Decision support for multi-component systems: visualizing interdependencies for predictive maintenance Gashi, Milot Mutlu, Belgin Lindstaedt, Stefanie Thalmann, Stefan 2021-12-24T17:32:22Z 2021-12-24T17:32:22Z 2022-01-04
dc.description.abstract Taking dependencies between components seriously and considering the multi-component perspective instead of the single-system perspective could help to improve the results of predictive maintenance (PdM). However, modeling and identifying the interdependencies in complex industrial systems is challenging. A way to tackle this challenge and to identify interdependencies is using visualization. To the best of our knowledge, existing research on visualizing interdependencies is not applied to multi-component systems (MCS) so far. Further, it is not clear how visualization approaches can provide suitable decision support to identify interdependencies in PdM tasks. We evaluate three key visualization approaches to represent interdependencies in the context of PdM for MCS using a crowd-sourced design study in a questionnaire survey involving 530 participants. Based on our study, we were able to rank these approaches based on performance and usability for our given PdM task. The multi-line approach outperformed other approaches with respect to performance.
dc.format.extent 10 pages
dc.identifier.doi 10.24251/HICSS.2022.211
dc.identifier.isbn 978-0-9981331-5-7
dc.language.iso eng
dc.relation.ispartof Proceedings of the 55th Hawaii International Conference on System Sciences
dc.rights Attribution-NonCommercial-NoDerivatives 4.0 International
dc.subject Interactive Visual Analytics and Visualization for Decision Making
dc.subject decision support
dc.subject interdependencies
dc.subject multi-component systems
dc.subject predictive maintenance
dc.subject visualization
dc.title Decision support for multi-component systems: visualizing interdependencies for predictive maintenance
dc.type.dcmi text
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
952.32 KB
Adobe Portable Document Format