Refine
Year of publication
Document Type
- Article (303)
- Conference Proceeding (303)
- Part of a Book (71)
- Workingpaper / Report (16)
- Book (5)
- Doctoral Thesis (5)
- Collection (4)
- Preprint (4)
- Patent (3)
- Article trade magazine (1)
Language
- English (719) (remove)
Has Fulltext
- no (719) (remove)
Keywords
- VSVR (39)
- Virtual (TV) Studio (21)
- FHD (15)
- Forena (12)
- Poster (8)
- security (8)
- security requirement (7)
- Querschnittsauswertung (6)
- Sound Spatialization (6)
- virtual studio (6)
Department/institution
- Fachbereich - Medien (303)
- Fachbereich - Maschinenbau und Verfahrenstechnik (228)
- Creative Media Production and Entertainment Computing (136)
- Fachbereich - Sozial- & Kulturwissenschaften (80)
- Fachbereich - Elektro- & Informationstechnik (58)
- Sound and Vibration Engineering (35)
- Digitale Vernetzung und Informationssicherheit (27)
- Fachbereich - Architektur (22)
- Fachbereich - Wirtschaftswissenschaften (12)
- Intelligente Mensch-Technik-Interaktion (9)
Acquiring human motion data from video images plays an important role in the field of computer vision. Ground truth tracking systems require markers to create high quality motion data. But in many applications it is desired to work without markers. In recent years affordable hardware for markerless tracking systems was made available at a consumer level. Efficient depth camera systems based on Time-of-Flight sensors and structured light systems have made it possible to record motion data in real time. However, the gap between the quality of marker-based and markerless systems is high. The error sources of a markerless motion tracking pipeline are discussed and a model-based filter is proposed, which adapts depending on spatial location. The proposed method is then proven to be more robust and accurate than the unfiltered data stream and can be used to visually enhance the presence of an actor within a virtual environment in live broadcast productions.
Mobile virtual archery
(2013)
The healthcare sector's digital transformation necessitates the involvement of stakeholders through participation and co-creation processes. This study aims to investigate the understanding and implementation of participation and co-creation in the development of hybrid interaction technologies in healthcare. Eight interdisciplinary research projects were examined through semi-structured group interviews with 49 participants from academia, industry, and the application field. The interviews focused on participants' perspectives on project goals, user groups, access to the field, methods of participation and co-creation, and user motivation. The results highlight the diverse understandings of participation and co-creation, with some perceiving them as research-driven and others as already embedded in user- centered design. The projects emphasized user needs but often excluded stakeholders from collaborative decision-making. Challenges in achieving continuous involvement and co-decision were acknowledged. The findings underscore the need for reflexive practice and evaluation of participation and co-creation throughout the development process, as well as further research on participation across projects. By addressing these challenges and embracing participatory approaches, digital health applications can better address ethical concerns, build trust, and increase acceptance and adoption in the healthcare sector.
In today’s market research mechanisms multi modal technologies are significant tools to perform flexible and price efficient studies for not only consumer products but also consumer goods. Current appraisal mechanisms in combination with applied computer graphics can improve the assessment of a product’s launch in the very early design phase or an innovation process. The combination of online questionnaires, Virtual Reality (VR) applications and a database management system offers a powerful tool to let a consumer judge products as well as innovated goods even without having produced a single article. In this paper we present an approach of consumer good studies consisting of common as well as interactive VR product presentations and online questionnaires bases on a bidirectional database management solution to configure and manage numerous studies, virtual sets, goods and participants in an effective way to support the estimation of the received data. Non-programmers can create their test environment including a VR scenario very quickly without any effort. Within the extensive knowledge of consumer goods, marketing instruments can be defined to shorten and improve the rollout process in the early product stages.
With the current movement towards Net Zero Energy Buildings (Net ZEBs) decisions regarding energy carrier weighting factors will have implications on which technologies could be favoured or disfavoured, and therefore adopted or not adopted, in the building sector of the near future. These implications should be taken into consideration by policy makers when developing legislation and regulations addressing the building sector. A parametric analysis was conducted on six buildings in Europe of different typologies and climates in order to assess how different weighting factors would impact the choice of technical systems to be installed. For each combination the amount of PV capacity necessary to achieve a net zero balance has been calculated and used as the main indicator for comparison; where less PV area means more favourable condition. The effect of including a solar thermal system is also discussed. With the current European national weighting factors, biomass boiler is largely the preferred solution, frequently achieving the balance with PV installed on the roof, while gas boiler is the most penalized. The situation changes when strategic weighting factors are applied. Lower weighting factors for electricity and district heating, e.g. reflecting national targets of increased penetration of renewables in such grids, would promote the use of heat pump and district heating, respectively. Asymmetric factors aimed at rewarding electricity export to the grid would facilitate the achievement of the zero balance for all technologies, promoting cogeneration in some cases. On the contrary, low weighting factors for electricity, e.g. reflecting a scenario of high decarbonisation of the power system, prove quite demanding; only few technical solutions would be able to reach the balance within the available roof area for PV, because of the low value credited to exported electricity. In this situation, the preferred solution would be heat pumps combined with solar thermal. In addition, the choice of weighting factors and the resulting favoured technologies will determine the temporal matching of load and generation. While all-electric solutions tend to use the grid as seasonal storage, other solutions will have a yearly net export of electricity to the grid to compensate for the supply of other (thermal) energy carriers. Therefore, it is important to consider the implications for the electricity grid resulting from the choice of weighting factors.
Development of open educational resources for renewable energy and the energy transition process
(2021)
A course called "Engineering Conferences" is presented that the authors have developed and installed as a mandatory part of the curriculum in Master programs for engineering students. The idea is to go beyond teaching the standards of academic writing and skills for working with scientific publications. By using a learner-centered approach, we get the students engaged in typical activities around an active attendance of a real conference. They write a paper complying with common academic standards, submit the paper and review submissions of their fellow students. Students also produce a poster and have to defend it in a poster session held publicly on campus. In this article, we present our rationale to develop the course and our results from the first semester teaching this course. This includes the presentation of useful resources for teaching and organizing scientific publishing as well as our reflected learning experience regarding the student's understanding of significance for scientific publishing.
Adaptive and contacting seals such as brush seals have been successfully applied to turbomachinery for several years. In large steam turbine applications, however, various challenges still persist. Special focus is directed at the long-term performance and longevity of brushes on conventional spring-backed seal segments in steam turbines. This issue is particularly related to wear during startup conditions. This paper discusses the results of wear tests, derived from simulated transient turbine behavior, where the resultant seal leakage under steady state conditions is monitored. It is shown that the brush seal is significantly capable of adapting to varying operating conditions, but exhibits a degree of performance degradation during the initial startups. Together with previously reported mid-term wear data and an experience based long-term phenomenological approach a general model for brush seal performance degradation is developed. This model can be used for performance prediction and exerts influence on brush seal design.
Undergraduate students in engineering often have little exposure to the world of scientific publishing and the culture of sharing research work. While the beneficial exchange between research and teaching is well promoted, while the benefits of conference participation for students have already been surveyed and while courses on scientific writing are readily available, the concept of mini-conferences as part of the curriculum combines all three aspects into one. Therefore, the course "Engineering Conferences" was developed and installed as a mandatory part of a master program for engineering students. The idea is to go beyond simply teaching the standards of academic writing and skills for using scientific publications. By using a learner-centered approach, the students are engaged in typical activities around an active attendance of a real conference. Based on their bachelor thesis, they write a paper complying with common academic standards, submit the paper and review submissions of their fellow students. They also produce a poster and defend their work in a poster session held publicly on campus. This contribution is based on the experience from the first four terms teaching the course. It explains the didactic rationale behind the concept and individual teaching modules, it comprises the collection of useful resources for teaching and organizing scientific publishing and it includes the consequences drawn from course evaluation results.
In the dynamic testing of jet engines the evaluation of loads on the mount structure is vital for comparison with finite element calculations of such testing. Measuring these loads with the help of strain gauges applied to the structure becomes difficult if the mount is overdetermined and thus not every strain gauge can be assigned to a single load direction. In this study, the overdetermined mount structure of the BR715 engine was examined at one of the three mounting points between the Boeing 717 airframe and the engine, where loads in five directions were reacted. Firstly, the dependence of five measured strains upon known static load conditions at the mounting point had to be determined. For this purpose a static calibration test was carried out where defined forces and moments in known directions were applied to the structure while the output from five strain gauges was measured accordingly. The result was the desired relationship between loads and strains in terms of a matrix, which yields the corresponding load condition of the examined mounting point if multiplied with a set of strains. The same calibration procedure was carried out with a finite element model of the mount, where direct comparison to dynamic load results from the model itself was possible. With this model the validity of the above method was shown as well as possible errors which may occur while evaluating dynamic test results. The method was found to give satisfactory results even for dynamic loading, although some inertia forces disturb the signals in dynamic testing. Finally, the results from an actual dynamic engine test were processed into loads and then compared to the simulated loads from a finite element model of the engine. Good agreement was found and the indication of any remaining discrepancies was used to update the model for an even better representation of the dynamic test loads.
Image restoration is a process used to remove blur (from different sources like object motion or aberrations) from images by either non-blind or blind-deconvolution. The metrics commonly used to quantify the restoration process are peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM). Often only a small sample of test images are used (like Lena or the camera guy). In optical design research PSNR and SSIM are not normally used, here image quality metrics based on linear system theory (e.g. modulation transfer function, MTF) are used to quantify optical errors like spherical or chromatic aberration. In this article we investigate how different image restoration algorithms can be quantified by applying image quality metrics. We start with synthetic image data that is used in camera test stands (e.g. Siemens star etc.), apply two different spatially variant degradation algorithms, and restore the original image by a direct method (Wiener filtering within sub-images), and by an iterative method (alternating direction method of multipliers, ADMM). Afterwards we compare the quality metrics (like MTF curves) for the original, the degraded and the restored image. As a first result we show that restoration algorithms sometimes fail in dealing with non-natural scenes, e.g. slanted-edge targets. Further, these first results indicate a correlation between degradation and restoration, i.e. the restoration algorithms are not capable of removing the optically relevant errors introduced by the degradation, a fact neither visible nor available from the PSNR values. We discuss the relevance in the context of the automotive industry, where image restoration may yield distinct advantages for camera-based applications, but testing methods rely on the used image quality metrics.
Abstract The modulation-transfer function (MTF) is a fundamental optical metric to measure the optical quality of an imaging system. In the automotive industry it is used to qualify camera systems for ADAS/AD. Each modern ADAS/AD system includes evaluation algorithms for environment perception and decision making that are based on AI/ML methods and neural networks. The performance of these AI algorithms is measured by established metrics like Average Precision (AP) or precision-recall-curves. In this article we research the robustness of the link between the optical quality metric and the AI performance metric. A series of numerical experiments were performed with object detection and instance segmentation algorithms (cars, pedestrians) evaluated on image databases with varying optical quality. We demonstrate with these that for strong optical aberrations a distinct performance loss is apparent, but that for subtle optical quality differences – as might arise during production tolerances – this link does not exhibit a satisfactory correlation. This calls into question how reliable the current industry practice is where a produced camera is tested end-of-line (EOL) with the MTF, and fixed MTF thresholds are used to qualify the performance of the camera-under-test.
Rituals, such as gazing at faces, are common in body dysmorphic disorder (BDD) and appear in cognitive-behavioral models as a maintaining factor. Rituals are also common in obsessive-compulsive disorder (OCD). In contrast to OCD, the proposed associations between rituals and intrusive thoughts/appearance preoccupation have not been empirically investigated for BDD. We examined if the assumed effect of gazing rituals on attractiveness ratings exists and if it is associated with dissociation. In an experiment, we asked N = 65 non-clinical females to focus on the nose of a photographed face at pre- and post-test. In between, participants gazed at the nose of either the same (relevant gazing) or another face (irrelevant gazing). We found increasing dissociation after gazing in both conditions and a differentially stronger decrease of attractiveness ratings in the relevant gazing condition. Our findings support the hypothesized effect of gazing rituals on attractiveness evaluation in cognitive-behavioral models for BDD.
CAD/CAM techniques are increasingly used in dentistry for the design and fabrication of teeth estorations. Important concerns are the correction of articulation problems that existed before treatment and the prevention of treatment-generated problems. These require interactive evaluation of the occlusal surfaces of teeth during mastication. Traditional techniques based on the use of casts with mechanical articulators require manual adjustment of occlusal surfaces, which becomes impractical when hard restoration materials like porcelain are used; they are also time and labor consuming and provide little visual information. We present new visual tools and a related user interface for global articulation simulation, developed for the Intelligent Dental Care System project. The aim of the simulation is visual representation of characteristics relevant to the chewing process. The simulation is based on the construction of distance maps, which are visual representations of the distributions of the distances of points in a tooth to the opposite jaw. We use rasterizing graphics hardware for fast calculation of the distance maps. Distance maps are used for collision detection and for the derivation of various characteristics showing the distribution of load on the teeth and the chewing capability of the teeth. Such characteristics can be calculated for particular positions of the jaws; cumulative characteristics are used to describe the properties of jaw movement. This information may be used for interactive design of the occlusal surfaces of restorations and for jaw articulation diagnosis. We also demonstrate elements of a user interface that exploit metaphors familiar to dentists from everyday practice.
CAD/CAM techniques are increasingly used in dentistry for the design and fabrication of teeth restorations. Important concerns are the correction of articulation problems that existed beforetreatment and the prevention of treatment-generated problems. These require interactive evaluation of the occlusal surfaces of teeth during mastication. Traditional techniques based on the use of casts with mechanical articulators require manual adjustment of occlusal surfaces, which becomes impractical when hard restoration materials like porcelain are used; they are also time and labor consuming and provide little visual information. We present new visual tools and a related user interface for global articulation simulation, developed for the Intelligent Dental Care System project. The aim of the simulation is visual representation of characteristics relevant to the chewing process. The simulation is based on the construction of distance maps, which are visual representations of the distributions of the distances of points in a tooth to the opposite jaw. We use rasterizing graphics hardware for fast calculation of the distance maps. Distance maps are used for collision detection and for the derivation of various characteristics showing the distribution of load on the teeth and the chewing capability of the teeth. Such characteristics can be calculated for particular positions of the jaws; cumulative characteristics are used to describe the properties of jaw movement. This information may be used for interactive design of the occlusal surfaces of restorations and for jaw articulation diagnosis. We also demonstrate elements of a user interface that exploit metaphors familiar to dentists from everyday practice.
Dynamic characteristics of occlusion during lower jaw motion are useful in the diagnosis of jaw articulation problems and in computer-aided design/manufacture of teeth restorations. The Functionally Generated Path (FGP), produced as a surface which envelops the actual occlusal surface of the moving opponent jaw, can be used for compact representation of dynamic occlusal relations. In traditional dentistry FGP is recorded as a bite impression in a patient’s mouth. We propose an efficient computerized technique for FGP reconstruction and validate it through implementation and testing. The distance maps between occlusal surfaces of jaws, calculated for multiple projection directions and accumulated for mandibular motion, provide information for FGP computation. Rasterizing graphics hardware is used for fast calculation of the distance maps. Real-world data are used: the scanned shape of teeth and the measured motion of the lower jaw. We show applications of FGP to analysis of the occlusion relations and occlusal surface design for restorations.
This paper summarises the state of two research phases within the scope of the IEA Task 40 / Annex 52 "Towards Net Zero Energy Solar Buildings" [1]. The first objective is a cross section analysis of a comprehensive collection of more than 280 international zero energy buildings. The aim is to show trends, motives of actors, as well as their method to reach the zero energy balance. Secondly, an in-depth study shows a rough analysis and characteristics of 50 exemplary Nets ZEBs from different countries and climate regions, as well as their combinations of measures concerning energy efficiency and renewable energy supply.
It is shown that diverse actors with miscellaneous motives have lead to a lot of different building variations. Typical strategies can be assigned to the typology groups "small residential building", "apartment building" and "non residential building". Net ZEBs are much more energy efficient than average buildings which were built according to national construction and energy regulations. None of the leading Net ZEB examples exist without generation of PV electricity. Trends give an outlook of current and possible future combinations of technologies and passive measures for the realization of (future) net zero energy buildings.
Null-/Plusenergiegebäude - Erfahrungen und Perspektiven zu klimaneutralen Gebäuden in Deutschland
(2011)
Camera-based object detection is widely used in safety-critical applications such as advanced driver assistance systems (ADAS) and autonomous vehicle research. Road infrastructure has been designed for human vision, so computer vision, with RGB cameras, is a vital source of semantic information from the environment. Sensors, such as LIDAR and RADAR, are also often utilized for these applications; however, cameras provide a higher spatial resolution and color information. The spatial frequency response (SFR), or sharpness of a camera, utilized in object detection systems must be sufficient to allow a detection algorithm to localize objects in the environment over its lifetime reliably. This study explores the relationship between object detection performance and SFR. Six state-of-the-art object detection models are evaluated with varying levels of lens defocus. A novel raw image dataset is created and utilized, containing pedestrians and cars over a range of distances up to 100-m from the sensor. Object detection performance for each defocused dataset is analyzed over a range of distances to determine the minimum SFR necessary in each case. Results show that the relationship between object detection performance and lens blur is much more complex than previous studies have found due to lens field curvature, chromatic aberration, and astigmatisms. We have found that smaller objects are disproportionately impacted by lens blur, and different object detection models have differing levels of robustness to lens blur
We derive a nonlinear model of the steam cycle of a solar power plant, estimate its unknown parameters with measured data, and design a linear model predictive controller based on the resulting model. Simulations show that the linear model predictive controller is able to regulate the electrical power of the nonlinear steam process of the plant to a given reference trajectory very well. Moreover, it results in very good disturbance rejection.
The synthesis of Nb-doped TiO2 nanoparticles by spray drying: an efficient and scalable method
(2011)
User-centered and Participatory Design approaches have become widespread within HCI, also when designing digital media for older adults. These methodologies are seen as crucial to adapt technology design to older people's needs and increase their acceptance of digital technology. Nevertheless, it is often difficult to reach a diverse group of older people, for instance, people with limited technology skills, limited mobility, or cognitive issues. In addition, gerontologists criticized lately how older people's participation unfolds in technology design projects, e.g. that people are pushed into the role of users. Little is known about the motivations and needs of older adults regarding their participation in HCI research. To close this gap, we conducted an online survey (N=46) and semi-structured interviews (N=8) focusing on motivations, willingness and experiences regarding participation. Results show that people are generally willing to participate due to interest in the topic, learning new things and social bonding. However, despite the conceptions within HCI that long-term engagement is crucial within participatory design, older people in the study preferred less commitment and more open formats.
A filtering model for efficient rendering of the spatial image of an occluded virtual sound source
(1999)
Rendering realistic spatial sound imagery for complex virtual environments must take into account the effects of obstructions such as reflectors and occluders. It is relatively well understood how to calculate the acoustical consequence that would be observed at a given observation point when an acoustically opaque object occludes a sound source. But the interference patterns generated by occluders of various geometries and orientations relative to the virtual source and receiver are computationally intense if accurate results are required. In many applications, however, it is sufficient to create a spatial image that is recognizable by the human listener as the sound of an occluded source. In the interest of improving audio rendering efficiency, a simplified filtering model was developed and its audio output submitted to psychophysical evaluation. Two perceptually salient components of occluder acoustics were identified that could be directly related to the geometry and orientation of a simple occluder. Actual occluder impulse responses measured in an anechoic chamber resembled the responses of a model incorporating only a variable duration delay line and a low-pass filter with variable cutoff frequency.
A filtering model for efficient rendering of the spatial image of an occluded virtual sound source
(1999)
Rendering realistic spatial sound imagery for complex virtual environments must take into account the effects of obstructions such as reflectors and occluders. It is relatively well understood how to calculate the acoustical consequence that would be observed at a given observation point when an acoustically opaque object occludes a sound source. But the interference patterns generated by occluders of various geometries and orientations relative to the virtual source and receiver are computationally intense if accurate results are required. In many applications, however, it is sufficient to create a spatial image that is recognizable by the human listener as the sound of an occluded source. In the interest of improving audio rendering efficiency, a simplified filtering model was developed and its audio output submitted to psychophysical evaluation. Two perceptually salient components of occluder acoustics were identified that could be directly related to the geometry and orientation of a simple occluder. Actual occluder impulse responses measured in an anechoic chamber resembled the responses of a model incorporating only a variable duration delay line and a low-pass filter with variable cutoff frequenc
Given limited computational resources available for the rendering of spatial sound imagery, we seek to determine effective means for choosing whatcomponents of the rendering will provide the most audible differences in the results. Rather than begin with an analytic approach that attempts to predict audible differences on the basis of objective parameters, we chose to begin with subjective tests of how audibly different the rendering result may be heard to be when that result includes two types of sound obstruction: reflectors and occluders. Single-channel recordings of 90 short speech sounds were made in an anechoic chamber in the presence and absence of these two types of obstructions, and as the angle of those obstructions varied over a 90 degree range. These recordings were reproduced over a single loudspeaker in that anechoic chamber, and listeners were asked to rate how confident they were that the recording of each of these 90 stimuli included an obstruction. These confidence ratings can be used as an integral component in the evaluation function used to determine which reflectors and occluders are most important for rendering.
The concept of Zero Energy Building (ZEB) has gained wide international attention during last few years and is now seen as the future target for the design of buildings. However, before being fully implemented in the national building codes and international standards, the ZEB concept requires clear and consistent definition and a commonly agreed energy calculation methodology. The most important issues that should be given special attention before developing anewZEB definition are: (1) the metric of the balance, (2) the balancing period, (3) the type of energy use included in the balance, (4) the type of energy balance, (5) the accepted renewable energy supply options, (6) the connection to the energy infrastructure and (7) the requirements for the energy efficiency, the indoor climate and in case of gird connected ZEB for the building–grid interaction. This paper focuses on the review of the most of the existing ZEB definitions and the various approaches towards possible ZEB calculation methodologies. It presents and discusses possible answers to the abovementioned issues in order to facilitate the development of a consistent ZEB definition and a robust energy calculation methodology.
The international cooperation project IEA SHC Task 40 / ECBCS Annex 52 “Towards Net Zero Energy Solar Buildings”, attempts to develop a common understanding and to set up the basis for an international definition framework of Net Zero Energy Buildings (Net ZEBs). Th e understanding of such buildings and how the Net ZEB status should be calculated differs in most countries. This paper presents an overview of Net ZEBs energy calculation methodologies proposed by organisations representing eight different countries: Austria, Canada, Denmark, Germany, Italy, Norway, Switzerland and the USA. The different parameters used in the calculations are discussed and the various renewable supply options considered in the methodologies are summarised graphically. Thus, the paper helps to understand different existing approaches to calculate energy balance in Net ZEBs, highlights the importance of variables selection and identify possible renewable energy supply options which may be considered in calculations. Finally, the gap between the methodology proposed by each organisation and their respective national building code is assessed; providing an overview of the possible changes building codes will need to undergo in the coming years.
In this paper we introduce a system for tracking persons walking or standing on a large planar surface and for using the acquired data to easily configure position based interactions for virtual studio productions. The tracking component of the system, radarTRACK, is based on a laser scanner device capable of delivering interaction points on a large configurable plane. By using the device on the floor it is possible to use the delivered data to detect feet positions and derive the position and orientation of one or more users in real time. The second component of the system, named OscCalibrator, allows for the easy creation of multidimensional linear mappings between input and output parameters and the routing of OSC messages within a single modular design environment. We demonstrate the use of our system to flexibly create position-based interactions in a virtual studio environment.
Female employment, reconciliation policies, and childbearing intentions in East and West Germany.
(2013)
Singing in different rooms: Common or individual adaptation patterns to the acoustic conditions?
(2020)
This paper presents an approach to integrate non-visual user feedback in today's virtual tv studio productions. Since recent studies showed that systems providing vibro-tactile feedback are not sufficient for replacing the common visual feedback, we developed an audio-based solution using an in ear headphone system, enabling a talent to move, avoid and point to virtual objects in a blue or green box. The system consists of an optical head tracking system, a wireless in ear monitor system and a workstation, which performs all application and audio processing. Using head related transfer functions, the talent gets directional and distance cues. Past research showed, that generating reflections of the sounds and simulating the acoustics of the virtual room helps the listener to conceive the acoustical feedback, we included this technique as well. In a user study with 15 participants the performance of the system was evaluated.
Higher control engineering concepts, including artificial intelligence and model-based control, are recently becoming more popular in complex industrial applications because they enable a significant increase in efficiency. E.g., a model-based approach can be used to enhance the control and monitoring of several coupled components of a larger turbomachinery train. This requires dynamic models of the components, including all machine characteristics, which may experience a shift in their behavior over the course of their lifetime. Such changes occur due to natural fouling, wear of sub-components or external effects induced by maintenance measures. To overcome this problem, we model machine-characteristic maps with artificial neural networks, which may be used as part of prediction models in a model predictive control unit. If an appropriate data set is available, this allows us to adapt the model to the current behavior of the machine without requiring in-depth knowledge about the underlying physics of this “concept drift”, as it is known in literature. However, the training of neural networks is usually connected with high computational effort while the task needs to be executed in real-time during operation. Furthermore, in real operating conditions, machine sensors can only provide labeled data from the current operating point of the machine, which can be stationary for long operation periods of up to several months. In general, this yields only an unrepresentative data subset of the machine-characteristics, which is not sufficient to retrain the whole model to a new state. To solve these problems, we firstly reduce the model adaptation to a convex optimization problem, which can be efficiently solved in real-time conditions. Secondly, we use a specialized data management system with which we can integrate historical data to supplement the unrepresentative data subset. In this paper we show the application of the outlined method on a compressor map and discuss the advantages and requirements of the method in the context of modeling applications for industrial turbomachinery.