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
Hongyan Zuo et al.
Summary: The article establishes a coupled electrochemical-thermal model to describe the surface temperature of a power lithium manganate battery during the discharging process, and estimates the SOC values under different discharging conditions using an improved functional link neural network model. The results indicate that the improved neural network model has higher SOC estimation accuracy.
Article
Thermodynamics
E. Jiaqiang et al.
Summary: This paper investigates the essence of inconsistency in lithium-ion batteries as State-Of-Charge (SOC) inconsistency, proposing a method to describe battery inconsistency using SOC disparity and studying the equalization control strategy. Through simulations and experiments, it is shown that active equalization significantly improves cell inconsistency and enhances energy utilization in the battery pack during charging and discharging processes. The proposed SOC estimation method meets accuracy requirements, and the equalization strategies effectively minimize SOC and voltage disparities among battery cells.
Review
Thermodynamics
Mohammad Shahjalal et al.
Summary: This paper provides a comprehensive overview of the present state of second-life Li-ion batteries by exploring relevant literature, including surveys on the fundamentals of Li-ion battery degradation and experimental approaches, as well as discussions on the obstacles and methods of reusing and recycling Li-ion batteries, related applications, cost issues, and business models.
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
Thermodynamics
Chuanping Lin et al.
Summary: This paper proposes a battery state of health estimation method based on constant current charging time, which can accurately and quickly estimate the health status of the battery. Compared with traditional methods, this method has higher prediction accuracy, requires less data, and has shorter training and prediction time.
Article
Chemistry, Physical
Zhongwei Deng et al.
Summary: Battery health monitoring is crucial for the maintenance and safety of electric vehicles. This paper proposes a method that utilizes early aging data of batteries to recognize degradation patterns and apply transfer learning for accurate state of health (SOH) estimation. The study demonstrates the effectiveness of using features extracted from battery discharge capacity curves and compares the performance of different machine learning algorithms, with Long short-term memory (LSTM) network achieving the best estimation accuracy. The proposed recognition and transfer learning methods further improve the estimation accuracy with mean absolute errors (MAE) and root mean square errors (RMSE) averaging at only 0.94% and 1.13%.
JOURNAL OF POWER SOURCES
(2022)
Article
Chemistry, Applied
Xinyan Liu et al.
Summary: This study presents a data-driven approach to forecast the capacity fading trajectory of lab-assembled lithium batteries, achieving high prediction accuracy under different conditions. The extracted features with physical meanings provide insights for the development of better batteries.
JOURNAL OF ENERGY CHEMISTRY
(2022)
Article
Energy & Fuels
Lewis Driscoll et al.
Summary: In this paper, a simple and effective machine learning-based model for estimating the state of health of lithium-ion batteries is proposed. The model extracts features from voltage, current, and temperature profiles and uses artificial neural networks for estimation. Experimental results show that the proposed model can accurately estimate the state of health of discharged batteries under different conditions with less input data required.
JOURNAL OF ENERGY STORAGE
(2022)
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
Isaias Gonzalez et al.
Summary: This paper presents a monitoring system for visualizing the operation of a Lithium-ion Battery (LiB), using Internet of Things (IoT) technology for data acquisition and analysis. The feasibility and successful performance of the system are demonstrated through experimental data.
JOURNAL OF ENERGY STORAGE
(2022)
Article
Energy & Fuels
Ruomei Zhou et al.
Summary: A novel State of Health (SOH) estimation method for fast-charging batteries is proposed in this study, using incremental capacity (IC) analysis and Gaussian process regression (GPR). The study discusses the aging of batteries under fast-charging conditions, introduces a new feature extracted from IC curves for SOH estimation, and establishes a GPR model trained with extracted features. The proposed method achieves over 90% reduction in mean absolute percentage error on two fast-charging batteries datasets.
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
Thermodynamics
Fu-Kwun Wang et al.
Summary: Accurately predicting the online remaining useful life (RUL) of batteries is crucial in industrial applications of battery management systems. This study proposes a bidirectional long short-term memory with attention mechanism (Bi-LSTM-AM) model for RUL prediction, continuously updating the model parameters. The model's performance is evaluated using six lithium-ion batteries and achieves relative errors ranging from 0% to 1.41%. The reliability of the model is further assessed by providing a prediction interval for RUL using the Monte Carlo dropout approach.
Review
Energy & Fuels
Xin Lai et al.
Summary: This study reviews the framework and methods of life cycle assessment (LCA) and evaluates the entire lifespan of lithium-ion batteries (LIBs). The results show that battery production significantly impacts the environment and resources, while battery materials recycling and remanufacturing have considerable environmental and economic values. Moreover, greening of electricity is critical to reducing carbon emissions during the battery life cycle.
Article
Energy & Fuels
Xiaoyu Li et al.
Summary: In this paper, a data-fusion method is proposed to forecast battery health conditions. The method utilizes Gaussian process regression to establish state and observation equations, and applies a particle filter algorithm for short-term and long-term health estimation and prediction. Experimental results demonstrate the accurate and robust forecasting capability of the proposed method.
Article
Automation & Control Systems
Kailong Liu et al.
Summary: This article applies advanced machine-learning techniques to predict future capacities and RUL for lithium-ion batteries with uncertainty quantification. The combined LSTM+GPR model outperforms other counterparts and provides accurate results for both 1-step and multistep ahead capacity predictions, demonstrating good adaptability and reliable uncertainty quantification for battery health diagnosis even at the early battery cycle stage.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2021)
Article
Energy & Fuels
Jianfang Jia et al.
Summary: This paper proposes a novel multi-scale model for SoH prediction in lithium-ion batteries, which processes temperature characteristic data in the frequency domain and determines alternative frequency bands for the temperature characteristics and battery capacity degradation using wavelet packet transform and correlation analysis. The prediction accuracy and robustness are improved compared with other data-driven methods, with a root-mean-square error value of less than 1.33% in SoH prediction.
JOURNAL OF ENERGY STORAGE
(2021)
Article
Energy & Fuels
Elisa Y. M. Ang et al.
Summary: This paper presents an intuitive and efficient predictive algorithm for estimating the State of Health (SoH) of lithium-ion batteries with accuracy comparable to more complex models. Key to achieving good prediction accuracy lies in data preprocessing, while a simplified version of the algorithm using only voltage time profiles is proposed for easier implementation.
JOURNAL OF ENERGY STORAGE
(2021)
Article
Energy & Fuels
Seongyoon Kim et al.
Summary: We propose a deep-learning based method for accurately predicting state-of-health and remaining useful life of Lithium-ion batteries, utilizing transfer learning to predict different battery types' states. The proposed method also estimates predictive uncertainty and degradation patterns, demonstrating reliability and accuracy in forecasting even for used batteries. Simulation results showcase the effectiveness of the model in reducing data collection efforts for new battery types.
JOURNAL OF ENERGY STORAGE
(2021)
Review
Chemistry, Physical
Valentin Sulzer et al.
Summary: Accurate battery life prediction is crucial for various applications, but existing methods based on lab data need to incorporate field data for a complete understanding of cell aging. Challenges arise due to uncontrolled operating conditions, less accurate sensors, and infrequent validation checks in real-world applications. Combining machine learning with physical models shows promise in estimating battery life, assessing second-life condition, and predicting future usage conditions.
Article
Engineering, Electrical & Electronic
Brahim Zraibi et al.
Summary: This paper suggests a hybrid method utilizing machine learning for predicting the remaining useful life of lithium-ion batteries, demonstrating the potential of new data-driven estimation approaches in battery life prediction.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2021)
Article
Energy & Fuels
Matteo Moncecchi et al.
Article
Engineering, Electrical & Electronic
Jinpeng Tian et al.
IEEE TRANSACTIONS ON POWER ELECTRONICS
(2020)
Article
Engineering, Electrical & Electronic
Wei Liu et al.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2020)
Review
Chemistry, Physical
Xiaosong Hu et al.
Article
Thermodynamics
Yuanwang Deng et al.
Article
Energy & Fuels
Kristen A. Severson et al.
Review
Green & Sustainable Science & Technology
Yi Li et al.
RENEWABLE & SUSTAINABLE ENERGY REVIEWS
(2019)
Article
Thermodynamics
Zengkai Wang et al.
Review
Energy & Fuels
Xuebing Han et al.
Article
Chemistry, Physical
Yi Li et al.
JOURNAL OF POWER SOURCES
(2018)
Article
Chemistry, Physical
Hisashi Kato et al.
JOURNAL OF POWER SOURCES
(2018)
Article
Green & Sustainable Science & Technology
Yan Jiang et al.
JOURNAL OF CLEANER PRODUCTION
(2018)
Article
Engineering, Electrical & Electronic
Ran Gu et al.
IEEE TRANSACTIONS ON TRANSPORTATION ELECTRIFICATION
(2016)
Article
Engineering, Electrical & Electronic
Yinjiao Xing et al.
MICROELECTRONICS RELIABILITY
(2013)