In this demo, using MATLAB, I've implemented machine learning based Lithium-Ion battery capacity estimation using multi-Channel charging Profiles.
Dataset used in this example is from "Battery data set" from NASA[1].
Basic implementation theory and approach is referenced by the recent published paper[2], and they proposed Multi-Channel charging profiles
based machine learning and deep learning model.
Throught this example, we will capture each approach described in paper, including following machine/deep learning methods
- FNN(Feed Forward Network)
- CNN(Convolutional Neural Network)
- LSTM(Long Short Term Memory Network)
Dataset should be downloaded from here: https://ti.arc.nasa.gov/tech/dash/groups/pcoe/prognostic-data-repository/#battery
[Reference]
[1] B. Saha and K. Goebel, ``Battery data set,''NASA AMES Prognostics Data Repository, 2007.
[2] Choi, Yohwan, et al. "Machine Learning-Based Lithium-Ion Battery Capacity Estimation Exploiting Multi-Channel Charging Profiles." IEEE Access 7 (2019): 75143-75152.
Copyright 2019 The MathWorks, Inc.
[Cite as]
Wanbin Song (2019). Machine Learning Lithium-Ion Battery Capacity Estimation (https://www.github.com/wanbin-song/BatteryMachineLearning), GitHub. Retrieved November 26, 2019.