Refine
Year of publication
- 2020 (30) (remove)
Document Type
- Journal article (29)
- Book chapter (1)
Language
- English (30) (remove)
Is part of the Bibliography
- yes (30)
Institute
- Informatik (10)
- ESB Business School (9)
- Life Sciences (8)
- Technik (3)
Publisher
- Elsevier (30) (remove)
Process quality has reached a high level on mass production, utilizing well known methods like the DoE. The drawback of the unterlying statistical methods is the need for tests under real production conditions, which cause high costs due to the lost output. Research over the last decade let to methods for correcting a process by using in-situ data to correct the process parameters, but still a lot of pre-production is necessary to get this working. This paper presents a new approach in improving the product quality in process chains by using context data - which in part are gathered by using Industry 4.0 devices - to reduce the necessary pre-production.
The data presented in this article characterize the thermomechanical and microhardness properties of a novel melamine-formaldehyde resin (MF) intended for the use as a self-healing surface coating. The investigated MF resin is able to undergo reversible crosslinking via Diels Alder reactive groups. The microhardness data were obtained from nanoindentation measurements performed on solid resin film samples at different stages of the self-healing cycle. Thermomechanical analysis was performed under dynamic load conditions. The data provide supplemental material to the manuscript published by Urdl et al. 2020 (https://doi.org/10.1016/j.eurpolymj.2020.109601) on the self-healing performance of this resin, where a more thorough discussion on the preparation, the properties of this coating material and its application in impregnated paper-based decorative laminates can be found.
We investigated the state of artificial intelligence (AI) in pharmaceutical research and development (R&D) and outline here a risk and reward perspective regarding digital R&D. Given the novelty of the research area, a combined qualitative and quantitative research method was chosen, including the analysis of annual company reports, investor relations information, patent applications, and scientific publications of 21 pharmaceutical companies for the years 2014 to 2019. As a result, we can confirm that the industry is in an ‘early mature’ phase of using AI in R&D. Furthermore, we can demonstrate that, despite the efforts that need to be managed, recent developments in the industry indicate that it is worthwhile to invest to become a ‘digital pharma player’.
The use of learning factories for education in maintenance concepts is limited, despite the important role maintenance plays in the effective operation of organizational assets. A training programme in a learning factory environment is presented where a combination of gamification, classroom training and learning factory applications is used to introduce students to the concepts of maintenance plan development, asset failure characteristics and the costs associated with maintenance decision-making. The programme included a practical task to develop a maintenance plan for different advanced manufacturing machines in a learning factory setting. The programme stretched over a four-day period and demonstrated how learning factories can be effectively utilized to teach management related concepts in an interdisciplinary team context, where participants had no, or very limited, previous exposure to these concepts.
Zero or plus energy office buildings must have very high building standards and require highly efficient energy supply systems due to space limitations for renewable installations. Conventional solar cooling systems use photovoltaic electricity or thermal energy to run either a compression cooling machine or an absorption-cooling machine in order to produce cooling energy during daytime, while they use electricity from the grid for the nightly cooling energy demand. With a hybrid photovoltaic-thermal collector, electricity as well as thermal energy can be produced at the same time. These collectors can produce also cooling energy at nighttime by longwave radiation exchange with the night sky and convection losses to the ambient air. Such a renewable trigeneration system offers new fields of applications. However, the technical, ecological and economical aspects of such systems are still largely unexplored.
In this work, the potential of a PVT system to heat and cool office buildings in three different climate zones is investigated. In the investigated system, PVT collectors act as a heat source and heat sink for a reversible heat pump. Due to the reduced electricity consumption (from the grid) for heat rejection, the overall efficiency and economics improve compared to a conventional solar cooling system using a reversible air-to-water heat pump as heat and cold source.
A parametric simulation study was carried out to evaluate the system design with different PVT surface areas and storage tank volumes to optimize the system for three different climate zones and for two different building standards. It is shown such systems are technically feasible today. With a maximum utilization of PV electricity for heating, ventilation, air conditioning and other electricity demand such as lighting and plug loads, high solar fractions and primary energy savings can be achieved.
Annual costs for such a system are comparable to conventional solar thermal and solar electrical cooling systems. Nevertheless, the economic feasibility strongly depends on country specific energy prices and energy policy. However, even in countries without compensation schemes for energy produced by renewables, this system can still be economically viable today. It could be shown, that a specific system dimensioning can be found at each of the investigated locations worldwide for a valuable economic and ecological operation of an office building with PVT technologies in different system designs.
Artificial Intelligence-based Assistants AIAs are spreading quickly both in homes and offices. They already have left their original habitats of "intelligent speakers" providing easy access to music collections. The initiated a multitude of new devices and are already populating devices such as TV sets. Characteristic for the intelligent digital assistants is the formation of platforms around their core functionality. Thus, AIS capabilities of the assistants are used to offer new services and create new interfaces for business processes. There are positive network effects between the assistants and the services as well as within the services. Therefore, many companies see the need to get involved in the field of digital assistants but lack a framework to align their initiatives with their corporate strategies. In order to lay the foundation for a comprehensive method, we are therefore investigating intelligent digital assistants. Based on this analysis, we are developing a framework of strategic opportunities and challenges.
Globalisation, shorter product life cycles, and increasing product varieties have led to complex supply chains. At the same time, there is a growing interest of customers and governments in having a greater transparency of brands, manufacturers, and producers throughout the supply chain. Due to the complex structure of collaborative manufacturing networks, the increase of supply chain transparency is a challenge for manufacturing companies. The blockchain technology offers an innovative solution to increase the transparency, security, authenticity, and auditability of products. However, there are still uncertainties when applying the blockchain technology to manufacturing scenarios and thus enable all stakeholders to trace back each component of an assembled product. This paper proposes a framework design to increase the transparency and auditability of products in collaborative manufacturing networks by adopting the blockchain technology. In this context, each component of a product is marked with a unique identification number generated by blockchain-based smart contracts. In this way, a transparent auditability of assembled products and their components can be achieved for all stakeholders, including the custome.
On the design of an urban data and modeling platform and its application to urban district analyses
(2020)
An integrated urban platform is the essential software infrastructure for smart, sustainable and resilitent city planning, operation and maintenance. Today such platforms are mostly designed to handle and analyze large and heterogeneous urban data sets from very different domains. Modeling and optimization functionalities are usually not part of the software concepts. However, such functionalities are considered crucial by the authors to develop transformation scenarios and to optimized smart city operation. An urban platform needs to handle multiple scales in the time and spatial domain, ranging from long term population and land use change to hourly or sub-hourly matching of renewable energy supply and urban energy demand.
Human bestrophin-1 (hBest1) is a transmembrane Ca2+- dependent anion channel, associated with the transport of Cl−, HCO3- ions, γ-aminobutiric acid (GABA), glutamate (Glu), and regulation of retinal homeostasis. Its mutant forms cause retinal degenerative diseases, defined as Bestrophinopathies. Using both physicochemical - surface pressure/mean molecular area (π/A) isotherms, hysteresis, compressibility moduli of hBest1/sphingomyelin (SM) monolayers, Brewster angle microscopy (BAM) studies, and biological approaches - detergent membrane fractionation, Laurdan (6-dodecanoyl-N,N-dimethyl-2-naphthylamine) and immunofluorescence staining of stably transfected MDCK-hBest1 and MDCK II cells, we report:
1) Ca2+, Glu and GABA interact with binary hBest1/SM monolayers at 35 °C, resulting in changes in hBest1 surface conformation, structure, self-organization and surface dynamics. The process of mixing in hBest1/SM monolayers is spontaneous and the effect of protein on binary films was defined as “fluidizing”, hindering the phase-transition of monolayer from liquid-expanded to intermediate (LE-M) state;
2) in stably transfected MDCK-hBest1 cells, bestrophin-1 was distributed between detergent resistant (DRM) and detergent-soluble membranes (DSM) - up to 30 % and 70 %, respectively; in alive cells, hBest1 was visualized in both liquid-ordered (Lo) and liquid-disordered (Ld) fractions, quantifying protein association up to 35 % and 65 % with Lo and Ld. Our results indicate that the spontaneous miscibility of hBest1 and SM is a prerequisite to diverse protein interactions with membrane domains, different structural conformations and biological functions.
The evaluation of the effectiveness of different machine learning algorithms on a publicly available database of signals derived from wearable devices is presented with the goal of optimizing human activity recognition and classification. Among the wide number of body signals we choose a couple of signals, namely photoplethysmographic (optically detected subcutaneous blood volume) and tri-axis acceleration signals that are easy to be simultaneously acquired using commercial widespread devices (e.g. smartwatches) as well as custom wearable wireless devices designed for sport, healthcare, or clinical purposes. To this end, two widely used algorithms (decision tree and k-nearest neighbor) were tested, and their performance were compared to two new recent algorithms (particle Bernstein and a Monte Carlo-based regression) both in terms of accuracy and processing time. A data preprocessing phase was also considered to improve the performance of the machine learning procedures, in order to reduce the problem size and a detailed analysis of the compression strategy and results is also presented.
Papermaking waste liquid (black liquor) is a serious source of water pollution worldwide. The subsequent treatment of it is very difficult cause it contains a large amount of lignin, inorganic salts, organic matter, and pigments, which lead to serious water pollution. Lignin is the main by-product of the paper industry and is the only natural aromatic recyclable resource. Its effective utilization rate is currently less than 3%. Therefore, how to effectively recycle lignin in papermaking waste liquid and further synthesize industrialized products is of great significance to the sustainable development and environmental protection. Besides, based on the shortage of petroleum resources in recent years, the application of biomass resources instead of petroleum resources in the industry is also an important issue. In this article, we explored the best optimal conditions for the oxypropylation and esterification of lignin, and prepared bio-bitumen based on modified lignin, and then applied it to the waterproof coating sheets. FTIR and mechanical properties (softening point, low-temperature flexibility, peel strength, etc.) were tested on the obtained waterproof coating sheets. The results show that the addition of modified lignin reduced the softening point and peel strength of the coating sheets. Interestingly, both oxypropylated lignin (OL) and esterified lignin (OEL) were very beneficial to resist the decrease in peel strength during the aging process, showing a significant improvement in the performance of the coating sheets after aging compared to the control.
Concrete is significant for construction. A problem in application is the appearance of cracks that will damage its strength. An autogenous crack-healing mechanism based on bacteria receives increasing attention in recent years. The bacteria are able to form calcium carbonate (CaCO3) precipitations in suitable conditions to protect and reinforce the concrete. However, a large number of spores are crushed in aged specimens, resulting in a loss of viability. A new kind of hydrogel crosslinked by alginate, chitosan and calcium ions was introduced in this study. It was observed that the addition of chitosan improved the swelling properties of calcium alginate. Opposite pH response to calcium alginate was observed when the chitosan content in the solution reached 1.0%. With an addition of 1.0% chitosan in hydrogel beads, 10.28% increase of compressive strength and 13.79% increase of flexural strength to the control were observed. The results reveal self-healing properties of concretes. A healing crack of 4 cm length and 1 mm width was observed when using cement PO325, with the addition of bacterial spores (2.54–3.07 × 105/cm3 concrete) encapsulated by hydrogel containing no chitosan.
Hypothesis
The origin of negative surface charge at water/air interface is still not clear. The most probable origin is specific adsorption of OH− ions. From diffuse layer potential, we can evaluate the surface density of ions in the Stern layer which can be a measure for the specific adsorption of ions and determines whether the surface charge is solely due to the specific adsorption of OH− ions.
Experiments
Equilibrium thickness of foam films of pure water and aqueous solutions of NaCl, HCl, and NaOH was measured as a function of disjoining pressure for water and as a function of concentration for the aqueous solutions at 298.15 K. Quartz-glass cells thoroughly cleaned and immersed in pure water before use were used for the measurement.
Findings
Application of a modified Poisson-Boltzmann equation to the equilibrium film thickness gave the diffuse layer potential and the surface density of ions in the Stern layer. From the concentration dependence of the surface density, it was concluded that not only OH− ions but also Cl− ions and HCO3− and/or CO32− ions adsorb specifically at the water/air interface.
Traditional communication of research on climate change fails to encourage individual, corporate, and political leaders to take appropriate action. We argue that this problem is based on an overly simplistic unidirectional model of science communication. Conversely, theory shows that active learning processes are better suited to initiate and mobilize engagement among all stakeholders. Here, we integrate theoretical insights on active learning with empirical evidence from serious gaming: communication should be understood as an integral design feature that relates active learning on climate change to tangible action.
In an effort to make the cultural and institutional aspects of energy efficiency in industrial organizations more visible, this article introduces a theoretical framework of decision-making processes. Taking a sociological perspective and viewing organizations as cultural systems embedded in wider social contexts, I have developed a multilevel framework addressing institutional, organizational, and individual dimensions shaping decisions on energy efficiency. The framework's development is based on qualitative empirical fieldwork and integrates insights into organizational theory; neo-institutional theory, the attention-based view of the firm, and organizational culture theories. I conclude that decisions on energy efficiency are results of problematization and theorization processes. These processes emerge between the institutional issue-field, the organization, and its members. The model explains decisions shaped by environment (external and material), organizational processes (energy-efficiency practices, climate and culture) and individuals’ characteristics. The framework serves several purposes: introducing a meta-theory of decision making, providing a concept for empirical analysis, and enabling connectivity to the research on barriers.
Here, we report the continuous peroxide-initiated grafting of vinyltrimethoxysilane (VTMS) onto a standard polyolefin by means of reactive extrusion to produce a functionalized liquid ethylene propylene copolymer (EPM). The effects of the process parameters governing the grafting reaction and their synergistic interactions are identified, quantified and used in a mathematical model of the extrusion process. As process variables the VTMS and peroxide concentrations and the extruder temperature setting were systematically studied for their influence on the grafting and the relative grafting degree using a face-centered central composite design (FCD). The grafting degree was quantified by 1H NMR spectroscopy. Response surface methodology (RSM) was used to calculate the most efficient grafting process in terms of chemical usage and graft yield. With the defined processing window, it was possible to make precise predictions about the grafting degree with at the same time highest possible relative degree of grafting.
The self-healing effect of melamine-based surfaces, triggered by temperature, was investigated. The temperature triggered reversible healing chemistry, on which the self-healing effect is based, was the Diels-Alder (DA) reaction between furan and malemeide groups. Melamine-furan containing building blocks were connected by multi-functional maleimide crosslinker via a Diels-Alder (DA) reaction to giva a DA adduct. The DA adduct was then reacted with formaldehyde to form a network by conventional condensation reaction of melamine amino groups with formaldehyde. The obtained resin was characterised and used for the impregnation of paper. Impregnated papers and neat resin werde used to perform scratch-healing tests and mechanical analysis of the novel coating system.
The approach of self-organized and autonomous controlled systems offers great potential to meet new requirements for the economical production of customized products with small batch sizes based on a distributed, flexible management of dynamics and complexity within the production and intralogistics system. To support the practical application of self-organization for intralogistics systems, a catalogue of criteria for the evaluation of the self-organization of flexible logistics systems has been developed and validated, which enables the classification of logistics systems as well as the identification and evaluation of corresponding potentials that can be achieved by increasing the degree of self-organization.
Rapidly changing market conditions and global competition are leading to an increasing complexity of logistics systems and require innovative approaches with respect to the organisation and control of these systems. In scientific research, concepts of autonomously controlled logistics systems show a promising approach to meet the increasing requirements for flexible and efficient order processing. In this context, this work aims to introduce a system that is able to adjust order processing dynamically, and optimise intralogistics transportation regarding various generic intralogistics target criteria. The logistics system under consideration consists of various means of transport for autonomous decision-making and fulfilment of transport orders with defined source-sink relationships. The context of this work is set by introducing the Learning Factory Werk 150 with its existing hardware and software infrastructure and its defined target figures to measure the performance of the system. Specifically, the important target figures cost and performance are considered for the transportation system. The core idea of the system’s logic is to solve the problem of order allocation to specific means of transport by linking a Genetic Algorithm with a Multi-Agent System. The implementation of the developed system is described in an application scenario at the learning factory.
Driven by digital transformation, manufacturing systems are heading towards autonomy. The implementation of autonomous elements in manufacturing systems is still a big challenge. Especially small and medium sized enterprises (SME) often lack experience to assess the degree of Autonomous Production. Therefore, a description model for the assessment of stages for Autonomous Production has been identified as a core element to support such a transformation process. In contrast to existing models, the developed SME-tailored model comprises different levels within a manufacturing system, from single manufacturing cells to the factory level. Furthermore, the model has been validated in several case studies.
The generous feed-in tariffs (FiTs) introduced in Germany—which resulted in major growth in decentralized solar photovoltaic (PV) systems—will phase out in the coming years, making many of the existing distributed generation assets stranded. This challenge creates an opportunity for community-focused energy utilities, such as Elektrizitätswerke Schönau eG (EWS) based in Schönau, Germany, to try a new approach to assist its customers, makes the transition to a more sustainable future. This chapter describes how EWS is developing products and offering community-based solutions including peer-to-peer trading using automated platforms. Such innovative offering may lead to successful differentiation in a competitive and highly decentralized future.
Learning factories can complement each other by training different competencies in the field of digitalisation and Industry 4.0. They depict diverse sections of the product development process and focus on various technologies. Within the framework of the International Association of Learning Factories (IALF), the operating organisations of learning factories exchange information on research, training and education. One of the aims is to develop joint projects. The article presents different concepts of cooperation between learning factories while focusing on the improvement of the development of learners competencies e.g. with a broader range of topics. A concept of a joint course between the learning factories in Bochum, Reutlingen and Darmstadt is explained in detail. The three learning factories will be examined with regard to their similarities and differences. The joint course focuses on the target group of students and the topic of digitalisation in the development and production of products. The course and its contents are explained in detail. The new learning approach is evaluated on the basis of feedback from the participants. Finally, challenges resulting from the cooperation between learning factories at different locations and with different operating models will be discussed.
Comparison of sleep characteristics measurements: a case study with a population aged 65 and above
(2020)
Good sleep is crucial for a healthy life of every person. Unfortunately, its quality often decreases with aging. A common approach to measuring the sleep characteristics is based on interviews with the subjects or letting them fill in a daily questionnaire and afterward evaluating the obtained data. However, this method has time and personal costs for the interviewer and evaluator of responses. Therefore, it would be important to execute the collection and evaluation of sleep characteristics automatically. To do that, it is necessary to investigate the level of agreement between measurements performed in a traditional way using questionnaires and measurements obtained using electronic monitoring devices. The study presented in this manuscript performs this investigation, comparing such sleep characteristics as "time going to bed", "total time in bed", "total sleep time" and "sleep efficiency". A total number of 106 night records of elderly persons (aged 65+) were analyzed. The results achieved so far reveal the fact that the degree of agreement between the two measurement methods varies substantially for different characteristics, from 31 minutes of mean difference for "time going to bed" to 77 minutes for "total sleep time". For this reason, a direct exchange of objective and subjective measuring methods is currently not possible.
In previous studies, we used a method for detecting stress that was based exclusively on heart rate and ECG for differentiation between such situations as mental stress, physical activity, relaxation, and rest. As a response of the heart to these situations, we observed different behavior in the Root Mean Square of the Successive differences heartbeats (RMSSD). This study aims to analyze Virtual Reality via a virtual reality headset as an effective stressor for future works. The value of the Root Mean Square of the Successive Differences is an important marker for the parasympathetic effector on the heart and can provide information about stress. For these measurements, the RR interval was collected using a breast belt. In these studies, we can observe the Root Mean Square of the successive differences heartbeats. Additional sensors for the analysis were not used. We conducted experiments with ten subjects that had to drive a simulator for 25 minutes using monitors and 25 minutes using virtual reality headset. Before starting and after finishing each simulation, the subjects had to complete a survey in which they had to describe their mental state. The experiment results show that driving using virtual reality headset has some influence on the heart rate and RMSSD, but it does not significantly increase the stress of driving.
Automatic anode rod inspection in aluminum smelters using deep-learning techniques: a case study
(2020)
Automatic fault detection using machine learning has become an exciting and promising area of research. This because it accurate and timely way to manage and classify with minimal human effort. In the computer vision community, deep-learning methods have become the most suitable approaches for this task. Anodes are large carbon blocks that are used to conduct electricity during the aluminum reduction process. The most basic function of anode rod inspection is to prevent a situation where the anode rod will not fit into the stub-holes of a new anode. It would be the case for a rod containing either severe toe-in, missing stubs, or a retained thimble on one or more stubs. In this work, to improve the accuracy of shape defect inspection for an anode rod, we use the Fast Region-based Convolutional Network method (Fast R-CNN), model. To train the detection model, we collect an image dataset composed of multi-class of anode rod defects with annotated labels. Our model is trained using a small number of samples, an essential requirement in the industry where the number of available defective samples is limited. It can simultaneously detect multi-class of defects of the anode rod in nearly real-time.
Based on a survey among customers of seven German municipal utilities, we estimate two regression models to identify the most prospective customer segments and their preferences and motivations for participating in peer-to-peer (P2P) electricity trading and develop implications for decision-makers in the energy sector and policy-makers for this currently relatively unknown product. Our results show a large general openness of private households towards P2P electricity trading, which is also the main predictor of respondents' intention to participate. It is mainly influenced by individuals’ environmental attitude, technical interest, and independence aspiration. Respondents with the highest willingness to participate in P2P electricity trading are mainly motivated by the ability to share electricity, and to a lesser extent by economic reasons. They also have stronger preferences for innovative pricing schemes (service bundles, time-of-use tariffs). Differences between individuals can be observed depending on their current ownership (prosumers) or installation probability of a microgeneration unit (consumers, planners). Rather than current prosumers, especially planners willing to install microgeneration in the foreseeable future are considered to be the most promising target group for P2P electricity trading. Finally, our results indicate that P2P electricity trading could be a promising niche option in the German energy transition.
Development work within an experimental environment, in which certain properties are investigated and optimized, requires many test runs and is therefore often associated with long execution times, costs and risks. This can affect product, material and technology development in industry and research. New digital driver technologies offer the possibility to automate complex manual work steps in a cost-effective way, to increase the relevance of the results and to accelerate the processes many times over. In this context, this article presents a low-cost, modular and open-source machine vision system for test execution and evaluates it on the basis of a real industrial application. For this purpose a methodology for the automated execution of the load intervals, the process documentation and for the evaluation of the generated data by means of machine learning to classify wear levels. The software and the mechanical structure are designed to be adaptable to different conditions, components and for a variety of tasks in industry and research. The mechanical structure is required for tracking the test object and represents a motion platform with independent positioning by machine vision operators or machine learning. An evaluation of the state of the test object is performed by the transfer learning after the initial documentation run. The manual procedure for classifying the visually recorded data on the state of the test object is described for the training material. This leads to an increased resource efficiency on the material as well as on the personnel side since on the one hand the significance of the tests performed is increased by the continuous documentation and on the other hand the responsible experts can be assigned time efficiently. The presence and know-how of the experts are therefore only required for defined and decisive events during the execution of the experiments. Furthermore, the generated data are suitable for later use as an additional source of data for predictive maintenance of the developed object.
This work is a study about a comparison of survey tools and it should help developers in selecting a suited tool for application in an AAL environment. The first step was to identify the basic required functionality of the survey tools used for AAL technologies and to compare these tools by their functionality and assignments. The comparative study was derived from the data obtained, previous literature studies and further technical data. A list of requirements was stated and ordered in terms of relevance to the target application domain. With the help of an integrated assessment method, the calculation of a generalized estimate value was performed and the result is explained. Finally, the planned application of this tool in a running project is explained.
Cardiovascular diseases are directly or indirectly responsible for up to 38.5% of all deaths in Germany and thus represent the most frequent cause of death. At present, heart diseases are mainly discovered by chance during routine visits to the doctor or when acute symptoms occur. However, there is no practical method to proactively detect diseases or abnormalities of the heart in the daily environment and to take preventive measures for the person concerned. Long-term ECG devices, as currently used by physicians, are simply too expensive, impractical, and not widely available for everyday use. This work aims to develop an ECG device suitable for everyday use that can be worn directly on the body. For this purpose, an already existing hardware platform will be analyzed, and the corresponding potential for improvement will be identified. A precise picture of the existing data quality is obtained by metrological examination, and corresponding requirements are defined. Based on these identified optimization potentials, a new ECG device is developed. The revised ECG device is characterized by a high integration density and combines all components directly on one board except the battery and the ECG electrodes. The compact design allows the device to be attached directly to the chest. An integrated microcontroller allows digital signal processing without the need for an additional computer. Central features of the evaluation are a peak detection for detecting R-peaks and a calculation of the current heart rate based on the RR interval. To ensure the validity of the detected R-peaks, a model of the anatomical conditions is used. Thus, unrealistic RR-intervals can be excluded. The wireless interface allows continuous transmission of the calculated heart rate. Following the development of hardware and software, the results are verified, and appropriate conclusions about the data quality are drawn. As a result, a very compact and wearable ECG device with different wireless technologies, data storage, and evaluation of RR intervals was developed. Some tests yelled runtimes up to 24 hours with wireless Lan activated and streaming.
In recent years, machine learning algorithms have made a huge development in performance and applicability in industry and especially maintenance. Their application enables predictive maintenance and thus offers efficiency increases. However, a successful implementation of such solutions still requires high effort in data preparation to obtain the right information, interdisciplinarity in teams as well as a good communication to employees. Here, small and medium sized enterprises (SME) often lack in experience, competence and capacity. This paper presents a systematic and practice-oriented method for an implementation of machine learning solutions for predictive maintenance in SME, which has already been validated.