use cases

Federated Service Engineering

Federated Service Engineering

A development methodology for the realization of mobility applications in the Gaia-X decentralized data ecosystem
Christoph Heinbach, Michael Pahl, Oliver Thomas
The decentralized data ecosystem Gaia-X, which is currently under development, supports the future viability of the digital data economy in Europe. But how can relevant use cases be realized in Gaia-X from a service-oriented perspective? To answer this question, this article presents a methodology that describes a structured and interdisciplinary approach to service development in the ongoing Gaia-X 4 ROMS consortium research project [1]. In this project, federated services are realized in five processing steps on the basis of use cases. IT experts, software developers and industry users can leverage the model to efficiently coordinate the joint realization of use cases with Gaia-X and the goal of sovereign data exchange.
Industry 4.0 Science | Volume 40 | 2024 | Edition 2 | Pages 40-47
A Machine Learning Compass for Product Development and Production

A Machine Learning Compass for Product Development and Production

Identification and planning of machine learning algorithms in manufacturing companies
Alexander Jacob, Carmen Krahe, Rebecca Funk, Gisela Lanza ORCID Icon
Engineers are often uncertain about the application of machine learning (ML) due to the amount of different machine learning methods and the complexity of modeling. Thus, the use of ML applications in manufacturing companies remains behind the technical possibilities. This paper presents an intuitive ML guideline for engineers to reduce this uncertainty. The guideline comprises a process model with AI-based solutions to common problems of product development and production. An industrial example is used to demonstrate the functionality and the possibilities of the guide.
Industrie 4.0 Management | Volume 37 | 2021 | Edition 2 | Pages 7-11
Machine Learning in Production

Machine Learning in Production

Application areas and freely available data sets
Hendrik Mende, Jonas Dorißen, Jonathan Krauß, Maik Frye, Robert Schmitt ORCID Icon
Data sets increasing data bases and computing power as well as decreasing costs for computing and storage capacities form the basis for the use of Machine Learning (ML) in production. The challenges are the identification of promising application areas, the recognition of the associated learning tasks as well as the uncovering of suitable data sets. This article therefore answers the following questions: Which application areas in production offer the greatest potential for the use of ML? Which freely accessible data sets are suitable for gaining experience and which learning tasks are associated with them? What are best practices for the application areas?
Industrie 4.0 Management | Volume 35 | 2019 | Edition 4 | Pages 39-42 | DOI 10.30844/I40M_19-4_S39-42