Sensors

This article describes a predictive maintenance approach in which a flexible sensor toolkit records and a prediction model monitors the component wear within technical systems. The condition of the components is not determined continuously, but based on time-discrete measurements. The prediction model predicts the presumable remaining useful life of the components based on the recorded data. A machine learning tool is trained with historical wear curves and used to generate the prediction. The training data is collected through statistical tests in which the influencing variables and characteristic curves of different types of wear are identified.

In process engineering, one thinks of production operations that are controlled or regulated by sensors and actuators. And any realization of matter transformation is based on a physical substratum, which holds equally for living systems and their behaviour. The article distinguishes between three system levels: the functional level, the interface to the environment and the cognitive level of. Using these three levels, the learning cycle or the previous Cognitive Loop can be very well illustrated. If one compares with this way of distinction the Bio-Informatization of human intelligence with the technical development stages of mechanization, automation, regulation and deep learning, then the cybernetic-sociological term “operational closure” becomes understandable. It becomes obvious that in the context of a digitized culture of production and organization, we should be prepared for a new kind of cognitive loop based on silicon (SI), an intelligent system behavior via ...

The growing amount of available data due to the digitalization of value creation is accelerating the transformation of manufacturing industries into providers of customer-oriented services. Smart services, currently the most highly developed level of data-based digital services to complement physical products for specific customer expectations, are an example of this. However, the analysis of expert interviews as well as of use cases from business practice shows that the knowledge of how such smart services can be developed is still rudimentary. This article presents a framework for Smart Service Lifecycle Management that supports the systematic development of Smart Services, taking into account business models and the value network. The framework concept will be implemented and validated based on an application example from the textile industry.

In this contribution, a method for the implementation of Industry 4.0 projects in production and logistics for small and medium-sized enterprises (SME) is described. This method takes various boundary conditions of SMEs into consideration and has been applied in different projects with SMEs within the “Mittelstand 4.0-Kompetenzzentrum Hamburg” initiative. The method focuses on an integration of new technologies into existing systems and the connection of newly generated data with known information flows.

In transport logistics the utilization of transports is often unknown. As a consequence it is not possible to use this information during the transport planning phase and it cannot be used for operational transport control. This report describes technologies which can measure the utilization of shipping spaces. Due to the lack of market-ready systems, a new system was developed that uses ultrasonic sensors to determine the transport utilization. The system was built on a trailer and was tested during live operation. It was shown that the system fulfills the given requirements and it is suggested to expand the tests.