Institut Digital Engineering (IDEE)
Refine
Document Type
- Article (56)
- Conference Proceeding (24)
- Part of a Book (6)
- Other (3)
- Report (3)
- Researchdata (2)
- Book (1)
- Part of Periodical (1)
Keywords
- Klimaanpassung (2)
- Maschinenbau (2)
- additive manufacturing (2)
- augmented reality (2)
- mainklimaplus (2)
- temperatur (2)
- 3D-Druck (1)
- Additive Fertigung (1)
- Arbeit (1)
- Architecture (1)
Institute
- Institut Digital Engineering (IDEE) (96)
- Fakultät Wirtschaftsingenieurwesen (45)
- Fakultät für angewandte Natur- und Geisteswissenschaften (13)
- Fakultät Maschinenbau (12)
- Technologietransferzentrum Main-Spessart (TTZ-MSP) (5)
- Fakultät Elektrotechnik (4)
- Institut für Sustainable Energy Systems (INSYS) (1)
This study examines StudyFAB in Schweinfurt, Germany, as a case of inner-city revitalization through a comparative analysis of third space initiatives. In response to declining pedestrian traffic and rising vacancies linked to online shopping, it investigates StudyFAB’s impact on foot traffic, perceived quality of stay, and user engagement, compared with Utopiastadt Wuppertal and CityLAB Berlin. Using a mixed-methods design, the study combines pedestrian counts, PHINEO impact metrics, usage data, and a survey of N = 93 participants (33 StudyFAB users, 30 aware non-users, and 30 non-users). The findings show that StudyFAB did not significantly increase overall city-wide pedestrian frequency, but statistical analysis indicates strong positive associations and behavioural tendencies within its target groups, including more frequent city centre visits, improved perceptions of the city image, high user satisfaction, and measurable participation. Compared with the broader neighborhood and governance approaches of Utopiastadt and CityLAB, StudyFAB demonstrates a focused but effective contribution to urban revitalization. The results suggest that third spaces can serve as complementary tools for urban transformation when social, cultural, educational, and commercial functions are integrated. Future research should examine long-term scalability, sustainable funding, and transfer effects across projects.
Low-dose and sparse-angle computed tomography (CT) reduces radiation exposure but makes image reconstruction challenging due to noisy and limited projection data. Popular reconstruction methods are based on two-stage approaches, typically involving filtered backprojection (FBP) followed by a neural network to enhance the image. FBP, however, amplifies noise and struggles with irregular sampling. Therefore, we explore filter-free initial reconstructions, shifting the filtering step to the neural network. In particular, we investigate how two-stage methods can be adapted for cases where implementing explicit filters is difficult, such as with irregular sampling. Specifically, we propose backprojection (BP) or a small number of Landweber iterations as the initial reconstruction, followed by a fine-tuned DRUNet model, referred to as BP-DRUNet and Landweber-DRUNet, respectively. For evaluation, we consider both regular and irregular sampling conditions: For regular sampling, we compare BP-DRUNet with FBP-DRUNet (using FBP as the initial stage) in order to benchmark against standard two-stage approaches. BP-DRUNet performs comparably to FBP-DRUNet under regular sampling. In irregular sampling, Landweber-DRUNet improves reconstruction quality with more iterations, though at the cost of longer training and inference times. Experiments are carried out on synthetic and real CT datasets with parallel- and fan-beam acquisitions across different sparse-angle setups.
Time-Series Modelling for Energy Consumption Prediction in CNC Milling with Regenerative Drives
(2026)
Accurately predicting the energy demand of Computerized Numeric Control (CNC) machining processes before production enables the assessment of a product’s CO₂ footprint, the identification of optimization opportunities, and the implementation of energy-aware scheduling strategies. However, forecasting the energy consumption of CNC machines equipped with regenerative drives presents unique challenges, as the energy demand of a given G-command is influenced by the preceding operation. This study investigates the application of time-series Machine Learning (ML) models to better capture these temporal dependencies and improve energy consumption accuracy. A significant variance in repeated measurements was observed during the experimental phase, prompting a comparative analysis of using raw versus averaged energy values as input data. Multiple time-series model architectures, including Long Short-Term Memory (LSTM) and Temporal Convolutional Networks (TCNs), are evaluated for their ability to learn sequential patterns in a 5-axis machining process. The results reveal that while ensemble methods such as LightGBM and Random Forest achieve the highest accuracy and efficiency on the test dataset, sequence-based models demonstrate greater robustness on unseen validation data. Incorporating a small portion of validation data into training further improves ensemble performance, highlighting the trade-off between robustness and efficiency in energy demand prediction.
Laser powder bed fusion of metal has emerged as a key technology in additive manufacturing, enabling the production of intricate, high-performance metal components directly from digital designs. However, challenges such as dimensional inaccuracies and internal defects continue to hinder its broader industrial application. Addressing these limitations requires enhanced process monitoring and control strategies. This study introduces an innovative process monitoring system, designed to improve defect detection and process control. By employing a dual scan head configuration, enabling precise and independent path planning of the laser and the measurement field of an infrared camera, the Synchronized Path Infrared Thermography (SPIT) setup utilizes the principle of exploiting differences in cooling behavior to identify subsurface defects. Pre-printed samples with embedded cylindrical defects ranging from 300 to 1000 μm in diameter are used and an additional layer of powder is applied and fused within the experimental setup. The volumetric energy density and scanning speed are varied to analyze their influence on process monitoring reliability. The sensor scan head is synchronized with the laser scan head’s movements, while the infrared camera captures thermal radiation at 1904 fps. The results demonstrate the system’s capability to detect subsurface defects with a minimum size of 356 µm.
This contribution presents a new technique for active thermography in laser powder bed fusion of metals (PBF-LB/M), utilizing the Synchronized Path Infrared Thermography (SPIT) setup. The approach uses the processing laser to thermally excite the surface of a stainless steel specimen allowing for in-situ non destructive testing. A secondary galvanometer scanner, optimized for MWIR radiation, in combination with a high-speed thermography system, is capable of conducting detailed subsurface defect analysis. The tests are carried out with artificially induced defects of varying sizes, the method uses temperature gradient analysis and higher order derivatives of the temperature profile along the laser path to identify undesirable thermal behavior. The findings highlight the potential of SPIT as a non-destructive and efficient tool for enhancing PBF-LB/M process monitoring, with implications for improved manufacturing quality and safety.
In this work, we present a comprehensive framework for approximating the weakly singular
power-law kernel 𝑡^{𝛼−1} of fractional integral and differential operators, where 𝛼 ∈ (0, 1) and
𝑡 ∈ [𝛿, 𝑇 ] with 0 < 𝛿 < 𝑇 < ∞, using a finite sum of exponentials. This approximation method
begins by substituting an exponential function into the Laplace transform of the power function, followed by the application of the trapezoidal rule to approximate the resulting integral. To ensure computational feasibility, the integral limits are truncated, leading to a finite exponential sum representation of the kernel. In contrast to earlier approaches, we pre-specify the admitted computational cost (measured in terms of the number of exponentials) and minimize the approximation error. Furthermore, to reduce computational cost while maintaining accuracy, we present a two-stage algorithm based on Prony’s method that compresses the exponential sum.
The compressed kernel is then embedded into the Riemann–Liouville fractional integral and
applied to solve fractional differential equations. To this end, we discuss two solution strategies, namely (a) method based on piecewise constant interpolation and (b) a transformation of the original fractional differential equation into a system of first-order ordinary differential equations (ODEs). This reformulation makes the problem solvable by standard ODE solvers with low computational cost while retaining the accuracy benefits of the exponential-sum approximation. Finally, we apply the proposed strategies to solve some well-known fractional differential equations and demonstrate the advantages, accuracy and the experimental order of convergence of the methods through numerical results.
Global climate change represents a cognitive challenge for many people and often evokes negative associations due to its complexity and its interactions with politics, social movements, and economic developments. Consequently, the development and possession of green skills have become central to addressing climate change. The European Council conclusions acknowledge this urgency and underline the need for a transition towards green skills. This recognition also extends to higher education, where institutions play a crucial role in tackling the climate crisis. Personal Green Skills in Higher Education (PeGSinHE) is an Erasmus+ KA2 project coordinated by Kauno Kolegija (KK, Lithuania), Tampere University of Applied Sciences (TAMK, Finland), Hochschule für Agrar- und Umweltpädagogik (HAUP, Austria), Universidad de Málaga (UMA, Spain), and the Technical University of Applied Sciences Würzburg-Schweinfurt (THWS, Germany). The strategically designed project aims not only to promote green skills among students and encourage personal behavioural change in line with the Sustainable Development Goals, but also to foster a sense of social responsibility within the partner institutions. A particular focus lies on empowering lecturers at partner universities through innovative teaching and learning approaches to effectively impart green skills to students. This report documents the pilot implementation of an international 3 ECTS Blended Intensive Programme (BIP) developed within the EU project and delivered for the first time at the Technical University of Applied Sciences Würzburg-Schweinfurt in Germany. The programme is based on a curriculum co-created in focus groups and informed by a previously developed methodology, clearly defined learning objectives and learning outcomes, as well as the competencies of the participating lecturers. This report documents the pilot implementation of an international 3 ECTS Blended Intensive Programme (BIP) developed within the EU project and delivered for the first time at the Technical University of Applied Sciences Würzburg-Schweinfurt in Germany. The programme is based on a curriculum co-created in focus groups and informed by a previously developed methodology, clearly defined learning objectives and learning outcomes, as well as the competencies of the participating lecturers. The report provides an overview of the experiences gained during the BIP week in May 2025 and includes all relevant course descriptions, teaching materials, and learning content. It is intended to enable higher education institutions outside the project consortium to implement the BIP independently with individual adaptations.
This HDF5-dataset contains in-situ high-speed infrared thermography data acquired during the Laser-Based Powder Bed Fusion (PBF-LB/M) process. The data was collected using a Synchronized Path Infrared Thermography (SPIT) setup, which employs a dual-scanhead configuration to guide both the processing laser and the thermal camera's field of view.
The primary feature of this dataset is the application of a temporally gated acquisition strategy. The infrared camera's integration time (800 µs) was synchronized with a modulated processing laser (500 Hz) to capture thermal data exclusively during the laser-off phases. This method effectively isolates the material's thermal emission from high-intensity laser reflections.
Dual Scan head approach for in-situ defect detection in laser powder bed fusion of metals - Dataset
(2025)
This dataset contains thermographic data from a study on in-situ defect detection in the Laser Powder Bed Fusion of Metals (PBF-LB/M) process. The data was collected using a novel experimental setup named Synchronized Path Infrared Thermography (SPIT), which employs a dual scan head configuration. One scan head directs the processing laser, while the second scan head positions the measurement field of an infrared (IR) camera. This setup allows for the precise analysis of the cooling behavior of the material decoupled from the immediate laser-material interaction zone.
The experiments were conducted on pre-fabricated stainless steel (EOS StainlessSteel PH1, DIN 14540) samples with embedded, cylindrical subsurface defects of varying diameters. A single layer of metal powder was applied to these samples and then fused by the laser. The dataset includes a series of measurements where process parameters, specifically the volumetric energy density and the laser scanning speed, were systematically varied to assess their influence on defect detection reliability.
The provided data consists of raw thermographic recordings, which capture the surface temperature distribution in the heat-affected zone behind the melt pool. These recordings can be used to identify localized areas of elevated temperature caused by the insulating effect of the subsurface defects, which impede heat transfer into the substrate. This dataset is valuable for researchers working on process monitoring, defect detection algorithms, and the validation of thermal simulations in additive manufacturing.
This article examines the transformative effects of Smart Factory technologies - such as human-robot collaboration, intelligent assistance systems and cyber-physical production systems - on organizational design, with a particular focus on central fields of action for Human Resources management (HRM) and operational management. A case study of a German automotive supplier is used to examine how digitalization and automation are changing human work and organizational structures. Two future scenarios for organizational models are proposed: the swarm organization, which consists exclusively of highly qualified employees while robots take over routine tasks, and the polarized organization, which is characterized by a division between highly qualified specialists and low-skilled employees. Each scenario brings different challenges and opportunities for HR management, as companies need to adapt to digital skills, new models of collaboration and the management of a highly specialized or polarized workforce. This paper provides a conceptual framework and actionable insights for HRM and production management to manage the shift towards advanced, automated organizational models and ensure a smooth transition to the Smart Factory of the future.
Cost-oriented sensor concept for magnetostrictive force measurement and its material requirements
(2025)
Ferromagnetic materials change their magnetic properties under load, enabling the implementation of a force sensor. The magnetic field emerging from such a sensor can be measured by secondary sensors to approximate the load acting on the sensor. A test setup simulating a potential application environment is described and its measurement results are presented. Furthermore, relevant magnetic material properties of an exemplarily chosen cold working steel are discussed.
Der Beitrag stellt ein neuartiges, kostenorientiertes Konzept zur Kraftmessung basierend auf dem magnetostriktiven Wandlungsprinzip vor. Kernelement ist ein scheibenförmiger Sensor, der remanent magnetisiert ist und unter Last eine äußerlich durch Sekundärsensoren messbare Magnetfeldänderung erzeugt. Die magnetischen Eigenschaften eines marktüblichen Kaltarbeitsstahls werden hinsichtlich der sensorischen Eignung für dieses Konzept diskutiert und erste Ergebnisse bezüglich der Korrelation von Sekundärsensorsignalen zur aufgebrachten Last dargestellt.
Many popular piecewise regression models rely on minimizing a cost function on the model fit with a linear penalty on the number of segments. However, this penalty does not take into account varying complexities of the model functions on the segments potentially leading to overfitting when models with varying complexities, such as polynomials of different degrees, are used. In this work, we enhance on this approach by instead using a penalty on the sum of the degrees of freedom over all segments, called degrees-of-freedom penalized piecewise regression. We show that the solutions of the resulting minimization problem are unique for almost all input data in a least squares setting. We develop a fast algorithm that does not only compute a minimizer but also determines an optimal hyperparameter—in the sense of rolling cross validation with the one standard error rule—exactly. This eliminates manual hyperparameter selection. Our method supports optional user parameters for incorporating domain knowledge. We provide an open-source Python/Rust code for the piecewise polynomial least squares case which can be extended to further models. We demonstrate the practical utility through a simulation study and by applications to real data. A constrained variant of the proposed method gives state-of-the-art results in the Turing benchmark for unsupervised changepoint detection.
Additive manufacturing (AM) has revolutionized production by offering design flexibility, reducing material waste, and enabling intricate geometries that are often unachievable with traditional methods. As the use of AM for metals continues to expand, it is crucial to ensure the quality and integrity of printed components. Defects can compromise the mechanical properties and performance of the final product. Non-destructive testing (NDT) techniques are necessary to detect and characterize anomalies during or post-manufacturing. Active thermography, a thermal imaging technique that uses an external energy source to induce temperature variations, has emerged as a promising tool in this field. This paper explores the potential of in-situ non-destructive testing using the processing laser of a PBF-LB/M setup as an excitation source for active thermography. With this technological approach, artificially generated internal defects underneath an intact surface can be detected down to a defect size of 350 μm – 450 μm.
The body tracking systems on the current market offer a wide range of options for tracking the movements of objects, people, or extremities. The precision of this technology is often limited and determines its field of application. This work aimed to identify relevant technical and environmental factors that influence the performance of body tracking in industrial environments. The influence of light intensity, range of motion, speed of movement and direction of hand movement was analyzed individually and in combination. The hand movement of a test person was recorded with an Azure Kinect at a distance of 1.3 m. The joints in the center of the hand showed the highest accuracy compared to other joints. The best results were achieved at a luminous intensity of 500 lx, and movements in the x-axis direction were more precise than in the other directions. The greatest inaccuracy was found in the z-axis direction. A larger range of motion resulted in higher inaccuracy, with the lowest data scatter at a 100 mm range of motion. No significant difference was found at hand velocity of 370 mm/s, 670 mm/s and 1140 mm/s. This study emphasizes the potential of RGB-D camera technology for gesture control of industrial robots in industrial environments to increase efficiency and ease of use.
Abstract
Small load carriers (SLCs) are standardized reusable containers used to transport and protect customer goods in many manufacturers. Throughout the life cycle of the SLCs, they will be collected, manually checked for defects (wear, cracks, and residue on the surface), and cleaned by specialized logistic companies. Human operators in small to medium-sized companies manually evaluate the defects due to the variety and degree of possible defects and varying customer needs. This manual evaluation is not scalable and prone to errors. This work aims to fill this gap by proposing a computer vision system that can recognize the SLC type for inventory management and perform defect detection automatically. First, we develop a camera portal, consisting of standard components, that capture the relevant surfaces of the SLC. A labeled dataset of 17,530 images of 34 different SLCs with their defect status was recorded using this camera portal. We trained a classification model (ConvNeXt) using our dataset to predict the different types of SLCs achieving 100% class prediction accuracy. For defect detection, we explore eight state-of-the-art (SOTA) anomaly detection models that achieved high rankings in the MVTec industrial anomaly detection benchmark. These models are trained using default hyperparameters and the two highest-scoring models were chosen and fine-tuned. The best-fine-tuned models based on “Area under the Receiver Operating Characteristic Curve (AUROC)” are PatchCore (0.811) and DRAEM (0.748). These results indicate that there is still potential for improvement in the automation of defect detection of SLCs.
Computerized Numerical Control (CNC) plays an important role in highly autonomous manufacturing systems with multiple machine tools. The necessary Numerical Control (NC) programs to manufacture the parts are mostly written in standardized G-code. An a priori evaluation of the energy demand of CNC-based machine processes opens up the possibility of scheduling multiple jobs according to balanced energy consumption over a production period. Due to this, we present a combined Machine Learning (ML) and Job-Shop-Scheduling (JSS) approach to evaluate G-code for a CNC-milling process with respect to the energy demand of each G-command. The ML model training data are derived by the Latin hypercube sampling (LHS) method facing the main G-code operations G00, G01, and G02. The resulting energy demand for each job enhances a JSS algorithm to smooth the energy demand for multiple jobs, as peak power consumption needs to be avoided due to its expense.
Die Studie befasst sich mit den Herausforderungen und Chancen, die kleine und mittlere Unternehmen (KMU) in der Region Mainfranken, insbesondere in den Bereichen Maschinenbau und Automobilindustrie, im Zuge des Wandels der Arbeitswelt erleben. Ein zentrales Thema ist der Mangel an qualifizierten Arbeitskräften, der 89 % der befragten KMU betrifft. Die Unternehmen müssen attraktive Arbeitsbedingungen schaffen, um Talente zu gewinnen und zu halten, was zu einem "War for Talent" führt.
Die Studie hebt die Notwendigkeit hervor, kreative Ansätze zur Mitarbeiterbindung und -gewinnung zu entwickeln, wie flexible Arbeitszeiten und Weiterbildungsmöglichkeiten. Zudem wird betont, dass eine enge Zusammenarbeit mit Bildungseinrichtungen und die Entwicklung maßgeschneiderter Schulungsprogramme entscheidend sind, um den Anforderungen des Marktes gerecht zu werden und die Wettbewerbsfähigkeit der Region zu sichern.
The described data set contains features from the machine control of a five-axis milling machine. The features were recorded during thirteen series productions. Each series production includes a changeover process in which the machine was set up for the production of a different product. In addition to the timestamps and the twenty recorded features derived from Numerical Control (NC) variables, the data set also contains labels for the different production phases. For this purpose, up to 23 phases were assigned, which are based on a generalized milling process. The data set consists of thirteen .csv files, each representing a series production. The data set was recorded in a production company in the contract manufacturing sector for components with real series orders in ongoing industrial production.
Given a Caputo-type fractional differential equation with order between 1 and 2, we consider two distinct solutions to this equation subject to different sets of initial conditions. In this framework, we discuss nontrivial upper and lower bounds for the difference between these solutions. The main emphasis is on describing how such bounds are related to the differences of the associated initial values.
