A multi-feature-based multi-model fusion method for state of health estimation of lithium-ion batteries

Lin, Mingqiang; Wu, Denggao; Meng, Jinhao; Wu, J.; Wu, Han

doi:10.1016/j.jpowsour.2021.230774

Cited by 93 publications

(20 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Classical machine learning regression algorithms such as support vector regression (SVR) [12,13], Gaussian process regression (GPR) [14], and neural networks and their variants [15][16][17] are also commonly used to mine the mapping relationship between features and SOH. Wang et al [18] adopted broad learning system (BLS) to effectively reconstruct the model through incremental learning, shortening the training process and avoiding catastrophic forgetting.…”

Section: Introductionmentioning

confidence: 99%

State of Health Estimation Method for Lithium-Ion Batteries via Generalized Additivity Model and Transfer Component Analysis

Lin

Yan

Zeng

2023

WEVJ

Self Cite

View full text Add to dashboard Cite

Battery state of health (SOH) is a momentous indicator for aging severity recognition of lithium-ion batteries and is also an indispensable parameter of the battery management system. In this paper, an innovative SOH estimation algorithm based on feature transfer is proposed for lithium-ion batteries. Firstly, sequence features with battery aging information are sufficiently extracted based on the capacity increment curve. Secondly, transfer component analysis is employed to obtain the mapping that minimizes the data distribution difference between the training set and the test set in the shared feature space. Finally, the generalized additive model is investigated to estimate the battery health status. The experimental results demonstrate that the proposed algorithm is capable of forecasting the SOH for lithium-ion batteries, and the results are more outstanding than those of several comparison algorithms. The predictive error evaluation indicators for each battery are both less than 2.5%. In addition, satisfactory SOH estimation results can also be obtained by only relying on a small amount of data as the training set. The comparative experiments using traditional features and different machine learning methods also testify to the superiority of the proposed algorithm.

show abstract

Section: Introductionmentioning

confidence: 99%

State of Health Estimation Method for Lithium-Ion Batteries via Generalized Additivity Model and Transfer Component Analysis

Lin

Yan

Zeng

2023

WEVJ

Self Cite

View full text Add to dashboard Cite

show abstract

“…Various techniques exist for forming a coating layer on the precursor or LNCM materials. The atomic layer deposition (ALD) coating method can produce a very thin and uniform film, but it is not suitable for actual industrial applications 38‐40 . Inexpensive and convenient solid‐state reactions exist, but they tend to form thick and uneven coatings on the surface of the precursor, and high‐energy ball‐milling can damage the primary particles 41,42 .…”

Section: Introductionmentioning

confidence: 99%

“…The atomic layer deposition (ALD) coating method can produce a very thin and uniform film, but it is not suitable for actual industrial applications. [38][39][40] Inexpensive and convenient solid-state reactions exist, but they tend to form thick and uneven coatings on the surface of the precursor, and high-energy ball-milling can damage the primary particles. 41,42 Wet chemical methods such as sol-gel, hydrothermal, and solvothermal methods are considered to readily produce a thin and even coating layer on the cover of the NCM(OH) 2 precursor.…”

Section: Introductionmentioning

confidence: 99%

Design of a hydrolysis‐supported coating layer on the surface of Ni‐rich cathodes in secondary batteries

Park

Lee

Kim

et al. 2022

Intl J of Energy Research

View full text Add to dashboard Cite

Summary The formation of Li4SiO4 (LSO) coating layer on LiNi0.88Co0.05Mn0.07O2 (LNCM) was achieved by incorporating a new tetraethyl orthosilicate (TEOS)‐dropping coating method. This concept includes the hydrolysis reaction of TEOS on the surface of Ni0.88Co0.05Mn0.07(OH)2 and the subsequent calcination process with lithium source to obtain LSO‐coated LNCM cathode materials successfully during the calcination process. This method provides the driving force for the formation of a more uniform and thin coating layer compared with the traditional wet‐chemical coating method. The bare LNCM and LSO‐coated LNCM showed similar capacity retention rates during room temperature (25°C) cycling, but the capacity retention of LSO‐LNCM (81.6% after 100 cycles) for the cycling test at elevated temperature was significantly increased compared with bare LNCM (63.69% after 100 cycles). Additionally, the Li‐ion accessibility of the coated LNCM electrode was improved by the existence of the Li‐containing coating materials, and the results of analysis by the galvanostatic intermittent titration technique (GITT) confirmed the better Li‐ion diffusivity of the coated sample. These results indicate the high possibility of this novel coating method for application in various materials for developing secondary batteries.

show abstract

“…The data-driven method, which has great viability, does not require proper physical and chemical model structure and instead mines the battery aging decrease law from battery historical operating data. 13,14 In recent years, machine learning algorithms have been widely used in battery SOH and RUL prediction, such as support vector machines, 15 Gaussian process regression (GPR), 16,17 probabilistic neural network (PNN). 18 Lin et al 17 proposed a multi-feature based multi-model fusion method to estimate the SOH of lithium-ion batteries while considering battery historical data features, the SOH prediction model fused multiple linear regression, support vector regression, and GPR.…”

Section: Introductionmentioning

confidence: 99%

“…13,14 In recent years, machine learning algorithms have been widely used in battery SOH and RUL prediction, such as support vector machines, 15 Gaussian process regression (GPR), 16,17 probabilistic neural network (PNN). 18 Lin et al 17 proposed a multi-feature based multi-model fusion method to estimate the SOH of lithium-ion batteries while considering battery historical data features, the SOH prediction model fused multiple linear regression, support vector regression, and GPR. Lin et al 18 estimated the SOH of lithium-ion batteries using a PNN.…”

Section: Introductionmentioning

confidence: 99%

Attention-based CNN-BiLSTM for SOH and RUL estimation of lithium-ion batteries

Zhu

Yang

Liu

et al. 2022

Journal of Algorithms & Computational Technology

View full text Add to dashboard Cite

The state of health (SOH) and remaining useful life (RUL) of lithium-ion batteries describe the current aging degree of the batteries from different perspectives, and accurate and efficient battery health estimation is essential for their safe use. To improve the effectiveness and accuracy of the batteries’ health assessment models, this paper proposes a new method for SOH and RUL estimation of lithium-ion batteries. Convolutional neural networks (CNNs), bi-directional long short-term memory (BiLSTM), and attention mechanism (AM) to build a hybrid network model for capacity estimation of lithium-ion batteries, and further calculate the SOH and RUL estimation results. By using Center for Advanced Life Cycle Engineering (CALCE) lithium-ion battery capacity degradation data, we extracted the battery health indicator (HI) and verified the reasonableness of HI selection by using Gray Relational Analysis (GRA) and compared it with other network models to calculate the prediction accuracy by various evaluation indexes. The experimental results show that the method has higher estimation accuracy while avoiding the construction of complex battery mechanism degradation models and is highly generalized.

show abstract

A multi-feature-based multi-model fusion method for state of health estimation of lithium-ion batteries

Cited by 93 publications

References 22 publications

State of Health Estimation Method for Lithium-Ion Batteries via Generalized Additivity Model and Transfer Component Analysis

State of Health Estimation Method for Lithium-Ion Batteries via Generalized Additivity Model and Transfer Component Analysis

Design of a hydrolysis‐supported coating layer on the surface of Ni‐rich cathodes in secondary batteries

Attention-based CNN-BiLSTM for SOH and RUL estimation of lithium-ion batteries

Contact Info

Product

Resources

About