A remaining capacity estimation approach of lithium-ion batteries based on partial charging curve and health feature fusion

2021 ◽  
Vol 43 ◽  
pp. 103115 ◽  
Author(s):  
Lingfeng Fan ◽  
Ping Wang ◽  
Ze Cheng
Keyword(s):  
Lithium Ion Batteries ◽  
Feature Fusion ◽  
Lithium Ion ◽  
Capacity Estimation ◽  
Remaining Capacity

Screening of retired lithium-ion batteries using incremental capacity charging curve based residual capacity estimation method for facilitating sustainable circular lithium-ion battery system

2021 ◽  
pp. 1-16
Author(s):  
Honglei Li ◽  
Liang Cong ◽  
Huazheng Ma ◽  
Weiwei Liu ◽  
Yelin Deng ◽  
...  
Keyword(s):  
Lithium Ion Batteries ◽  
Estimation Method ◽  
Lithium Ion ◽  
Capacity Fade ◽  
Characteristic Parameters ◽  
Capacity Estimation ◽  
Capacity Curve ◽  
Residual Capacity ◽  
Remaining Capacity ◽  
Incremental Capacity

Abstract The rapidly growing deployment of lithium-ion batteries in electric vehicles is associated with a great waste of natural resource and environmental pollution caused by manufacturing and disposal. Repurposing the retired lithium-ion batteries can extend their useful life, creating environmental and economic benefits. However, the residual capacity of retired lithium-ion batteries is unknown and can be drastically different owing to various working history and calendar life. The main objective of this paper is to develop a fast and accurate capacity estimation method to classify the retired batteries by the remaining capacity. The hybrid technique of adaptive genetic algorithm and back propagation neural network is developed to estimate battery remaining capacity using the training set comprised of the selected characteristic parameters of incremental capacity curve of battery charging. Also, the paper investigated the correlation between characteristic parameters with capacity fade. The results show that capacity estimation errors of the proposed neural network are within 3%. Peak intensity of the incremental capacity curve has strong correlation with capacity fade. The findings also show that the translation of peak of the incremental capacity curve is strongly related with internal resistance.

scholarly journals Remaining capacity estimation of lithium-ion batteries based on the constant voltage charging profile

PLoS ONE ◽  
2018 ◽  
Vol 13 (7) ◽  
pp. e0200169 ◽  
Author(s):  
Zengkai Wang ◽  
Shengkui Zeng ◽  
Jianbin Guo ◽  
Taichun Qin
Keyword(s):  
Lithium Ion Batteries ◽  
Lithium Ion ◽  
Constant Voltage ◽  
Capacity Estimation ◽  
Remaining Capacity

scholarly journals Online capacity estimation of lithium-ion batteries with deep long short-term memory networks

2021 ◽  
Vol 482 ◽  
pp. 228863
Author(s):  
Weihan Li ◽  
Neil Sengupta ◽  
Philipp Dechent ◽  
David Howey ◽  
Anuradha Annaswamy ◽  
...  
Keyword(s):  
Lithium Ion Batteries ◽  
Short Term Memory ◽  
Lithium Ion ◽  
Capacity Estimation ◽  
Short Term ◽  
Term Memory ◽  
Long Short Term Memory

scholarly journals A Rayleigh Quotient-Based Recursive Total-Least-Squares Online Maximum Capacity Estimation for Lithium-Ion Batteries

2015 ◽  
Vol 30 (3) ◽  
pp. 842-851 ◽  
Author(s):  
Taesic Kim ◽  
Yebin Wang ◽  
Zafer Sahinoglu ◽  
Toshihiro Wada ◽  
Satoshi Hara ◽  
...  
Keyword(s):  
Least Squares ◽  
Lithium Ion Batteries ◽  
Lithium Ion ◽  
Rayleigh Quotient ◽  
Total Least Squares ◽  
Capacity Estimation ◽  
Maximum Capacity

scholarly journals Online Capacity Estimation for Lithium-Ion Batteries Based on Semi-Supervised Convolutional Neural Network

2021 ◽  
Vol 12 (4) ◽  
pp. 256
Author(s):  
Yi Wu ◽  
Wei Li
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Convolutional Neural Network ◽  
Lithium Ion Batteries ◽  
Estimation Method ◽  
Lithium Ion ◽  
Estimation Methods ◽  
Estimation Accuracy ◽  
Capacity Estimation ◽  
Practical Applications

Accurate capacity estimation can ensure the safe and reliable operation of lithium-ion batteries in practical applications. Recently, deep learning-based capacity estimation methods have demonstrated impressive advances. However, such methods suffer from limited labeled data for training, i.e., the capacity ground-truth of lithium-ion batteries. A capacity estimation method is proposed based on a semi-supervised convolutional neural network (SS-CNN). This method can automatically extract features from battery partial-charge information for capacity estimation. Furthermore, a semi-supervised training strategy is developed to take advantage of the extra unlabeled sample, which can improve the generalization of the model and the accuracy of capacity estimation even in the presence of limited labeled data. Compared with artificial neural networks and convolutional neural networks, the proposed method is demonstrated to improve capacity estimation accuracy.

Sign in / Sign up

Export Citation Format

Share Document