Convolutional autoencoder-based SOH estimation of lithium-ion batteries using electrochemical impedance spectroscopy

Obregon, Josue; Han, Yuri; Ho, Chang Won; Mouraliraman, Devanadane; Lee, Chang Woo; Jung, Jae‐Yoon

doi:10.1016/j.est.2023.106680

Cited by 29 publications

(6 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are three methods commonly used for predicting SOH: model‐based methods, 11,12 data‐based methods, 13,14 and statistical methods 15,16 . Model‐based methods involve implementing electrochemical or electro‐physical models that can represent the lifespan characteristics of batteries and using them to predict SOH.…”

Section: Introductionmentioning

confidence: 99%

“…8 For this reason, it is required to consider not only a single variable, such as internal resistance, but also the application of various soundness indicators, such as cell deviation, temperature, and so forth, to determine the life of a battery pack. 9,10 There are three methods commonly used for predicting SOH: model-based methods, 11,12 data-based methods, 13,14 and statistical methods. 15,16 Model-based methods involve implementing electrochemical or electro-physical models that can represent the lifespan characteristics of batteries and using them to predict SOH.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Enhanced S‐ARIMAX model performance and state‐of‐health prediction accuracy with battery pack degradation factor combinations

Lee,

Baek

et al. 2024

Energy Storage

View full text Add to dashboard Cite

This study addresses the critical need for accurate state‐of‐health (SOH) predictions in lithium‐ion batteries, crucial for maintaining efficient battery operation and extending lifespan. We propose a novel approach utilizing the Seasonal autoregressive integrated moving average with exogenous variables (S‐ARIMAX) model, integrating multiple battery degradation factors as exogenous variables for precise SOH estimation. Our methodology involves correlation analysis to identify optimal factors, which are then incorporated into distinct cases of the S‐ARIMAX model. We evaluate the model's performance using mean absolute percentage error (MAPE) and identify voltage deviation as a highly correlated exogenous variable significantly impacting predictive accuracy. Notably, our findings underscore the S‐ARIMAX model's superiority in longer cycles, demonstrating a MAPE as low as 0.1113 at 160 cycles, emphasizing the model's adeptness at capturing cyclic patterns for precise long‐term SOH forecasts. Comparing S‐ARIMAX and ARIMAX models highlights the pivotal role of seasonality, particularly in long‐term predictions. The study's quantitative findings emphasize the necessity of integrating highly correlated variables and accounting for seasonal patterns in optimizing lithium‐ion battery SOH predictions. Our approach presents practical implications for maintaining battery performance and lifespan in electric vehicles and energy storage systems, underlining the importance of selecting strongly correlated variables and integrating seasonal components for accurate and reliable SOH forecasts.

show abstract

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

Enhanced S‐ARIMAX model performance and state‐of‐health prediction accuracy with battery pack degradation factor combinations

Lee,

Baek

et al. 2024

Energy Storage

View full text Add to dashboard Cite

show abstract

“…Data-based SOH estimation studies aim to estimate SOH by reflecting the characteristics of the data without considering the complex state changes inside the battery [7][8][9]. Cui and Joe used a dynamic spatiotemporal attention-based gated recurrent unit (GRU) model based on a GRU [4], Gu et al combined a convolutional neural network (CNN) and a transformer [5], and Li et al used active state tracking long short-term memory neural network (AST-LSTM NN) for estimating SOH and predicting remaining useful life [6].…”

Section: Introductionmentioning

confidence: 99%

Improving SOH estimation for lithium-ion batteries using TimeGAN

Seol,

Lee,

Yoon

et al. 2023

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

Recently, the xEV market has been expanding by strengthening regulations on fossil fuel vehicles. It is essential to ensure the safety and reliability of batteries, one of the core components of xEVs. Furthermore, estimating the battery's state of health (SOH) is critical. There are model-based and data-based methods for SOH estimation. Model-based methods have limitations in linearly modeling the nonlinear internal state changes of batteries. In data-based methods, high-quality datasets containing large quantities of data are crucial. Since obtaining battery datasets through measurement is difficult, this paper supplements insufficient battery datasets using TimeGAN and compares the improvement rate in SOH estimation accuracy through long short-term memory and gated recurrent unit based on recurrent neural networks. According to the results, the average RMSE (Root Mean Square Error) of battery SOH estimation improved by approximately 25%, and the learning stability improved by approximately 40%.

show abstract

“…At present, the research on SOH and RUL of marine power LIB mainly focuses on the model-based method 5 and data-driven method. 6 For the model-based method, different kinds of equivalent circuit models, 7 electrochemical models 8 and empirical models 9 for LIB are widely constructed. Based on the existing models the detailed operating mechanism of battery can be excavated and analyzed, and the internal characteristics of the battery can be also detected to realize the prediction of SOH and RUL.…”

mentioning

confidence: 99%

Prediction of Battery SOH and RUL Based on Cooperative Characteristics in Voltage-Temperature-Time Dimensions

Tang,

Zhang,

Ning

et al. 2023

J. Electrochem. Soc.

View full text Add to dashboard Cite

In the prognostics health management (PHM) of marine power lithium batteries, the estimation of the state of health (SOH) and the prediction of remaining useful life (RUL) are of great importance to ensure the battery operational safety and efficiency. In this study, an improved multivariate dimensionality-reduction for Bayesian optimized bi-directional long short-term memory (IMD-BiLSTM) algorithm is proposed and applied to realize SOH estimation and RUL prediction of lithium battery. Specifically, based on the discharging data of lithium battery under specific operating conditions, several health indicators are proposed for the work. On this basis, a collaborative dimensionality reduction algorithm based on Pearson correlation and principal component analysis is proposed to further retain feature information and reduce input dimensionality. Then, the prediction model based on BiLSTM is established, in which the hyperparameters are optimized by Bayesian algorithm. Finally, the effectiveness of the proposed IMD-BiLSTM method is verified by experiments based on the NASA PCoE dataset, and the prediction accuracies of SOH and RUL are emphatically analyzed. Numerical simulation results show that the proposed IMD-BiLSTM-method can effectively extract battery health characteristics and achieve dimensionality reduction. In addition, the proposed IMD-BiLSTM-method significantly outperforms the compared state-of-the-art algorithms in SOH/RUL prediction accuracy and robustness.

show abstract

Convolutional autoencoder-based SOH estimation of lithium-ion batteries using electrochemical impedance spectroscopy

Cited by 29 publications

References 43 publications

Enhanced S‐ARIMAX model performance and state‐of‐health prediction accuracy with battery pack degradation factor combinations

Enhanced S‐ARIMAX model performance and state‐of‐health prediction accuracy with battery pack degradation factor combinations

Improving SOH estimation for lithium-ion batteries using TimeGAN

Prediction of Battery SOH and RUL Based on Cooperative Characteristics in Voltage-Temperature-Time Dimensions

Contact Info

Product

Resources

About