Skip to content

Machine Learning pipeline to predict the Remaining Useful Life (RUL) of Li-ion batteries for EVs

License

Notifications You must be signed in to change notification settings

aweditya/ev-battery-degradation

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

76 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Predicting Remaining Useful Life (RUL) of EV Batteries

The purpose of this project is to predict RUL of EV batteries by estimating Battery Capacity using indirect discharge cycle parameters. A thorough EDA is performed after which pertinent features are extracted from the data. Seven different learning models are trained on data from one battery but are tested on other batteries as well.

The dataset used in the project was obtained from the Prognostics Centre of Excellence.

Directory Structure

.
├── README.md
├── datasets
│   ├── README.txt
│   ├── data.zip
│   └── save_data_as_pickle.py
├── images
│   ├── mlp_blue.png
│   └── model.png
├── report
│   ├── Report.pdf
│   └── Supplementary.pdf
├── requirements.txt
└── src
    └── Predicting RUL of EV Batteries.ipynb

Dataset Citation

B. Saha and K. Goebel (2007). "Battery Data Set", NASA Ames Prognostics Data Repository (http://ti.arc.nasa.gov/project/prognostic-data-repository), NASA Ames Research Center, Moffett Field, CA

About

Machine Learning pipeline to predict the Remaining Useful Life (RUL) of Li-ion batteries for EVs

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published