Deep learning enabled state of charge, state of health and remaining useful life estimation for smart battery management system: Methods, implementations, issues and prospects

Lipu, Molla Shahadat Hossain; Ansari, Shaheer; Miah, Md. Sazal; Meraj, Sheikh Tanzim; Hasan, Kamrul; Shihavuddin, A.S.M.; Hannan, M. A.; Muttaqi, Kashem M.; Hussain, Aini

doi:10.1016/j.est.2022.105752

Cited by 59 publications

(21 citation statements)

References 111 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The new indicator KPP not only provides an auxiliary indicator for predicting the occurrence of knee point, but it can improve the accuracy of SOH nonlinear prediction. Hossain Lipu [70] introduced an assessment process for SOC, SOH, and remaining useful life (RUL) based on deep learning, as depicted in figure 9. Non-recursive algorithms like support vector regression (SVR) [71], backpropagation neural networks (BPNN) [72], extreme learning machine (ELM) [73], multi-layer perceptrons (MLP) [74], and others have been applied to estimate battery health.…”

Section: Modeling Of Integrated Internal and External Factorsmentioning

confidence: 99%

Advances in performance degradation mechanism and safety assessment of LiFePO₄ for energy storage

Xiao,

Chen,

Zhao

et al. 2024

Nanotechnology

View full text Add to dashboard Cite

In the context of "energy shortage", developing a novel energy-based power system is essential for advancing the current power system towards low-carbon solutions. As the usage duration of lithium-ion batteries for energy storage increases, the nonlinear changes in their aging process pose challenges to accurately assess their performance. This paper focuses on the study LiFeO4(LFP), used for energy storage, and explores their performance degradation mechanisms. Furthermore, it introduces common battery models and data structures & algorithms, which used for predicting the correlation between electrode materials and physical parameters, applying to SOH assessment and thermal warning. This paper also discusses the establishment of digital management system. Compared to conventional battery networks, dynamically reconfigurable battery networks can realize real-time monitoring of lithium-ion batteries, and reduce the probability of fault occurrence to an acceptably low level.

show abstract

Section: Modeling Of Integrated Internal and External Factorsmentioning

confidence: 99%

Advances in performance degradation mechanism and safety assessment of LiFePO₄ for energy storage

Xiao,

Chen,

Zhao

et al. 2024

Nanotechnology

View full text Add to dashboard Cite

show abstract

“…64 The hybrid method can adaptively adjust according to the needs of different application scenarios, thereby further improving the accuracy and reliability of SOC estimation. 65 Figure 1. Neural network model.…”

Section: Soc Socmentioning

confidence: 99%

Review—Optimized Particle Filtering Strategies for High-Accuracy State of Charge Estimation of LIBs

Wang¹,

Jia²,

Takyi‐Aninakwa³

et al. 2023

J. Electrochem. Soc.

View full text Add to dashboard Cite

Lithium-ion batteries (LIBs) are used as energy storage systems due to their high efficiency. State of charge (SOC) estimation is one of the key functions of the battery management system (BMS). Accurate SOC estimation helps to determine the driving range and effective energy management of electric vehicles (EVs). However, due to complex electrochemical reactions and nonlinear battery characteristics, accurate SOC estimation is challenging. Therefore, this review examines the existing methods for estimating the SOC of LIBs and analyzes their respective advantages and disadvantages. Subsequently, a systematic and comprehensive analysis of the methods for constructing LIB models is conducted from various aspects such as applicability and accuracy. Finally, the advantages of particle filtering (PF) over the Kalman filter (KF) series algorithm for estimating SOC are summarized, and various improved PF algorithms for estimating the SOC of LIBs are compared and discussed. Additionally, this review provides corresponding suggestions for researchers in the battery field.

show abstract

“…The nonlinear system is linearized by using Taylor series expansion and ignoring higher-order terms to obtain a new state transition matrix and observation-driven matrix to update the linear space equation. The recursion of the EKF algorithm is shown in Equation (6).…”

Section: Sreksmentioning

confidence: 99%

“…4 In BMS function management, the reliability analysis of the battery's state of charge (SOC), state of energy (SOE), state of health (SOH), state of power (SOP), state of temperature (SOT), state of safety (SOS), residual service life (RUL), and residual discharge time (RDT) is a prerequisite for the management of battery charge-discharge efficiency, safety management, thermal management and health. 5,6 Accurate and effective estimation of SOC and SOE is the basis of the battery management system and also the key to the estimation of battery remaining capacity. SOC stands for the state of the battery's remaining charge, and SOE stands for the state of the battery's remaining energy.…”

Section: Introductionmentioning

confidence: 99%

An improved long short‐term memory based on global optimization square root extended Kalman smoothing algorithm for collaborative state of charge and state of energy estimation of lithium‐ion batteries

Wang

Cao

et al. 2023

Circuit Theory & Apps

View full text Add to dashboard Cite

SummaryState of charge and state of energy are essential performance indicators of the battery management system and the key to reflecting the remaining capacity of batteries. Aiming at the problems of low precision, long time, and strongly nonlinear system estimation of state of charge and state of energy of lithium‐ion batteries based on traditional algorithm under complex working conditions, this paper proposes a hybrid method consisting of the long short‐term memory neural network and square root extended Kalman smoothing. The long short‐term memory neural network can enhance the memory ability of the previous time data. The sliding window technology is introduced into the network to improve the correlation between the last time and the subsequent time estimation. Based on the traditional Kalman filtering algorithm, the square root and reverse smoothing algorithms are introduced to solve the risk of the negative covariance matrix and the problems of slow convergence and significant estimation deviation caused by a strongly nonlinear system. According to experiments, under the hybrid pulse power characterization working condition at 25°C, the maximum absolute errors of state of charge and state of energy are 1.779% and 1.487%, and the mean absolute errors are 0.352% and 0.894%, respectively. Under the Beijing bus dynamic stress test working condition at 25°C, the maximum absolute errors of state of charge and state of energy are 2.703% and 2.369%, and the mean absolute errors are 0.462% and 0.621%, respectively. The experimental results show that this algorithm can obtain reliable state of charge and state of energy under different complex working conditions with high accuracy, convergence, and robustness.

show abstract

Deep learning enabled state of charge, state of health and remaining useful life estimation for smart battery management system: Methods, implementations, issues and prospects

Cited by 59 publications

References 111 publications

Advances in performance degradation mechanism and safety assessment of LiFePO₄ for energy storage

Advances in performance degradation mechanism and safety assessment of LiFePO₄ for energy storage

Review—Optimized Particle Filtering Strategies for High-Accuracy State of Charge Estimation of LIBs

An improved long short‐term memory based on global optimization square root extended Kalman smoothing algorithm for collaborative state of charge and state of energy estimation of lithium‐ion batteries

Contact Info

Product

Resources

About

Deep learning enabled state of charge, state of health and remaining useful life estimation for smart battery management system: Methods, implementations, issues and prospects

Cited by 59 publications

References 111 publications

Advances in performance degradation mechanism and safety assessment of LiFePO4 for energy storage

Advances in performance degradation mechanism and safety assessment of LiFePO4 for energy storage

Review—Optimized Particle Filtering Strategies for High-Accuracy State of Charge Estimation of LIBs

An improved long short‐term memory based on global optimization square root extended Kalman smoothing algorithm for collaborative state of charge and state of energy estimation of lithium‐ion batteries

Contact Info

Product

Resources

About

Advances in performance degradation mechanism and safety assessment of LiFePO₄ for energy storage

Advances in performance degradation mechanism and safety assessment of LiFePO₄ for energy storage