相关参考文献
注意：仅列出部分参考文献，下载原文获取全部文献信息。
Article
Thermodynamics
Yong Zhou et al.
Summary: Due to the complex behaviors of lithium-ion batteries, accurately estimating their state-of-health remains a critical challenge. Most existing battery health prognosis methods focus on low-frequency sampled time-domain response, which may not fully reflect the battery health status in automotive applications. This paper proposes a data-driven method using high and medium frequency impedance spectroscopy data to estimate battery state-of-health. Experimental results demonstrate the high accuracy and robustness of the proposed method, with an estimation error of 1.12%.
Article
Thermodynamics
Ji Wu et al.
Summary: This paper proposes an improved radial basis function neural network (IRBFNN) to accurately estimate the state of health (SOH) of lithium-ion batteries. The IRBFNN can simultaneously fit general trends and local fluctuations, and the maximum estimation errors are within +/- 4%. The results show that the proposed method effectively alleviates the poor estimation performance of traditional neural network-based algorithms in the later stage of battery aging.
Article
Thermodynamics
Haiyan Jin et al.
Summary: This paper focuses on addressing the challenge of creating a high-performance model with a compact structure for battery State-of-Health (SOH) estimation. The proposed method utilizes an auto-configurable Gaussian Process Regression (GPR) with elastic feature construction and an evolutionary framework to eliminate the impact of kernels. Additionally, a hierarchical feature construction strategy reduces complexity.
Article
Thermodynamics
Mingqiang Lin et al.
Summary: This paper develops a data-driven approach to estimate the state-of-health (SOH) of lithium-ion batteries by considering the battery's internal resistance. The method effectively integrates the equivalent circuit model (ECM) and the data-driven method. The internal resistance is identified under constant current charging conditions by simplifying the ECM, and the thermoelectric coupling features are used as model inputs. An explanation boosting machine (EBM) is used to construct the SOH estimator, and the model parameters are optimized using an ant colony algorithm. Comparative experiments on the Oxford dataset demonstrate the accuracy of the proposed method with a mean absolute error of less than 1%.
Article
Thermodynamics
Huanwei Xu et al.
Summary: The article proposes a feature selection method to enhance the accuracy of SOH prediction by removing insignificant features from the input data during data preparation. Additionally, a skip connection is added to the CNN-LSTM model to address the degradation of neural networks caused by multi-layer LSTM. Experimental results demonstrate that the feature selection approach improves SOH prediction accuracy and reduces computational load. Compared to other neural network models, the CNN-LSTM-Skip model exhibits better robustness and higher accuracy across different conditions, achieving RMSE below 0.004 on the NASA and Oxford datasets.
Article
Thermodynamics
Xinyuan Bao et al.
Summary: This study presents an end-to-end multi-battery shared hybrid neural network (NN) prognostic framework for accurate estimation of the state-of-health (SOH) of lithium-ion batteries (LIBs). By employing a combination of convolutional neural network (CNN), multi-layer variant long-short-term memory (VLSTM) NN, and dimensional attention mechanism (CNN-VLSTM-DA), this framework effectively captures temporal correlations and assigns different weights to features of each dimension, providing reliable prediction results for LIBs.
Article
Energy & Fuels
Ephrem Chemali et al.
Summary: This paper introduces a CNN-based framework for estimating the state-of-health (SOH) of Li-ion batteries directly from voltage, current, and temperature measurements during charging. The proposed algorithm achieved a low average error and high accuracy under different charge states and temperatures.
Article
Thermodynamics
Zhicheng Xu et al.
Summary: An accurate estimation of the state of charge (SOC) and state of health (SOH) of lithium-ion batteries is crucial for their management system, as well as for the safety and performance of electric vehicles and energy storage systems. A model-based method utilizing an equivalent circuit model and a minimalist electrochemical model has been proposed to simultaneously assess SOC and SOH, showing promising results with a mean error of around 2% for predicting battery capacity. This co-estimation method proves to be effective in real-time tracking of battery health and state of charge.
Review
Chemistry, Physical
Shida Jiang et al.
Summary: Batteries, especially lead-acid batteries, play a crucial role in modern society. This review examines various methods for estimating the state of health (SOH) of lead-acid batteries, categorizing them into different classes and analyzing their characteristics, advantages, and limitations in practical applications. Recommended methods for different scenarios are provided, along with unresolved issues to inspire further research in this field.
JOURNAL OF POWER SOURCES
(2022)
Article
Chemistry, Physical
Mingqiang Lin et al.
Summary: This paper proposes a multi-feature-based multi-model fusion method for estimating the state-of-health (SOH) of lithium-ion batteries. By extracting features from different sources and using multi-model fusion, the accuracy of SOH estimation is improved.
JOURNAL OF POWER SOURCES
(2022)
Article
Engineering, Electrical & Electronic
Zhongbao Wei et al.
Summary: This study proposes a multistage SOH estimation method that can accurately estimate the health status of LIBs even under partial charging conditions. By extracting different sets of health indicators and using artificial neural networks for fusion, the accuracy and robustness of the estimates are improved.
IEEE TRANSACTIONS ON POWER ELECTRONICS
(2022)
Article
Thermodynamics
Zhiqiang Lyu et al.
Summary: This study proposes a hybrid kernel function relevance vector machine (HKRVM) optimized model for battery prognostics and health management. It extracts ageing features (AFs) from the incremental capacity curve to monitor battery state of health (SOH) and predicts remaining useful life (RUL) using a metabolic extreme learning machine. The HKRVM captures the relationship between AFs and capacity and determines optimal weights and kernel parameters using a genetic grey wolf optimizer (GGWO).
Article
Thermodynamics
Mingqiang Lin et al.
Summary: Accurate state of health estimation is crucial for lithium-ion batteries management. This paper proposes a novel method using simulated annealing algorithm and support vector regression, which extracts health factors from DTC curves and constructs a model to estimate SOH with optimized hyperparameters. Experimental results show the superiority of the proposed method in accuracy and real-time performance compared to other models.
Article
Energy & Fuels
Yi-Feng Luo et al.
Summary: This paper proposes a method to predict the battery current SOH using the training data from electrochemical impedance spectroscopy when the battery is fully charged. The results show that the estimated SOH has a maximum relative error of only 1.31% with the best performance neural network. Furthermore, a technique to estimate the battery SOH under different temperatures without collecting the AC impedance through the whole cycle life test is discussed.
JOURNAL OF ENERGY STORAGE
(2022)
Article
Energy & Fuels
Zixuan Wei et al.
Summary: This paper proposes an assessment method for the state of health of echelon utilization batteries based on deep neural network learning with error correction. The main characteristic parameters characterizing the performance aging of echelon utilization batteries are mined, and a state of health evaluation model is established using deep neural network learning. The prediction accuracy of the model is further improved using Markov chain error correction. The simulation analysis verifies the effectiveness of the proposed method, with average absolute errors of the state of health prediction for echelon utilization batteries being less than 0.8%.
JOURNAL OF ENERGY STORAGE
(2022)
Article
Energy & Fuels
Danhua Zhou et al.
Summary: Accurate estimation of the state of health (SOH) of lithium-ion batteries is crucial for ensuring their safe use. A novel attention depthwise temporal convolutional network (AD-TCN) model is proposed for SOH estimation, considering the degradation trend of voltage and temperature as the health feature sequence. The model shows strong reliability and high prediction accuracy.
JOURNAL OF ENERGY STORAGE
(2022)
Article
Energy & Fuels
Xiaojia Su et al.
Summary: Accurate capacity estimation is crucial for the safety and reliability improvement of lithium-ion battery systems. This paper proposes a fast capacity estimation method for Li-ion batteries by extracting health indicators through online identification of Low-frequency electrochemical impedance spectroscopy (LEIS) using Gaussian process regression (GPR). The results show high accuracy in state of health (SOH) estimation, making it vital for online SOH evaluation and early safety warning.
Article
Thermodynamics
Jianping Wen et al.
Summary: In this paper, a battery SOH prediction model based on incremental capacity analysis and BP neural network is proposed to predict battery SOH at different ambient temperatures. By analyzing the correlation between the characteristics of IC curve and SOH, the mapping relationship between temperature and IC curve characteristics is established, and the SOH prediction model at different temperatures is obtained. The accuracy of the model is verified by comparing the model test results and experimental results.
Article
Energy & Fuels
Xiaojia Su et al.
Summary: Accurate capacity estimation is critical to improving the safety and reliability of lithium-ion battery systems. This paper proposes a method combining LEIS and GPR for fast capacity estimation of Li-ion batteries, achieving a goodness-of-fit of 0.96 and significantly improving SOH estimation accuracy with novel HIs related to the Li-ion diffusion coefficient.
Article
Thermodynamics
Lei Yao et al.
Summary: This study proposes an intelligent fault diagnosis method based on support vector machine for Lithium-ion batteries. It includes denoising, modification of covariance matrix to reduce current fluctuation influence, and optimization of SVM parameters through grid search method to achieve high accuracy and timeliness.
Article
Thermodynamics
Yuejiu Zheng et al.
Summary: This paper proposes a framework for battery capacity prediction based on the feedforward empirical model and the feedback data-driven method. By modifying the parameters of the empirical model based on the difference of estimated capacities, the fusion capacity is predicted accurately.
Article
Thermodynamics
L. Vichard et al.
Summary: Batteries are complex systems that are affected by variable ambient operating conditions, and understanding their dynamic behavior and degradation laws under actual conditions is essential for durability improvement. This study proposes a method to model batteries based on experimental data from postal vehicles, which shows promising results in estimating state of health indicators linked to internal resistance and available capacity. The proposed model aims to provide accurate state of charge estimation onboard and contribute to a better understanding of battery degradation laws.
Article
Engineering, Multidisciplinary
Xin Li et al.
Summary: This paper presents a method for predicting the remaining useful life (RUL) of lithium-ion batteries in electric vehicles using a dual filters fusion algorithm. The algorithm updates battery degradation state and model parameters simultaneously, providing superior performance for RUL prediction.
Article
Chemistry, Physical
Kodjo S. R. Mawonou et al.
Summary: This paper investigates the critical health assessment of Lithium-ion batteries and proposes two new aging indicators to improve current solutions, as well as introducing a data-driven battery aging prediction method using the random forest algorithm. The study shows that these methods can generate reliable health status evaluation and high-precision aging prediction.
JOURNAL OF POWER SOURCES
(2021)
Article
Automation & Control Systems
Lei Ren et al.
Summary: The integration of various aspects of the manufacturing process with new information technologies like IoT, big data, and cloud computing leads to more flexible and intelligent industrial manufacturing systems. This paper proposes a new LIB RUL prediction method named Auto-CNN-LSTM, based on improved CNN and LSTM, which utilizes an autoencoder to enhance data dimensions for better training and a filter for smoother output. Experiments show the effectiveness of this method compared to other commonly used techniques.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2021)
Article
Energy & Fuels
Qiao Wang et al.
Summary: This paper proposes a co-estimation model for accurately estimating the SOC and capacity of aged lithium-ion batteries based on charging data. The results show that the proposed model outperforms other models, with a maximum RMSE of 0.85% and a computational cost below 5 s.
Article
Energy & Fuels
Marvin Messing et al.
Summary: This paper introduces a method for estimating State of Health (SoH) of batteries using Electrochemical Impedance Spectroscopy (EIS) technology, combining fractional order impedance modeling and short-term relaxation effects for rapid SoH determination. The method has demonstrated an average estimation error of less than 1% and offers a new way of utilizing EIS for SoH estimation.
JOURNAL OF ENERGY STORAGE
(2021)
Article
Energy & Fuels
Joonki Hong et al.
Article
Computer Science, Information Systems
Danhua Zhou et al.
Article
Engineering, Electrical & Electronic
Yinjiao Xing et al.
MICROELECTRONICS RELIABILITY
(2013)
Article
Engineering, Electrical & Electronic
Akram Eddahech et al.
INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS
(2012)
Article
Chemistry, Physical
Wei He et al.
JOURNAL OF POWER SOURCES
(2011)
