Fraunhofer-Institut für Angewandte Informationstechnik FIT

Filters
2
2
Reset filters

Settings
Now showing 1 - 2 of 2
No Thumbnail Available
Publication

Economic Perspective on Algorithm Selection for Predictive Maintenance

2019 , Fabri, Lukas , Häckel, Björn , Oberländer, Anna Maria , Töppel, Jannick , Zanker, Patrick

The increasing availability of data and computing capacity drives optimization potential. In the industrial context, predictive maintenance is particularly promising and various algorithms are available for implementation. For the evaluation and selection of predictive maintenance algorithms, hitherto, statistical measures such as absolute and relative prediction errors are considered. However, algorithm selection from a purely statistical perspective may not necessarily lead to the optimal economic outcome as the two types of prediction errors (i.e., alpha error ignoring system failures versus beta error falsely indicating system failures) are negatively correlated, thus, cannot be jointly optimized and are associated with different costs. Therefore, we compare the prediction performance of three types of algorithms from an economic perspective, namely Artificial Neural Networks, Support Vector Machines, and Hotelling T² Control Charts. We show that the translation of statistical measures into a single cost-based objective function allows optimizing the individual algorithm parametrization as well as the un-ambiguous comparison among algorithms. In a real-life scenario of an industrial full-service provider we derive cost advantages of more than 17% compared to an algorithm selection based on purely statistical measures. This work contributes to the theoretical and practical knowledge on predictive maintenance algorithms and supports predictive maintenance investment decisions.

View
No Thumbnail Available
Publication

Development of dynamic key figures for the identification of critical components in smart factory information networks

2017 , Häckel, Björn , Miehle, Daniel , Pfosser, Stefan , Übelhör, Jochen

Informational risks in smart factories arise from the growing interconnection of its components, the increasing importance of real-time accessibility and exchange of information, and highly dynamic and complex information networks. Thereby, physical production more and more depends on functioning information networks due to increasing informational dependencies. Accordingly, the operational capability of smart factories and their ability to create economic value heavily depend on its information network. Thus, information networks of smart factories have to be evaluated regarding informational risks as a first prerequisite for subsequent steps regarding the management of a smart factory. In this paper, we focus on the identification of critical components in information networks based on key figures that quantitatively depict the availability of the information network. To enable analyses regarding dynamic effects, the developed key figures cover dynamic propagation and recovery effects. To demonstrate their applicability, we investigate two possible threat scenarios in an exemplary information net-work. Further, we integrated the insights of two expert interviews of two global companies in the automation and packaging industry. The results indicate that the developed key figures offer a promising approach to better analyse and understand informational risks in smart factory information networks.

View