Related references
Note: Only part of the references are listed.
Article
Energy & Fuels
Hao Duan et al.
Summary: Artificial neural network methods have been widely applied in solving nonlinear small sample problems. This paper proposes an improved method for predicting the performance of hydrogen enriched compressed natural gas engines and demonstrates its accuracy, generalization ability, and superiority in terms of time efficiency.
Article
Engineering, Industrial
Yan Ma et al.
Summary: This paper proposes a novel SOH estimation method based on multiple health indicators fusion using transfer learning and deep belief network-long short-term memory hybrid network. It effectively improves the accurate estimation of battery health status.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2023)
Article
Automation & Control Systems
Guangcai Zhao et al.
Summary: This article proposes a novel data-driven method using generative adversarial networks to estimate the health status of lithium-ion batteries. By generating auxiliary samples and detecting anomalous aging indicators, a general model is developed and a model building rule is proposed. The experimental results show that this method outperforms other models in prediction performance.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2023)
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
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.
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
Computer Science, Information Systems
Xinming Zhang et al.
Summary: This paper proposes an improved SL-PSO algorithm, called TLS-PSO, which enhances the optimization performance of PSO through the use of three learning strategies and a hybrid learning mechanism. Experimental results demonstrate that TLS-PSO outperforms state-of-the-art PSO variants and other algorithms on complex functions and engineering problems, indicating its superior performance and potential for practical problem-solving.
INFORMATION SCIENCES
(2022)
Article
Green & Sustainable Science & Technology
Huzaifa Rauf et al.
Summary: This paper reviews the importance of designing and deploying cost-effective and high-performance electric vehicles (EVs) for decarbonization of the transportation sector. It emphasizes the significance of state-of-health (SOH) and remaining useful life (RUL) estimation in evaluating battery performance and optimizing EV efficiency. The paper also highlights the advantages of machine learning techniques in accurately estimating SOH and RUL with low computation and high accuracy, and provides applications-oriented discussions to further drive research in this field.
RENEWABLE & SUSTAINABLE ENERGY REVIEWS
(2022)
Article
Engineering, Electrical & Electronic
Lin Chen et al.
Summary: This study proposes an innovative method using hierarchical extreme learning machine (HELM) to estimate battery state-of-health (SoH) and improve estimation robustness and accuracy. The method utilizes a novel health indicator (HI) to characterize battery aging and builds a HELM model to capture the underlying correlation between the HI and capacity degradation. The results demonstrate the good generalization and reliability of the proposed method for SoH estimation in dynamic scenarios with different temperatures.
IEEE TRANSACTIONS ON TRANSPORTATION ELECTRIFICATION
(2022)
Article
Energy & Fuels
Kieran Mc Carthy et al.
Summary: This paper performs correlation analysis between equivalent circuit elements and impedance spectra of multiple commercial Li-ion polymer batteries to identify and quantify the degree of dependence, and proposes optimal impedance variables that demonstrate high dependence with state of charge (SoC), state of health (SoH) and internal temperature (IT). Knowledge of this information is of high value for developing direct impedance-based state estimation models for real-time battery management systems.
JOURNAL OF ENERGY STORAGE
(2022)
Article
Energy & Fuels
Zhansheng Ning et al.
Summary: This paper proposes a multi-scale co-estimation method for accurate estimation of state of charge (SOC) and state of health (SOH) for 48V battery system. The method includes a multi-scale estimation framework, recursive least squares for internal resistance identification, and advanced filtering algorithms for SOC and capacity estimation. The proposed method reduces computing burden and enables application on embedded BMS.
JOURNAL OF ENERGY STORAGE
(2022)
Article
Energy & Fuels
Fang Liu et al.
Summary: In this paper, a joint estimation method for the key states of batteries based on AR-ECM is proposed. The method can accurately estimate the state of health, state of charge, and state of power of batteries. By analyzing the characteristics of model parameters, a differentiated parameter identification strategy is proposed. Experimental results show that the method has high estimation accuracy and robustness.
JOURNAL OF ENERGY STORAGE
(2022)
Article
Energy & Fuels
Yan Ma et al.
Summary: This study proposes an IPSO-BPNN method to estimate SOH and predict RUL based on HIs extracted from the charging process, showing higher accuracy and validity compared to the standard BPNN method in battery health management.
JOURNAL OF ENERGY STORAGE
(2022)
Article
Energy & Fuels
Bo Jiang et al.
Summary: This study investigates a systematic comparative study of three categories of features extracted from battery electrochemical impedance spectroscopy (EIS) in state of health (SOH) estimation. Experimental results highlight that using the fixed-frequency impedance feature can realize outstanding performance in battery SOH estimation.
Article
Computer Science, Artificial Intelligence
Zewang Chen et al.
Summary: This paper proposes an online state of health estimation method for lithium-ion batteries based on bat algorithm optimized relevance vector machine (BA-RVM) with dynamic integration. The method improves estimation accuracy by performing feature extraction, establishing an integration model, continuously updating sub-model weights, and dynamically integrating sub-model outputs. It shows better generalization ability and uncertainty expression compared to other data-driven methods.
APPLIED SOFT COMPUTING
(2022)
Article
Thermodynamics
Gengfeng Liu et al.
Summary: This paper proposes a multi-feature fusion model to estimate battery state of health (SOH) by combining different feature parameters and support vector regression (SVR) with long short-term memory network (LSTM). The effectiveness of the proposed method is verified through battery aging test data set and NASA battery test data set.
Article
Thermodynamics
Dongliang Gong et al.
Summary: This paper aims to assess the applicability and prediction accuracy of an energy features-based state of health (SOH) estimation model for different lithium-ion batteries and charging/discharging scenarios. The experimental results demonstrate that the model has high prediction accuracy and excellent generalization ability.
Article
Chemistry, Physical
Bin Ma et al.
Summary: In this paper, a combination of differential thermal voltammetry (DTV) signal analysis methods and recursive neural networks data-driven methods is used to accurately predict battery degradation and estimate its state of health (SOH). By applying the Savitzky-Golay (SG) method and Pearson correlation analysis, the DTV curve is smoothed and useful feature variables are extracted, bridging signaling characteristics and phase transition characteristics. The proposed method shows promising results in predicting remaining useful life (RUL) and estimating battery SOH.
JOURNAL OF POWER SOURCES
(2022)
Article
Energy & Fuels
Barno Abdullaeva et al.
Summary: A new fractional model for lithium-ion battery is introduced in this study, and the parameters of the model are optimized using the Krill Herd optimizer. The optimized fractional-order model shows higher reliability and precision under various working conditions.
JOURNAL OF ENERGY STORAGE
(2022)
Article
Energy & Fuels
Chunyu Wang et al.
Summary: Accurate estimation of battery SOC and SOH is crucial for battery management systems. This paper proposes an advanced fusion estimation method considering temperature and aging effects, achieving precise estimation through parameter identification and adaptive filtering.
JOURNAL OF ENERGY STORAGE
(2022)
Article
Electrochemistry
Hongye Lin et al.
Summary: This paper proposes a hybrid estimation method for the state of health (SOH) of lithium-ion batteries (LIBs) based on incremental capacity (IC) curve and back-propagation neural network (BPNN). Experimental results show that the proposed method has high estimation accuracy and can be embedded in a battery management system for online estimation.
Article
Energy & Fuels
Bo Jiang et al.
Summary: This study systematically investigates and compares three categories of features extracted from battery electrochemical impedance spectroscopy (EIS) in battery state of health (SOH) estimation, showing that the fixed-frequency impedance feature performs outstandingly in battery SOH estimation.
Article
Mathematics, Applied
J. A. Tenreiro Machado et al.
Summary: This paper proposes a generalization of the PSO algorithm by incorporating complex-order derivatives to design the CoPSO algorithm, which has been shown to outperform previous algorithms in benchmark tests. Sensitivity analysis and performance validation were conducted to demonstrate the feasibility and efficiency of CoPSO.
COMMUNICATIONS IN NONLINEAR SCIENCE AND NUMERICAL SIMULATION
(2021)
Article
Energy & Fuels
Manh-Kien Tran et al.
Summary: The research found that state of health (SOH) has an impact on Thevenin ECM parameters, and it is recommended to use a new empirical model to represent this impact to improve parameter identification accuracy, with experimental validation yielding favorable results.
JOURNAL OF ENERGY STORAGE
(2021)
Article
Multidisciplinary Sciences
Xing Shu et al.
Summary: This paper explores the significance of accurate state of health (SOH) prediction for lithium-ion batteries, looking at the development of machine learning techniques in this area. It defines the concept of SOH, classifies prediction methods, surveys health feature extraction methods, conducts comparison, and discusses challenges and research directions for more reliable SOH prediction.
Article
Engineering, Electrical & Electronic
Xiaosong Hu et al.
Summary: This article conducts a comprehensive study on data-driven State of Health (SOH) estimation methods for lithium-ion batteries. A new classification for health indicators is proposed, and a combination of fusion-based selection method and Gaussian process regression (GPR) shows superior estimation performance.
IEEE TRANSACTIONS ON TRANSPORTATION ELECTRIFICATION
(2021)
Article
Energy & Fuels
Fan Luo et al.
Summary: The proposed method provides a rapid and accurate estimation of the health of retired power batteries through a mathematical model. Experimental results show that this method can save time, energy, and achieve rapid estimation of the unknown state of charge and health of the battery with a prediction error of less than 2%.
JOURNAL OF ENERGY STORAGE
(2021)
Article
Computer Science, Information Systems
Kanishkavikram Purohit et al.
Summary: The proliferation of electric vehicle technology is crucial for sustainability, with the study showing that two-layer feed-forward neural-network-based soft sensors can effectively estimate the state of charge, state of energy, and power loss of EV battery packs with high accuracy.
APPLIED SYSTEM INNOVATION
(2021)
Article
Automation & Control Systems
Farshid Naseri et al.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2020)
Article
Chemistry, Physical
Kai He et al.
INTERNATIONAL JOURNAL OF HYDROGEN ENERGY
(2020)
Article
Energy & Fuels
Yaxiang Fan et al.
JOURNAL OF ENERGY STORAGE
(2020)
Article
Energy & Fuels
Ran Tu et al.
Article
Energy & Fuels
Yuanyuan Li et al.
Article
Chemistry, Physical
Yuanyuan Liu et al.
Article
Electrochemistry
Xin Lai et al.
ELECTROCHIMICA ACTA
(2019)
Article
Chemistry, Physical
Xiaopeng Tang et al.
JOURNAL OF POWER SOURCES
(2018)
Article
Mathematical & Computational Biology
Chunhui Bao et al.
COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE
(2018)
Article
Engineering, Electrical & Electronic
Xiaosong Hu et al.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2018)
Article
Thermodynamics
Guangzhong Dong et al.
Article
Computer Science, Information Systems
Ran Cheng et al.
INFORMATION SCIENCES
(2015)
Article
Engineering, Electrical & Electronic
Yinjiao Xing et al.
MICROELECTRONICS RELIABILITY
(2013)