahen unabhängigen Systems zur optimierten Bereitstellung von Kühlschmierstoffen mit angepassten Drücken für die jeweilige Werkstoffapplikationen wird gezeigt.
Diese Veröffentlichung beleuchtet die Herausforderungen und Lösungsansätze zur Bewältigung des Fachkräftemangels in der deutschen produzierenden Industrie. Der Mangel an qualifizierten Arbeitskräften verursacht erhebliche Kosten und verringert das Produktionspotenzial. Hauptursachen sind demografische Veränderungen und veränderte Wertvorstellungen der Beschäftigten. Die Attraktivität des Arbeitsumfelds soll durch die Sichtbarmachung individueller Beiträge und die Stärkung des Gemeinschaftsgefühls erhöht werden. Maßnahmen aus dem Umfeld von Large-Language-Models werden vorgestellt. Abschließend wird die Vision einer modernen, vollvernetzten und arbeitnehmerfreundlichen Produktionsstätte skizziert.
In an industrial context, AI-based methods are becoming increasingly important in the optical systems used for identification, inspection and classification. The reasons for this are that AI-based image processing algorithms are easy to use on the operator side and often achieve superior results. E.g. in complex classification tasks. In the sand cast industry, the complexity in optical inspection of cast parts is connected with strong variations in the local surface topography and in the global object geometry change. Despite the great potential of AI-based methods, application is often hindered by the immense effort involved in acquiring a suitable training dataset. This refers not only to the acquisition of the required number of images but also to the tedious labelling. In this work, we investigate the capabilities and limits of synthetic training data on an AI-based optical scanner used to identify and track cast parts. The optical scanner is capable of detecting and classifying a codification specifically designed for the casting industry. By reading the code, the scanner can deduce the specific number of the cast part. For synthetic image generation, we use physically based rendering, which has advantage of full control over all rendering parameters. This allows for both a systematic investigation of the importance of the parameters and, an automatic labelling process of the training datasets. Our results show that, in particular, a detailed geometric modelling of the local surface topography and global object geometry of the pins have a positive influence on the recognition rate of the neural network. With that accuracy rates up to 56 % are achieved using synthetic training datasets, only.
Large Language Models (LLMs) have become widely adopted recently. Research explores their use both as autonomous agents and as tools for software engineering. LLM-integrated applications, on the other hand, are software systems that leverage an LLM to perform tasks that would otherwise be impossible or require significant coding effort. While LLM-integrated application engineering is emerging as new discipline, its terminology, concepts and methods need to be established. This study provides a taxonomy for LLM-integrated applications, offering a framework for analyzing and describing these systems. It also demonstrates various ways to utilize LLMs in applications, as well as options for implementing such integrations.
Following established methods, we analyze a sample of recent LLM-integrated applications to identify relevant dimensions. We evaluate the taxonomy by applying it to additional cases. This review shows that applications integrate LLMs in numerous ways for various purposes. Frequently, they comprise multiple LLM integrations, which we term ``LLM components''. To gain a clear understanding of an application's architecture, we examine each LLM component separately. We identify thirteen dimensions along which to characterize an LLM component, including the LLM skills leveraged, the format of the output, and more. LLM-integrated applications are described as combinations of their LLM components. We suggest a concise representation using feature vectors for visualization.
The taxonomy is effective for describing LLM-integrated applications. It can contribute to theory building in the nascent field of LLM-integrated application engineering and aid in developing such systems. Researchers and practitioners explore numerous creative ways to leverage LLMs in applications. Though challenges persist, integrating LLMs may revolutionize the way software systems are built.
Clubfoot is a common congenital foot deformity that leads to constant pain and significant limitations if left untreated or not treated adequately. The most used method for treating clubfoot is the Ponseti method. It involves a correction phase where about five plaster casts are applied and changed weekly. This treatment lasting about 2 to 3 months, is the most chosen method due to its high success rate. However, treated babies often experience skin complications caused by stiff and tight casts. Previous research showed that viable solutions already exist including orthoses. In this research, a developed method known as VDI 2221 was applied and the printable orthosis using 3D printer was selected as an alternative to Ponseti method. Calculations and finite element method (FEM) analysis demonstrated that the orthosis made of PA6-CF provides sufficient stiffness and strength, assuming the weight force of the foot is 10 N. The selected design was developed based on requirements and functional analysis, effectively mitigating the disadvantages of the Ponseti method. The developed orthosis can be manufactured globally using the 3D printing process, with a manufacturing cost of around €150, excluding assembly costs. In summary, a new solution was proposed within the same treatment method, effectively eliminating skin complications, and enabling cost-effective manufacturability on a global scale.
Algorithms for causal discovery have recently undergone rapid advances and increasingly draw on flexible nonparametric methods to process complex data. With these advances comes a need for adequate empirical validation of the causal relationships learned by different algorithms. However, for most real and complex data sources true causal relations remain unknown. This issue is further compounded by privacy concerns surrounding the release of suitable high-quality data. To tackle these challenges, we introduce causalAssembly, a semisynthetic data generator designed to facilitate the benchmarking of causal discovery methods. The tool is built using a complex real-world dataset comprised of measurements collected along an assembly line in a manufacturing setting. For these measurements, we establish a partial set of ground truth causal relationships through a detailed study of the physics underlying the processes carried out in the assembly line. The partial ground truth is sufficiently informative to allow for estimation of a full causal graph by mere nonparametric regression. To overcome potential confounding and privacy concerns, we use distributional random forests to estimate and represent conditional distributions implied by the ground truth causal graph. These conditionals are combined into a joint distribution that strictly adheres to a causal model over the observed variables. Sampling from this distribution, causalAssembly generates data that are guaranteed to be Markovian with respect to the ground truth. Using our tool, we showcase how to benchmark several well-known causal discovery algorithms.