Related references
Note: Only part of the references are listed.
Article
Automation & Control Systems
Zhongbao Wei et al.
Summary: This article proposes a thermal-model-based method for multistate joint observation in lithium-ion battery management. By embedding distributed temperature sensors, a novel smart battery design enables real-time monitoring of internal and surface temperatures, as well as state parameters with high space resolution.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2023)
Article
Automation & Control Systems
Xinghao Du et al.
Summary: This article proposes a novel series-connected dual pseudorandom sequence for enhancing the signal power content in all frequency ranges in online battery impedance acquisition. A weighted bilateral impedance filter is further carried out to process the measurement data, compensating for noise-induced biases and achieving nearly unbiased results. Experimental studies verify the accuracy and robustness of the proposed method.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2023)
Article
Chemistry, Applied
Rui Xiong et al.
Summary: This study proposes a convolutional neural network (CNN) based method for accurate battery capacity estimation using only raw impedance spectra as input. An input reconstruction module is designed to effectively utilize impedance spectra without corresponding capacities, reducing the cost of collecting training data. The proposed method outperforms supervised benchmarks, even with fewer samples with measured capacities, and can reduce the root mean square error by up to 50.66%.
JOURNAL OF ENERGY CHEMISTRY
(2023)
Article
Electrochemistry
Jinpeng Tian et al.
Summary: In this study, a data-driven solution is proposed to predict battery impedance spectra at different states. An encoder-decoder deep neural network is developed to simultaneously predict impedance spectra and state of charge using short-term pulse data sampled at 1 Hz, eliminating the need for specific hardware and reducing test requirements. Validation results show that the proposed method enables accurate predictions at different temperatures and ageing levels, with errors of impedance spectra and SOC restricted within 1.5 mΩ and 1.26%, respectively. Additionally, the predicted impedance spectra provide detailed physical insight into battery kinetics and allow for accurate extraction of critical parameters of an impedance model. This method makes EIS measurement more accessible for evaluating battery characteristics and demonstrates the potential of deep learning in battery research.
ELECTROCHIMICA ACTA
(2023)
Article
Engineering, Civil
Quanqing Yu et al.
Summary: In this paper, a SOC estimation method for a series-parallel lithium-ion battery pack based on the newly constructed OCV-SOC-temperature relationship was proposed. The method utilizes cosine similarity to quantify cell inconsistency and constructs the OCV-SOC-temperature relationship of the battery pack using representative cells. A multi-branch fusion method is then used to estimate the SOC of the battery pack. The accuracy of the proposed method is verified under various dynamic conditions, with an estimated SOC error of less than 1.5%.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Multidisciplinary Sciences
Jiahuan Lu et al.
Summary: This article presents a deep-learning framework that enables accurate estimation of battery state of health without the need for target battery labels. The framework utilizes deep neural networks with domain adaptation to produce accurate results.
NATURE COMMUNICATIONS
(2023)
Article
Chemistry, Physical
Matthieu Dubarry et al.
Summary: Digital twins are cyber-physical systems that integrate real-time sensor data and models for accurate predictions and optimal decisions in specific assets. In the case of batteries, this concept has been applied at different scales. However, a comprehensive approach is needed for battery digital twins to achieve their full potential in industrial settings. Standardized and transparent data sharing, as well as principled methods to quantify and propagate uncertainty, are essential. Physical modeling and sensing approaches for battery manufacturing and thermal runaway also need improvement.
Article
Chemistry, Physical
Rui Xiong et al.
Summary: In this study, a novel method combining four algorithms was proposed to select the most important features for estimating the state of health (SOH) of lithium-ion batteries (LiBs). The selected features improved the accuracy of SOH estimation by 63.5% and 71.1% for NCA and LFP batteries, respectively, compared to using all features. Additionally, the method allowed the use of data obtained in partial voltage ranges, resulting in minimum root mean square errors of 1.2% and 1.6% for NCA and LFP batteries, respectively, demonstrating its capability for onboard applications.
ENERGY STORAGE MATERIALS
(2023)
Article
Multidisciplinary Sciences
Xiaopeng Tang et al.
Summary: Onboard measuring the electrochemical impedance spectroscopy (EIS) for lithium-ion batteries has been a challenging issue for the development of technologies like portable electronics and electric vehicles. In this study, we propose a fast and accurate EIS predicting system by combining the fractional-order electric circuit model with a median-filtered neural network machine learning. Our method allows using size-varying input data sampled at a rate down to 10 Hz and unlocks opportunities to detect the battery's internal electrochemical characteristics onboard via low-cost embedded sensors.
Article
Thermodynamics
Shanshan Guo et al.
Summary: This study investigates the performance of four state-of-the-art deep learning algorithms in state-of-charge estimation, evaluating their accuracy, robustness, and efficiency using experimental data.
Article
Thermodynamics
Hanqing Yu et al.
Summary: In order to ensure the secure and healthy usage of lithium-ion batteries, accurately estimating the state of charge (SOC) in battery management systems is necessary. The development of deep learning (DL) provides a new solution for battery SOC estimation. This paper proposes a method that integrates mechanism knowledge of the battery domain into the DL framework, resulting in improved SOC estimation performance.
Article
Thermodynamics
Bo Jiang et al.
Summary: This study proposes a mechanics-based battery SOC estimation using deep learning techniques, which establishes the relationship between battery stress and SOC and achieves the interlink between battery external measurements and internal states. Experimental results demonstrate that the proposed method achieves acceptable accuracy under different conditions and limited data length.
Article
Automation & Control Systems
Xinghao Du et al.
Summary: Broadband battery impedance spectroscopy provides valuable information for states estimation and fault diagnosis. This article proposes a novel hybrid pseudorandom sequence (HPRS) to enhance signal power in the low-frequency region and suppress disturbances. The feasibility of the HPRS signal is experimentally verified, demonstrating superior accuracy and robustness in impedance measurements under different ambient temperatures and state of charges (SOCs), with a maximum normalized root-mean-square error (NRMSE) limited to 0.77%.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2023)
Review
Chemistry, Physical
Zijie Huang et al.
Summary: In this review, the task-oriented implementation of machine learning in battery health is comprehensively discussed, focusing on specific features and targets in different application scenarios. The article explores the tasks assisted by ML based on multi-level cell degradation and highlights the significance of considering potential feature-target pairs during model training to gain more health information about LIBs and to design tasks for new application scenarios.
Article
Energy & Fuels
Kaixuan Zhang et al.
Summary: This study proposes a pseudo-open circuit voltage (OCV) modeling method to improve the performance of a closed-loop feedback correction. First, the relationship between the derivative of OCV and SOC is analyzed to select the appropriate SOC interval for OCV curve construction. Then, a pseudo-OCV curve is established and compared with the real OCV to determine the optimal construction interval. Finally, SOC estimation is carried out using the constructed full pseudo-OCV and compared with the reference SOC, with results showing an SOC estimation error of less than 3% over the full SOC range.
Article
Multidisciplinary Sciences
Matthieu Dubarry et al.
Summary: To address the challenge of diagnosing photovoltaics-connected Li-ion batteries, the authors propose a diagnostic methodology that utilizes machine learning algorithms trained on data from the photovoltaic charging process. This approach effectively reduces the diagnostic error by directly utilizing the data from the charging process.
NATURE COMMUNICATIONS
(2023)
Review
Energy & Fuels
M. S. Reza et al.
Summary: The continuously growing population and urban growth rates are responsible for the sharp rise in energy consumption, which leads to increased CO2 emissions and demand-supply imbalances. The power sector is switching to alternative energy sources, such as renewable energy resources (RES) and battery energy storage systems (BESS), due to an increase in the use of fossil fuels and their shortage. However, the uncertainty associated with the power generation of these resources and their integration into the power grid pose complex challenges, and thus, research on system uncertainties is receiving increasing attention.
JOURNAL OF ENERGY STORAGE
(2023)
Article
Energy & Fuels
Fulai An et al.
Journal of Energy Storage
(2023)
Article
Energy & Fuels
Quanqing Yu et al.
Summary: Lithium-ion batteries are considered the best energy storage option for various portable and energy storage applications. Efficient fault diagnosis methods are crucial to address safety risks. This review examines and compares fault modes, data, and diagnosis methods in different scenarios, such as the laboratory, electric vehicles, energy storage systems, and simulation. The limitations and performance of these methods, as well as the challenges and outlook for real-world applications, are discussed. More significant work is needed to apply laboratory research advancements to improve fault diagnosis accuracy in real-world applications.
Article
Energy & Fuels
Zhimin Xi et al.
Summary: This paper proposes a time-delayed recurrent neural network for lithium ion battery modeling and SOC estimation, and analyzes its performance. It is found that overexcited neurons may cause poor performance of the neural network.
Article
Energy & Fuels
Chia-Wei Hsu et al.
Summary: By developing novel deep neural networks and utilizing special training strategies, it is possible to predict the residual life of a battery and accurately forecast the cycle profiles of used batteries with just one cycle of testing. This provides higher accuracy and economic benefits for battery reuse and recycling.
Article
Energy & Fuels
Weihan Li et al.
Summary: The accurate real-time prediction of the dynamic available charging and discharging power of the battery is essential for the safety and longevity of battery energy storage systems, but it is challenging due to high nonlinearities in battery dynamics. This paper presents an electrochemical model-based online state-of-power prediction algorithm for lithium-ion batteries, which improves the safety and reliability of battery operation.
Article
Chemistry, Physical
Shuzhi Zhang et al.
Summary: This paper presents a novel low-complexity state-of-energy (SOE) estimation method for series-connected lithium-ion battery pack based on representative cell selection and operating mode division. The method accurately estimates the SOE of the battery pack by tracking the freshest cell and the oldest cell, dividing battery cell operating mode into two classes, and using an adaptive weighted strategy. Validation results show that the developed method achieves accurate SOE estimation with limited error bands.
JOURNAL OF POWER SOURCES
(2022)
Article
Chemistry, Physical
Te Han et al.
Summary: This study proposes a novel deep learning framework assisted with domain adaptation for real-time capacity estimation of lithium-ion batteries, achieving nonlinear mapping between monitored data and battery capacity to improve estimation precision when dealing with inconsistent battery data.
JOURNAL OF POWER SOURCES
(2022)
Article
Energy & Fuels
Isaiah Oyewole et al.
Summary: In this paper, a Controllable Deep Transfer Learning (CDTL) network is proposed for short and long-term state-of-charge (SOC) estimation. The CDTL utilizes shared knowledge between target cells and historical source cells using controllable Multiple Domain Adaptation (MDA). Experimental results demonstrate that the CDTL outperforms existing benchmarks in deep learning and transfer learning.
Article
Energy & Fuels
Yan Cheng et al.
Summary: The traditional method for estimating the state of charge (SOC) of a battery using neural networks has a large estimation error when there are drastic changes in current and voltage. To solve this problem, a new method based on wavelet transform is proposed, which improves the accuracy of battery SOC estimation.
Article
Thermodynamics
Chunsheng Hu et al.
Summary: This paper proposes a method for estimating the state of charge (SoC) of LiFePO4 batteries during the charging process using a deep neural network (DNN). Battery data collected from different charging protocols are used to train the DNN model. The developed DNN can accurately estimate the battery's SoC during charging and can be used to calculate the SoC during discharging. Experimental results show that the maximum error and root mean square error of the SoC estimation using DNN are within an acceptable range.
Article
Thermodynamics
Shuzhi Zhang et al.
Summary: In this paper, a comparative study of different adaptive extended Kalman filters (AEKFs)/adaptive unscented Kalman filters (AUKFs) is conducted to achieve more precise and reliable lithium-ion battery state-of-charge (SOC) estimation. A novel multi-objective analysis decision method is proposed to allocate weights for various extracted indexes and further compare the comprehensive estimation performance of different AEKFs/AUKFs. The results provide suggestions and guidance for researchers when choosing AEKFs/AUKFs for online SOC estimation.
Article
Thermodynamics
Kuo Yang et al.
Summary: This study proposes a deep learning approach based on a dual-stage attention mechanism to improve the accuracy of state of charge (SOC) estimation for lithium-ion batteries and reduce the influence of noise. By incorporating domain knowledge features such as current, voltage, and temperature into an encoder-decoder network with gated recurrent units, useful features can be adaptively extracted. The proposed method utilizes attention mechanisms to consider the correlation of time series and accurately estimate SOC.
Article
Engineering, Electrical & Electronic
Naifeng Gan et al.
Summary: This article proposes a two-layer overdischarge fault diagnosis strategy based on machine learning for detecting and preventing overdischarge in lithium-ion batteries for electric vehicles. The method involves comparing battery voltage with cutoff voltage and utilizing a detection approach based on the eXtreme Gradient Boosting algorithm.
IEEE TRANSACTIONS ON POWER ELECTRONICS
(2022)
Article
Electrochemistry
Chunsheng Hu et al.
Summary: This paper proposes a novel neural network method, TCN-LSTM model, for accurate and robust estimation of the state of charge (SOC) of lithium-ion batteries. The proposed method combines temporal convolutional network (TCN) and long short-term memory (LSTM), and achieves excellent generalization and robustness in various estimation conditions.
JOURNAL OF THE ELECTROCHEMICAL SOCIETY
(2022)
Article
Engineering, Mechanical
Weihua Li et al.
Summary: Deep Transfer Learning combines the advantages of Deep Learning in feature representation and Transfer Learning in knowledge transfer, making DL-based fault diagnosis methods more reliable and robust. However, further research is needed to explore the potential of DTL-based approaches in Intelligent Fault Diagnosis.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2022)
Article
Chemistry, Physical
Glenn Palmer et al.
Summary: This paper presents a calibration method to improve the accuracy of uncertainty estimation in machine learning models. It demonstrates that the direct bootstrap ensemble standard deviation is not an accurate estimate of uncertainty, but can be improved through calibration.
NPJ COMPUTATIONAL MATERIALS
(2022)
Article
Chemistry, Physical
Le Xu et al.
Summary: A novel non-destructive parameter identification method is proposed in this study to optimize the electrochemical model, and successful experimental results are demonstrated.
ENERGY STORAGE MATERIALS
(2022)
Article
Energy & Fuels
Arpita Mondal et al.
Summary: An approach combining online parameter identification and improved adaptive extended Kalman filter is proposed to estimate the state-of-charge (SoC) of Li-ion battery. The effectiveness of this approach is validated through experiments under various complex operating conditions. Additionally, the approach is integrated into a cloud-based system to ensure continuous and accurate battery state monitoring.
JOURNAL OF ENERGY STORAGE
(2022)
Review
Chemistry, Physical
Yang Lu et al.
Summary: Comprehensive understanding of multiple Li kinetics in batteries is crucial for studying mechanisms and designing materials. Time scale information in batteries can provide insights into various kinetic processes, such as ionic conductions, charge transfer, and diffusion. Time scale characterization, combined with non-destructive impedance characterization, can be a powerful tool for online battery monitoring.
Article
Engineering, Multidisciplinary
Dickson N. T. How et al.
Summary: SOC is a crucial battery quantity that requires machine learning for estimation, with deep learning being a prominent approach. However, optimal performance depends on proper hyperparameter selection. This study proposes an automated approach using TPE optimization and Hyperband pruning algorithm.
IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS
(2022)
Article
Engineering, Industrial
Te Han et al.
Summary: This article presents a novel OOD detection-assisted trustworthy machinery fault diagnosis approach, which integrates multiple deep neural networks and utilizes uncertainty analysis to enhance the reliability and safety of intelligent models, showing significant advantages in identifying OOD samples.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2022)
Review
Chemistry, Applied
Kai Luo et al.
Summary: This paper emphasizes the significance of predicting the state of charge and the state of health of lithium-ion batteries in the field of energy storage. The review highlights the utilization of machine learning and deep learning approaches to establish data-driven models for accurate and efficient battery performance prediction. The details, advantages, and limitations of these approaches are presented, compared, and summarized. Additionally, future challenges and opportunities are discussed.
JOURNAL OF ENERGY CHEMISTRY
(2022)
Article
Engineering, Electrical & Electronic
Xueyuan Wang et al.
Summary: This article proposes a fast calculation method based on the S transform for obtaining broadband battery impedance. By processing the step disturbance and response generated by a common charging/discharging device, the method reduces the requirements for impedance acquisition and improves calculation efficiency. The experimental results show that the method has high accuracy within the error range of both the real and imaginary parts, and can save a significant amount of time compared to traditional methods.
IEEE TRANSACTIONS ON TRANSPORTATION ELECTRIFICATION
(2022)
Review
Energy & Fuels
Aaruththiran Manoharan et al.
Summary: This review paper discusses the application of Artificial Intelligence in Li-ion battery state estimation for Electric Vehicles. It focuses on data-driven methods for estimating State of Charge and State of Health, and reviews recent works using Support Vector Machines, Gradient Boosting, and Artificial Neural Networks. The implementation of proposed algorithms on hardware prototypes and current challenges are also discussed, along with a detailed analysis of input features and future research directions.
JOURNAL OF ENERGY STORAGE
(2022)
Article
Chemistry, Physical
Jinpeng Tian et al.
Summary: Accurately monitoring battery states is crucial for developing intelligent battery management systems. This study presents a flexible method that can estimate both maximum and remaining capacities using only short pieces of charging data, addressing the challenges of state of health and state of charge estimation. Experimental results demonstrate that the proposed method achieves reliable estimation on different types of batteries.
ENERGY STORAGE MATERIALS
(2022)
Article
Chemistry, Physical
Jinpeng Tian et al.
Summary: Accurate estimation of state of charge (SOC) is vital for the reliable operations of lithium-ion batteries. This study proposes a solution that incorporates domain knowledge into deep learning-based SOC estimation, resulting in improved accuracy. By decoupling voltage and current sequences, and fusing SOC estimation results from deep neural networks (DNNs) with short-term Ampere-hour predictions, the proposed method achieves significant reduction in estimation errors.
ENERGY STORAGE MATERIALS
(2022)
Article
Energy & Fuels
Xiaopeng Tang et al.
Summary: The long-term storage of battery operating data is crucial for tracking and analyzing historical usage. The vast amount of raw data generated daily poses a challenge, requiring an efficient data compression method. This paper proposes a method that records the entire current trajectory while only capturing partial voltage data, achieving accurate data reconstruction through the establishment of a battery model and the use of a corrector.
Article
Engineering, Electrical & Electronic
Ruibing Jin et al.
Summary: In industry, the prediction of remaining useful life (RUL) using deep learning techniques plays a crucial role in improving system reliability and efficiency. However, existing methods that directly use raw signals suffer from noise and therefore have degraded RUL prediction accuracy. To address this, we propose a new handcrafted feature representation and a novel two-stream network to effectively integrate these features with the raw input signals.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2022)
Review
Chemistry, Multidisciplinary
Yudi Qin et al.
Summary: This review focuses on the mechanisms, effects, and supporting hardware of pulsed operation on lithium-ion batteries (LIBs) for future grids. The study found that pulsed operation, with appropriate parameters, can effectively address the instability issues caused by the large-scale utilization of renewable energy sources, even under high-power charging and low-temperature operation.
CELL REPORTS PHYSICAL SCIENCE
(2022)
Article
Thermodynamics
Xiong Feng et al.
Summary: This paper presents a novel neural network structure called CWRNN, which effectively addresses long-term dependencies, reduces training and computation costs, and is validated under different temperature conditions.
Article
Thermodynamics
Xiaoqing Ren et al.
Summary: This paper proposes a long short-term memory neural network based on particle swarm optimization for state-of-charge estimation of lithium-ion batteries. By optimizing parameters and adding random noise, the method improves estimation accuracy and anti-interference ability, with experimental results showing accurate estimation under different conditions.
Article
Chemistry, Physical
Marco Ragone et al.
Summary: This study proposes a modeling framework for SOC estimation using different machine learning methods, including SVR, ANN, and LSTM networks. By developing training data from simulations of BEV and integrating LIB's electrochemical model, a more precise SOC estimation can be achieved. The research emphasizes the importance of considering different components of BEV in the development of informative datasets.
JOURNAL OF POWER SOURCES
(2021)
Review
Chemistry, Physical
Donal P. Finegan et al.
Summary: The article discusses how to improve the accuracy of battery failure prediction by designing experiments, processing data, applying data prediction methods, and using physics knowledge to reduce the number of experiments and costs.
Article
Chemistry, Physical
Yufang Lu et al.
Summary: A novel decomposed electrode model (DEM) is proposed in this paper for real-time observation of anode potential in lithium-ion batteries, showing high accuracy and computational efficiency. This model can also be used to develop a lithium plating-free fast charging algorithm.
JOURNAL OF POWER SOURCES
(2021)
Article
Electrochemistry
Qingrui Gong et al.
Summary: This paper proposes a hybrid neural network model based on deep learning for estimating the state of charge (SOC) of lithium-ion batteries. The model consists of convolutional module, ULSAM module, and GRU module for feature extraction and SOC value output. Experimental results demonstrate that the model can accurately estimate SOC values under complex operating conditions.
JOURNAL OF THE ELECTROCHEMICAL SOCIETY
(2021)
Article
Chemistry, Physical
Zhongbao Wei et al.
Summary: With advancements in technology, smart batteries and management systems have emerged as the new focus. Research is shifting towards smart batteries and smart cell management to address the limitations of traditional BMS. Emerging sensing techniques and system integration innovations present new opportunities and challenges for battery management.
JOURNAL OF POWER SOURCES
(2021)
Article
Computer Science, Artificial Intelligence
Eyke Huellermeier et al.
Summary: Uncertainty plays a major role in machine learning, with aleatoric and epistemic uncertainty being two key types. As machine learning becomes increasingly relevant for practical applications, handling uncertainty becomes more important.
Article
Multidisciplinary Sciences
M. A. Hannan et al.
Summary: This article introduces a deep learning-based transformer model for accurate SOC estimation of Li-ion batteries, trained with self-supervised learning to eliminate the need for feature engineering or adaptive filtering. The model achieves low RMSE and MAE at different ambient temperatures, and demonstrates the ability to train with minimal data and still achieve good predictive performance. It also shows that the learning weights from SSL training can be transferred to new Li-ion cells with different chemistry for comparable performance.
SCIENTIFIC REPORTS
(2021)
Article
Engineering, Multidisciplinary
Mahammad A. Hannan et al.
Summary: This study compares commonly used deep learning models and proposes a two-hidden layer stacked gated recurrent unit model trained with a one-cycle policy learning rate scheduler, achieving a minimum RMSE of 0.52% on the train dataset and 0.65% on the test dataset while maintaining a relatively low computation cost.
IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS
(2021)
Article
Engineering, Electrical & Electronic
Arnab Bhattacharjee et al.
Summary: This paper proposes a one-dimensional convolutional neural network-based algorithm for estimating the state of charge of electric vehicle batteries, utilizing transfer learning to improve model generalization and accuracy, and demonstrating the model's ability to learn sufficiently with significantly less data.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2021)
Article
Chemistry, Physical
Antti Aitio et al.
Summary: Using big data techniques, researchers accurately diagnose the health of solar-connected batteries, predicting end of life in advance to address the issue of hundreds of millions lacking access to electricity.
Article
Chemistry, Physical
Yanzhou Duan et al.
Summary: In this paper, a deep learning-based method using a convolutional neural network is proposed to predict impedance spectra in lithium ion batteries over their lifespan. The results show accurate predictions of impedance spectra, validating the effectiveness of the method.
ENERGY STORAGE MATERIALS
(2021)
Article
Engineering, Mechanical
Serkan Kiranyaz et al.
Summary: CNNs have become the standard for various Computer Vision and Machine Learning operations, with 1D CNNs offering advantages in applications with 1D signals. This paper provides a comprehensive review of 1D CNNs architecture, principles, and their recent progress in engineering applications.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2021)
Article
Energy & Fuels
L. Ma et al.
Summary: State of charge (SOC) and state of energy (SOE) are crucial battery states. A novel data-driven method based on LSTM deep neural network was proposed to estimate SOC and SOE simultaneously, showing higher accuracy and robustness compared to other popular algorithms. This approach provides a new way of conducting multiple state estimation of batteries using deep learning.
JOURNAL OF ENERGY STORAGE
(2021)
Article
Energy & Fuels
Yu Liu et al.
Summary: This study investigates accurate state of charge estimation algorithms for lithium-ion batteries based on long short-term memory recurrent neural network and transfer learning. The developed framework shows precise estimation capability of state of charge in different aging states and time-varying temperature conditions. Additionally, the transfer learning algorithm allows for accurate estimation with only 30% training data when transferred to different batteries.
JOURNAL OF ENERGY STORAGE
(2021)
Article
Chemistry, Physical
Jinpeng Tian et al.
Summary: The proposed method in this paper utilizes offline OCV test results to estimate aging diagnosis of lithium ion batteries at an electrode level, achieving fast diagnosis. The estimated aging parameters are close to the results obtained by offline tests, enabling reconstruction of OCV-Q curves for battery capacity estimation with high accuracy. The influence of voltage ranges on estimation results is also discussed in the study.
ENERGY STORAGE MATERIALS
(2021)
Article
Energy & Fuels
Jinpeng Tian et al.
Summary: A method based on deep neural network is proposed for fast and accurate estimation of SOC for LiFePO4 batteries, with an error of less than 2.03% over the entire battery SOC range. By integrating the DNN with a Kalman filter, the robustness of SOC estimation against random noises and error spikes can be improved.
Review
Engineering, Mechanical
Wenwen Wang et al.
Summary: The paper explores the application of digital twin in addressing research challenges related to batteries and the development opportunities in the battery field. It also summarizes the development trends and challenges in smart battery management.
CHINESE JOURNAL OF MECHANICAL ENGINEERING
(2021)
Article
Engineering, Electrical & Electronic
M. A. Hannan et al.
Summary: In this study, a deep fully convolutional network model was proposed to accurately estimate the state-of-charge (SOC) of lithium-ion batteries, achieving impressive performance under different temperature conditions.
IEEE TRANSACTIONS ON POWER ELECTRONICS
(2021)
Article
Chemistry, Physical
Weihan Li et al.
Summary: The study introduces a hybrid state estimation method that combines physics-based and machine learning models to accurately estimate the internal states of lithium-ion batteries, demonstrating high reliability and generalization ability.
JOURNAL OF POWER SOURCES
(2021)
Article
Engineering, Electrical & Electronic
Chong Bian et al.
Summary: The research introduces a deep transfer neural network (DTNN) with multiscale distribution adaptation (MDA) for cross-domain SOC estimation, which learns dynamic features from battery measurements in different domains and minimizes distribution discrepancy through constraint terms. DTNN shows improved performance under specific battery conditions with limited training data, compared to existing transfer learning methods, enhancing generalizability and robustness.
IEEE TRANSACTIONS ON TRANSPORTATION ELECTRIFICATION
(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
Chemistry, Physical
Jinpeng Tian et al.
Summary: The study introduces a method to accurately estimate the entire constant-current charging curves using a deep neural network, which can capture the curves accurately in a short amount of time and demonstrate effectiveness through validation, as well as the advantage of transfer learning.
Review
Energy & Fuels
Xueyuan Wang et al.
Summary: Impedance is closely related to the internal physical and chemical processes of lithium-ion batteries, providing detailed information. This paper reviews over 170 papers and discusses the possibility and value of impedance in onboard battery management, as well as the challenges faced. More significant work is needed to realize a more smart battery management system.
Article
Computer Science, Information Systems
Zhaowei Zhang et al.
Summary: The proposed NAG-based Bi-GRU method leverages deep learning to estimate SOC in lithium-ion batteries, addressing issues with traditional gradient descent algorithms by optimizing the gradient updates and capturing temporal information in both forward and backward directions. Experimental results demonstrate improved precision in SOC estimation across various ambient temperatures compared to previous methods.
Article
Thermodynamics
Chong Bian et al.
Article
Automation & Control Systems
Satadru Dey et al.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2020)
Article
Multidisciplinary Sciences
Peter M. Attia et al.
Review
Computer Science, Artificial Intelligence
Greg Van Houdt et al.
ARTIFICIAL INTELLIGENCE REVIEW
(2020)
Review
Engineering, Mechanical
Yaguo Lei et al.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2020)
Article
Thermodynamics
Fangfang Yang et al.
Article
Energy & Fuels
Weihan Li et al.
JOURNAL OF ENERGY STORAGE
(2020)
Article
Chemistry, Physical
Kai Li et al.
JOURNAL OF POWER SOURCES
(2020)
Article
Engineering, Multidisciplinary
Dickshon N. T. How et al.
IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS
(2020)
Article
Chemistry, Physical
Liang Ma et al.
JOURNAL OF POWER SOURCES
(2020)
Article
Chemistry, Physical
Matthieu Dubarry et al.
JOURNAL OF POWER SOURCES
(2020)
Article
Energy & Fuels
Joonki Hong et al.
Review
Computer Science, Artificial Intelligence
Man-Fai Ng et al.
NATURE MACHINE INTELLIGENCE
(2020)
Article
Automation & Control Systems
Minghang Zhao et al.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2019)
Article
Thermodynamics
Fangfang Yang et al.
Article
Engineering, Electrical & Electronic
Rui Xiong et al.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2019)
Article
Energy & Fuels
Jinhao Meng et al.
IEEE TRANSACTIONS ON ENERGY CONVERSION
(2019)
Article
Electrochemistry
Xianke Lin
JOURNAL OF THE ELECTROCHEMICAL SOCIETY
(2019)
Article
Computer Science, Information Systems
Fangfang Yang et al.
Article
Computer Science, Information Systems
Xiangbao Song et al.
Article
Electrochemistry
Xin Lai et al.
ELECTROCHIMICA ACTA
(2018)
Article
Automation & Control Systems
Ephrem Chemali et al.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2018)
Article
Automation & Control Systems
Zhongbao Wei et al.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2018)
Article
Engineering, Electrical & Electronic
Yongzhi Zhang et al.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2018)
Review
Chemistry, Physical
Yuejiu Zheng et al.
JOURNAL OF POWER SOURCES
(2018)
Article
Computer Science, Information Systems
Mahammad A. Hannan et al.
Review
Computer Science, Information Systems
Rui Xiong et al.
Article
Chemistry, Physical
Ephrem Chemali et al.
JOURNAL OF POWER SOURCES
(2018)
Review
Green & Sustainable Science & Technology
M. A. Hannan et al.
RENEWABLE & SUSTAINABLE ENERGY REVIEWS
(2017)
Article
Energy & Fuels
Cheng Lin et al.
Article
Chemistry, Physical
Xuebing Han et al.
JOURNAL OF POWER SOURCES
(2015)
Review
Multidisciplinary Sciences
Yann LeCun et al.
Article
Chemistry, Physical
Minggao Ouyang et al.
JOURNAL OF POWER SOURCES
(2014)
Article
Energy & Fuels
Yuejiu Zheng et al.
Article
Chemistry, Physical
Jiahao Li et al.
JOURNAL OF POWER SOURCES
(2013)
Article
Energy & Fuels
Hongwen He et al.
Article
Chemistry, Physical
Xiaosong Hu et al.
JOURNAL OF POWER SOURCES
(2012)
Article
Chemistry, Physical
D. Andre et al.
JOURNAL OF POWER SOURCES
(2011)
Article
Computer Science, Artificial Intelligence
Sinno Jialin Pan et al.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2010)
Article
Biochemical Research Methods
Karsten M. Borgwardt et al.
Article
Chemistry, Physical
M Anderman
JOURNAL OF POWER SOURCES
(2004)
