Predicting Remaining Useful Life Based on Instance-based Learning

Shahraki, Ameneh Forouzandeh; Roy, Arighna; Yadav, Om Prakash; Rathore, Ajay Pal Singh

doi:10.1109/rams.2019.8768979

Cited by 2 publications

(3 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this case, the aim is not only to show the deterioration of the component over time, but also the interdependencies effect between the components. Extensive research works focusing on PdM in the context of MCSs, which used visualization to demonstrate the presence of interdependencies can be found [9,10,11,12,13]. For instance, Assaf et al [9] used line charts to show the presence of interdependencies between components.…”

Section: Visualization For Decision Makingmentioning

confidence: 99%

“…As a result, a mathematical model for multi-component degradation modeling is presented. Shahraki et al [10] used multi-line visualizations to show interdependencies between the components within an MCS. However, none of these studies has evaluated the usefulness of visualization aiming to show and identify the interdependencies.…”

Section: Visualization For Decision Makingmentioning

confidence: 99%

“…One way to present the interdependencies in an appropriate and user-friendly way are visualization approaches [8]. In literature, some studies have used different visualizations to present the results in the context of MCS, even though the visualization of interdependencies was not the focus of these studies [9,10,11,12,13]. To the best of our knowledge, we did not find any approach tackling this particular challenge of visualizing interdependencies for MCSs.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Decision support for multi-component systems: visualizing interdependencies for predictive maintenance

Gashi¹,

Mutlu²,

Lindstaedt³

et al. 2022

Proceedings of the Annual Hawaii International Conference on System Sciences

View full text Add to dashboard Cite

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.

show abstract