2021
DOI: 10.1016/j.apenergy.2020.116410
|View full text |Cite
|
Sign up to set email alerts
|

Lithium-ion battery capacity estimation — A pruned convolutional neural network approach assisted with transfer learning

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
54
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
7
1

Relationship

1
7

Authors

Journals

citations
Cited by 166 publications
(54 citation statements)
references
References 39 publications
0
54
0
Order By: Relevance
“…It is also worth mentioning that a traditional feedforward neural network is sufficient to describe the relationship between the selected IC-based features and the battery's capacities in this work. But readers may also use more advanced recurrent neural network 39 or convolutional neural network 40 for enhanced performances.…”
Section: Methodsmentioning
confidence: 99%
“…It is also worth mentioning that a traditional feedforward neural network is sufficient to describe the relationship between the selected IC-based features and the battery's capacities in this work. But readers may also use more advanced recurrent neural network 39 or convolutional neural network 40 for enhanced performances.…”
Section: Methodsmentioning
confidence: 99%
“…Such approaches can avoid the establishment of empirical mathematical models. Moreover, the advancements in deep learning techniques have further broadened the ability in complex nonlinear data analysis [14]; thus, numerous artificial intelligence methods have been applied to the predictive field, such as long short term memory (LSTM), adaptive recurrent neural network (ARNN), Box-Cox transformation (BCT) and so on [15][16][17][18][19][20][21][22][23]. Yong et al [15] introduced the LSTM model with the Monte Carlo simulation to generate probability distribution, which improved the prediction accuracy of the RNN algorithm.…”
Section: Introductionmentioning
confidence: 99%
“…By employing the orthogonal method to optimize the model parameters, the proposed method reduced the training time and reached 90.9% prediction accuracy. Further assimilating the concepts of transfer learning and network pruning, Li et al [21] built a compact CNN model on a comparatively small dataset, which outperformed other models in terms of accuracy and computational efficiency. Moreover, Wilbik et al [22] used a fuzzy logic method to derive linguistic summaries of time series.…”
Section: Introductionmentioning
confidence: 99%
“…On the other hand, the convolution neural network and recurrent neural network (RNN) were proposed to the RUL field in recent years. For example, Li et al built a novel framework using compact convolutional neural network models through the concepts of transfer learning to improve the battery health estimation accuracy 18 . Another disadvantage of these methods is that the chosen prediction model possesses more input parameters and need to have time consecutive 19 .…”
Section: Introductionmentioning
confidence: 99%