Indirect health state prognosis of lithium-ion batteries based on VMD decomposition and neural network model DOI

Qinming Liu,

Fengze Yun,

Ming Dong

и другие.

International Journal of Production Research, Год журнала: 2025, Номер unknown, С. 1 - 20

Опубликована: Фев. 26, 2025

Язык: Английский

A review of data-driven whole-life state of health prediction for lithium-ion batteries: Data preprocessing, aging characteristics, algorithms, and future challenges DOI
Yanxin Xie, Shunli Wang, Gexiang Zhang

и другие.

Journal of Energy Chemistry, Год журнала: 2024, Номер 97, С. 630 - 649

Опубликована: Июнь 19, 2024

Язык: Английский

Процитировано

34
Exploring impedance spectrum for lithium-ion batteries diagnosis and prognosis: A comprehensive review DOI Creative Commons
Xinghao Du, Jinhao Meng, Yassine Amirat

и другие.

Journal of Energy Chemistry, Год журнала: 2024, Номер 95, С. 464 - 483

Опубликована: Апрель 12, 2024

Lithium-ion batteries have extensive usage in various energy storage needs, owing to their notable benefits of high density and long lifespan. The monitoring battery states failure identification are indispensable for guaranteeing the secure optimal functionality batteries. impedance spectrum has garnered growing interest due its ability provide a valuable understanding material characteristics electrochemical processes. To inspire further progress investigation application spectrum, this paper provides comprehensive review determination utilization spectrum. sources inaccuracies systematically analyzed terms frequency response characteristics. applicability utilizing diverse features diagnosis prognosis is elaborated. Finally, challenges prospects future research discussed.

Язык: Английский

Процитировано

25
Dynamic conditions-oriented model-data fused framework enabling state of charge and capacity accurate co-estimation of lithium-ion battery DOI

C.H.E.N. Shouxuan,

Z.H.A.N.G. Shuting,

G.E.N.G. Yuanfei

и другие.

Energy, Год журнала: 2025, Номер unknown, С. 134668 - 134668

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

3
Accuracy comparison and improvement for state of health estimation of lithium-ion battery based on random partial recharges and feature engineering DOI Creative Commons
Xingjun Li,

Dan Yu,

Søren Byg Vilsen

и другие.

Journal of Energy Chemistry, Год журнала: 2024, Номер 92, С. 591 - 604

Опубликована: Янв. 29, 2024

State of health (SOH) estimation e-mobilities operated in real and dynamic conditions is essential challenging. Most existing estimations are based on a fixed constant current charging discharging aging profiles, which overlooked the fact that profiles random not complete application. This paper investigates influence feature engineering accuracy different machine learning (ML)-based SOH acting recharging sub-profiles where realistic battery mission profile considered. Fifteen features were extracted from partial considering factors such as starting voltage values, charge amount, sliding windows. Then, selected selection pipeline consisting filtering supervised ML-based subset selection. Multiple linear regression (MLR), Gaussian process (GPR), support vector (SVR) applied to estimate SOH, root mean square error (RMSE) was used evaluate compare performance. The results showed can improve by 55.05%, 2.57%, 2.82% for MLR, GPR SVR respectively. It demonstrated with lower voltage, large charge, window size more likely achieve higher accuracy. work hopes give some insights into recharges performance tries fill gap effective between theoretical study

Язык: Английский

Процитировано

15
Lithium-Ion Battery State of Health Estimation Using a Hybrid Model with Electrochemical Impedance Spectroscopy DOI
Wu Jian, Jinhao Meng, Mingqiang Lin

и другие.

Reliability Engineering & System Safety, Год журнала: 2024, Номер 252, С. 110450 - 110450

Опубликована: Авг. 22, 2024

Язык: Английский

Процитировано

12
Refined lithium-ion battery state of health estimation with charging segment adjustment DOI
Kun Zheng, Jinhao Meng, Zhipeng Yang

и другие.

Applied Energy, Год журнала: 2024, Номер 375, С. 124077 - 124077

Опубликована: Авг. 6, 2024

Язык: Английский

Процитировано

9
State-of-Health Prediction of Lithium-Ion Batteries Using Exponential Smoothing Transformer With Seasonal and Growth Embedding DOI Creative Commons

Muhammad Rifqi Fauzi,

Novanto Yudistira, Wayan Firdaus Mahmudy

и другие.

IEEE Access, Год журнала: 2024, Номер 12, С. 14659 - 14670

Опубликована: Янв. 1, 2024

In the world of modern energy, Lithium-Ion batteries reign supreme, offering rechargeability, sustainability, and long-term energy storage. However, their lifespan is not infinite, calling for accurate prediction remaining life under various conditions. Deep learning shines in this domain, with Transformer architecture blossoming as a powerful tool time series forecasting. This research dives into data collection, processing, model design, training, evaluation, making key methodological contributions to battery prediction. Notably, SGEformer model, enhanced growth seasonal embedding, emerges groundbreaking innovation. Comparing ETSformer, Informer, Reformer, Transformer, LSTM reveals its unique strengths. With an impressive MSE score 0.000117, establishes itself highly effective prediction, highlighting value embedding boosting accuracy. propels state-of-the-art state-of-health robust foundation precise reliable forecasts.

Язык: Английский

Процитировано

8
Adversarial Training Defense Strategy for Lithium-ion Batteries State of Health Estimation with Deep Learning DOI
Kun Zheng, Yijing Li, Zhipeng Yang

и другие.

Energy, Год журнала: 2025, Номер unknown, С. 134411 - 134411

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

1
Battery State of Health Estimation Based on Energy Features and ResNet‐SVR Model DOI
Yueying Xiao,

LU Zhen-feng,

Chao-Chun Huang

и другие.

Quality and Reliability Engineering International, Год журнала: 2025, Номер unknown

Опубликована: Апрель 1, 2025

ABSTRACT The accurate estimation of battery state health (SOH) is crucial for monitoring status and alerting users to replace the degraded batteries. Energy, as a comprehensive feature integrating current voltage, can effectively reflect amount stored energy, graphical energy features contain more information. In this study, hybrid ResNet‐SVR model based on proposed estimate battery's SOH. sequential are first constructed during constant charging process. Then they transformed into two‐dimensional structure through sliding window inputs, which shows significant differences between cycles. uses ResNet extract relevant information from data SVR regression prediction. It combines advantages convolutional neural network extraction prediction achieve better results. method validated two datasets achieves satisfactory results in estimation, with an average mean absolute error 0.0072 percentage 0.83%. Overall, our findings highlight potential SOH significantly enhances performance management system various applications.

Язык: Английский

Процитировано

1
State Estimation of Lithium-Ion Batteries via Physics-Machine Learning Combined Methods: A Methodological Review and Future Perspectives DOI
Hanqing Yu, Hongcai Zhang, Zhengjie Zhang

и другие.

eTransportation, Год журнала: 2025, Номер unknown, С. 100420 - 100420

Опубликована: Апрель 1, 2025

Язык: Английский

Процитировано

1