Online Capacity Estimation of Lithium-Ion Batteries Based on Deep Convolutional Time Memory Network and Partial Charging Profiles

Xue, Qiao; Li, Junqiu; Chen, Zheng; Zhang, Hongjie; Liu, Yonggang; Shen, Jiangwei

doi:10.1109/tvt.2022.3205439

Cited by 10 publications

(2 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To smooth the prediction results, a firstorder filter was used. Xue et al [16] developed a prediction model featuring automatic feature extraction and target estimation termed a deep convolutional temporal memory network, which achieves accurate capacity estimation by merging CNN with LSTM. The data-driven approach is straightforward to operate without the need for complex chemical, physical, or mathematical models.…”

Section: Introductionmentioning

confidence: 99%

A hybrid remaining useful life prediction method for lithium-ion batteries based on transfer learning with CDRSN-BiGRU-AM

Li,

Zhang

2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

The prediction of the remaining useful life (RUL) of lithium-ion batteries (LIBs), which are increasingly used in a wide range of applications, has been an important study. Existing techniques are difficult to strike a balance between prediction accuracy and execution time. To realize highly accurate RUL prediction in a short time, a hybrid RUL prediction method for LIBs was developed. The method first adopts a channel-wise deep residual shrinkage network (CDRSN) for adaptive extraction of input data feature, enhances important information features, and suppresses ineffective features according to the importance of feature information. Then, a bidirectional gated recurrent unit (BiGRU) was utilized to extract bidirectional temporal features of the processed data, and an attention mechanism (AM) was introduced to maximize the extraction of the important temporal mutual information in the data. Finally, a fully connected layer transfer strategy was applied to deploy the model from offline training to online prediction, which could prevent the problem of unstable prediction due to random initialization of the model and greatly improve the computational efficiency of the model. The simulation results indicated that the RMSE of the proposed method did not exceed 1.77% and the MAE did not exceed 1.44%. Both were smaller than the results in the other literature compared. Therefore, the proposed method could obtain accurate RUL prediction accuracy for LIBs online.

show abstract

Section: Introductionmentioning

confidence: 99%

A hybrid remaining useful life prediction method for lithium-ion batteries based on transfer learning with CDRSN-BiGRU-AM

Li,

Zhang

2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…Currently, electric vehicles powered by lithium-ion batteries face several challenges, including limited driving range [1], slow charging times [2,3], battery temperature inconsistencies [4][5][6], the risk of thermal runaway [7,8], and short battery life [9,10]. Researchers have concentrated on increasing the energy density of lithium-ion batteries to tackle the issue of restricted range.…”

Section: Introductionmentioning

confidence: 99%

The Polarization and Heat Generation Characteristics of Lithium-Ion Battery with Electric–Thermal Coupled Modeling

Guo,

Liu

et al. 2023

Batteries

View full text Add to dashboard Cite

This paper investigates the polarization and heat generation characteristics of batteries under different ambient temperatures and discharge rates by means of using a coupled electric–thermal model. This study found that the largest percentage of polarization is ohmic polarization, followed by concentration polarization and electrochemical polarization. The values of the three types of polarization are generally small and stable under normal-temperature environments and low discharge rates. However, they increase significantly in low-temperature environments and at high discharge rates and continue to rise during the discharge process. Additionally, ohmic heat generation and polarization generation also increase significantly under these conditions. Reversible entropy heat is less sensitive to ambient temperature but increases significantly with the increase in the discharge rate. Ohmic heat generation and polarization heat generation contribute to the total heat generation of the battery at any ambient temperature, while reversible entropy heat only contributes to the total heat generation of the battery at the end of discharge.

show abstract

A general multi-source ensemble transfer learning framework for health prognostic of lithium-ion batteries

Qiu,

Yan,

Wang

et al. 2024

Applied Energy

View full text Add to dashboard Cite

Online Capacity Estimation of Lithium-Ion Batteries Based on Deep Convolutional Time Memory Network and Partial Charging Profiles

Cited by 10 publications

References 50 publications

A hybrid remaining useful life prediction method for lithium-ion batteries based on transfer learning with CDRSN-BiGRU-AM

A hybrid remaining useful life prediction method for lithium-ion batteries based on transfer learning with CDRSN-BiGRU-AM

The Polarization and Heat Generation Characteristics of Lithium-Ion Battery with Electric–Thermal Coupled Modeling

A general multi-source ensemble transfer learning framework for health prognostic of lithium-ion batteries

Contact Info

Product

Resources

About