Abstract
Efficient maintenance of industrial equipment requires degradation monitoring and prediction. Currently used prediction models are mostly deterministic and cannot consider uncertainty inherent to degradation measurements. In this paper we propose using time series models obtained using Facebook Prophet algorithm to predict the evolution of degradation of turbomachinery. We illustrate our considerations with data from large scale industrial centrifugal compressors. Our predictions are promising and confidence intervals cover the predictions well.
| Original language | English |
|---|---|
| Title of host publication | 2021 25th International Conference on Methods and Models in Automation and Robotics (MMAR) |
| Publisher | IEEE/AIAA |
| Pages | 321-324 |
| Number of pages | 4 |
| ISBN (Electronic) | 9781728173801 |
| DOIs | |
| Publication status | Published - 2021 |
| Externally published | Yes |
Keywords
- approximation theory
- control systems
- time-domain Oustaloup approximation
- noninteger order systems
- digital environment
- classical method
- discretization
- Approximation methods
- Transfer functions
- Eigenvalues and eigenfunctions
- Time-domain analysis
- Stability analysis
- Sensitivity