Text · dataset · 2025
Comparison of Prognostic Algorithms for Estimating Remaining Useful Life of Batteries
Listed in NASA Data Portal
We were interested here in particular in conditions where un-modeled effects are present as manifested by the different degradation curve at 45°C. Although all algorithms were given the same amount of information to the degree practical, there were considerable differences in performance.
Description
Specifically, the combined Bayesian regression-estimation approach implemented as a RVM-PF framework has significant advantages over conventional methods of RUL estimation like ARIMA and EKF.
ARIMA, being a purely data-driven method, does not incorporate any physics of the process into the computation, and hence ends up with wide uncertainty margins that make it unsuitable for long-term predictions. Additionally, it may not be possible to eliminate all non-stationarity from a dataset even after repeated differencing, thus adding to prediction inaccuracy. EKF, though robust against non-stationarity, suffers from the inability to accommodate un-modeled effects and can diverge quickly as shown.
Read the rest (1 more)
We did not explore other variations of the Kalman Filter that might provide better performance such as the unscented Kalman Filter. The Bayesian statistical approach, on the other hand, appears to be well suited to handle various sources of uncertainties since it defines probability distributions over both parameters and variables and integrates out the nuisance terms. Also, it does not simply provide a mean estimate of the time-to-failure; rather it generates a probability distribution over time that best encapsulates the uncertainties inherent in the system model and measurements and in the core concept of failure prediction.
Links
Get the data
- 2009_TransRoyal_AlgComp.pdf c3.nasa.gov/dashlink/static/media/publication/2009_TransRoyal_AlgComp.pdf ↗
download · from data nasa gov
Where it is published
- NASA Data Portal dataset page data.nasa.gov/dataset/comparison-of-prognostic-algorithms-for-estimating-rem… ↗
landing page · from data nasa gov
Catalogue records · 1
- CKAN API data.nasa.gov/api/3/action/package_show?id=681ff45b-5f70-4764-b7a4-e27e97ce4… ↗
metadata API · from data nasa gov
Provenance · 1 source records, 6 field assertions
| Source | Key | Last seen | Raw |
|---|---|---|---|
| NASA Data Portal | 681ff45b-5f70-4764-b7a4-e27e97ce4580 | 12 d ago | JSON v1 |
| Field | Assertion | Extractor | Evidence |
|---|---|---|---|
| created_date | source · data nasa gov | connector:data_nasa_gov@1.0.0 | |
| description | source · data nasa gov | connector:data_nasa_gov@1.0.0 | /notes |
| license_text | source · data nasa gov | connector:data_nasa_gov@1.0.0 | |
| publication_date | source · data nasa gov | connector:data_nasa_gov@1.0.0 | |
| title | source · data nasa gov | connector:data_nasa_gov@1.0.0 | /title |
| updated_date | source · data nasa gov | connector:data_nasa_gov@1.0.0 |