2020
DOI: 10.1002/er.6005
|View full text |Cite
|
Sign up to set email alerts
|

Deep learning networks for capacity estimation for monitoring SOH of Li‐ion batteries for electric vehicles

Abstract: Summary Data‐driven modeling using measurable battery signals tends to provide robust battery capacity estimation without delving deep into electrochemical phenomenon inside the battery. Nowadays, with the advent of artificial intelligence, deep neural networks are playing crucial role in data modeling and analysis. In this article, models of three different families of network architectures such as feed‐forward neural network (FNN), convolutional neural network (CNN), and long short‐term memory neural network… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1

Citation Types

0
38
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
8

Relationship

2
6

Authors

Journals

citations
Cited by 99 publications
(38 citation statements)
references
References 39 publications
(108 reference statements)
0
38
0
Order By: Relevance
“…ML algorithms with least root mean square errors (RMSE), results in minimum degradation and less charging time to optimize the battery‐charging protocols, could be used in SOH estimation. In the most recent work, Kaur et al [ 74 ] have estimated the SOH of Li‐ion batteries using ANN, LSTM, and CNN models with comparatively reduced RMSE values. This work provides a line of sight for accurately predicting the SOH of Li‐ion batteries by processing large battery datasets using AI‐ and ML‐based methods with a comparatively lesser computational cost and time.…”
Section: Proposed Frameworkmentioning
confidence: 99%
“…ML algorithms with least root mean square errors (RMSE), results in minimum degradation and less charging time to optimize the battery‐charging protocols, could be used in SOH estimation. In the most recent work, Kaur et al [ 74 ] have estimated the SOH of Li‐ion batteries using ANN, LSTM, and CNN models with comparatively reduced RMSE values. This work provides a line of sight for accurately predicting the SOH of Li‐ion batteries by processing large battery datasets using AI‐ and ML‐based methods with a comparatively lesser computational cost and time.…”
Section: Proposed Frameworkmentioning
confidence: 99%
“…The performance of three different neural network models for capacity estimation, i.e. feed-forward neural network, LSTM and CNN, were compared in [27], and the test results revealed the difficulty of the resultant models in dealing well with limited available battery data. It is clear that these machine learning-based methods have shown great potentials in battery capacity estimation, yet their performance is heavily dependent on the size of the training dataset.…”
Section: Introductionmentioning
confidence: 99%
“…The capacity monitoring techniques can be categorized into data‐driven approaches and model‐based methods as well 23 . Data‐driven methods have been widely used, including Neural Networks, 24 Bayesian Networks, 25 fusion algorithm, 26 and online sequential extreme learning machine method 27 . For the model‐based methods, different parameters are used, including the inner resistance, 28 dQ/dV curve, 29 charging characters curve, 30 and voltage stabilization 31 are studied.…”
Section: Introductionmentioning
confidence: 99%