Lithium-ion batteries are widely used due to their high energy density & low self-discharge. Early detection of inadequate performance through Prognostic & Health Management (PHM) can reduce costs & prevent accidents. A data-driven, LSTM-based approach was tested using NASA's battery dataset & found to match or surpass other ML algorithms in predicting battery SoH & SOC.
-
Notifications
You must be signed in to change notification settings - Fork 0
Developed a data-driven prognostic model using the Long short-term memory (LSTM) algorithm to predict the state of charge (SoC) and state of health (SoH) of the lithium-ion battery where the dataset was taken from the NASA Repository. The proposed LSTM algorithm was compared against other deep learning algorithms based on RMSE value.
HarimJung/ML-Battery-Modeling
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
Developed a data-driven prognostic model using the Long short-term memory (LSTM) algorithm to predict the state of charge (SoC) and state of health (SoH) of the lithium-ion battery where the dataset was taken from the NASA Repository. The proposed LSTM algorithm was compared against other deep learning algorithms based on RMSE value.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published
Languages
- Python 100.0%