State-of-health estimation for lithium-ion batteries based on historical dependency of charging data and ensemble SVR

Guo, Yongfang; Huang, Kai; Yu, Xiangyuan; Wang, Yashuang

doi:10.1016/j.electacta.2022.140940

Cited by 29 publications

(15 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To verify the advancement of the proposed framework, we gather all validation cases and compare our accuracy with that of four popular methods, including Gaussian process regression 35 (GPR), random forest 45 (RF), support vector regression 46 (SVR), and CNN 47 . Their hyper-parameter settings can be found in Table S3 .…”

Section: Resultsmentioning

confidence: 99%

Deep learning to estimate lithium-ion battery state of health without additional degradation experiments

Xiong

Tian

et al. 2023

Nat Commun

View full text Add to dashboard Cite

State of health is a critical state which evaluates the degradation level of batteries. However, it cannot be measured directly but requires estimation. While accurate state of health estimation has progressed markedly, the time- and resource-consuming degradation experiments to generate target battery labels hinder the development of state of health estimation methods. In this article, we design a deep-learning framework to enable the estimation of battery state of health in the absence of target battery labels. This framework integrates a swarm of deep neural networks equipped with domain adaptation to produce accurate estimation. We employ 65 commercial batteries from 5 different manufacturers to generate 71,588 samples for cross-validation. The validation results indicate that the proposed framework can ensure absolute errors of less than 3% for 89.4% of samples (less than 5% for 98.9% of samples), with a maximum absolute error of less than 8.87% in the absence of target labels. This work emphasizes the power of deep learning in precluding degradation experiments and highlights the promise of rapid development of battery management algorithms for new-generation batteries using only previous experimental data.

show abstract

Section: Resultsmentioning

confidence: 99%

Deep learning to estimate lithium-ion battery state of health without additional degradation experiments

Xiong

Tian

et al. 2023

Nat Commun

View full text Add to dashboard Cite

show abstract

“…Currently, some ensemble methods have been proposed for SOH estimation. [24][25][26] The model structure, feature source, and estimation accuracy are compared and shown in Table 8.…”

Section: Comparison With Other Ensemble Methodsmentioning

confidence: 99%

“…Guo et al selected the cumulative voltage and charging capacity as the HFs, then an ensemble SVR model is designed for SOH estimation. 26 Essentially, these approaches are mainly multifeature fusion methods with a single model, and without thoroughly exploiting the crucial features that form the temperature, voltage, or IC curves. As mentioned in Lin et al, 27 each data-driven approach has its own unique limitations, which lead to poor robustness of single-model estimation methods.…”

Section: Introductionmentioning

confidence: 99%

“…Liu et al 25 used SVR and LSTM to construct a stacking ensemble learning model, features from the current profiles of the constant voltage charging phase were extracted to map the aging process. Guo et al selected the cumulative voltage and charging capacity as the HFs, then an ensemble SVR model is designed for SOH estimation 26 . Essentially, these approaches are mainly multifeature fusion methods with a single model, and without thoroughly exploiting the crucial features that form the temperature, voltage, or IC curves.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

State‐of‐health estimation for lithium‐ion batteries based on partial charging segment and stacking model fusion

Liu

Zhang

et al. 2022

Energy Science & Engineering

View full text Add to dashboard Cite

State-of-health (SOH) estimation is essential for evaluating the aging process of lithium-ion batteries, which can effectively guarantee the steady application of the battery system. Most existing prediction approaches apply a single model or a single feature to achieve SOH estimation based on the entire charging curve. In this paper, a multifeature-based stacked ensemble learning framework is proposed for SOH prediction using partial charging curves. Firstly, combined with the range of state-of-charge (SOC) commonly used in the actual operation of vehicles, the charging segment is effectively intercepted through the mapping correlation between the SOC and the terminal voltage.Then, five relevant features characterizing the battery health status are extracted from multiple data, such as temperature, voltage, and incremental capacity profiles. Finally, a two-level stacking ensemble framework is developed to fuse several individual estimation methods for higher SOH accuracy. To validate the performance of the proposed method, the Oxford University data set and the NASA data set are deployed for comparison experiments, and the results reveal the superior precision and robustness of the developed model in SOH estimation.

show abstract

“…The lithium-ion battery has been hugely popular for over a century due to the critical need for a reliable source of power for portable and non-portable electronic equipment, such as smartphones and watches, smart grids, submarines, and space vehicles [7][8][9]. 'However, the use of lithium-ion batteries has safety risks due to over-charging and over-discharging, resulting in an explosion and shortened service life [10]. Moreover, battery characteristics can vary based on various operating situations.…”

Section: Introductionmentioning

confidence: 99%

Adaptive state of charge estimation for lithium‐ion batteries using feedback‐based extended Kalman filter

Monirul

Pan

Ruby

et al. 2023

IET Control Theory & Appl

View full text Add to dashboard Cite

The battery management system (BMS) is a crucial component of electric vehicles (EVs) owing to its sustainable operation. To ensure optimal performance of the BMS, state of charge (SOC) of the equipped battery is required to be effectively and accurately estimated. In this paper, the authors consider high‐order equivalent circuit model (ECM) to capture the dynamic characteristics of lithium‐ion batteries, which are connected in series with internal resistance by 2‐RC networks. The parameters of the RC network are determined by mathematically solving the working conditions of the two states. Moreover, the parameters of the battery can be derived by hybrid pulse power characterization (HPPC) tests. Then, based on the open‐circuit voltage, the proposed feedback‐based extended Kalman filtering (FEKF) algorithm is established. The parameters from the simulation have shown that the highest error is 0.0306 V, the optimal knowledge of which can improve the SOC estimation approach remarkably and can provide a reference value. Afterwards, the non‐linear predicting and corrective techniques are applied to the experiment in the extended calculation process. The original error is reduced by the FEKF algorithm, where the maximum and average errors are 0.0298 and 0.0240 V, respectively. Consequently, the established high‐order ECM utilizing the FEKF algorithm may provide SOC estimation with an error of 1.5% or less, resulting in superb performance from the lithium‐ion battery pack.

show abstract

State-of-health estimation for lithium-ion batteries based on historical dependency of charging data and ensemble SVR

Cited by 29 publications

References 47 publications

Deep learning to estimate lithium-ion battery state of health without additional degradation experiments

Deep learning to estimate lithium-ion battery state of health without additional degradation experiments

State‐of‐health estimation for lithium‐ion batteries based on partial charging segment and stacking model fusion

Adaptive state of charge estimation for lithium‐ion batteries using feedback‐based extended Kalman filter

Contact Info

Product

Resources

About