Remaining useful life Prediction for lithium-ion battery based on CEEMDAN and SVR

Shi, Yuanhao; Yang, Yanru; Wen, Jinyu; Cui, Fangshu; Wang, Jingcheng

doi:10.1109/indin45582.2020.9442125

Cited by 10 publications

(5 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the prediction phase of the RUL of lithium-ion batteries, B0005, B0006, B0007 and B0018 batteries of NASA and CS2_33, CS2_34, CS2_35, CS2_36, CS2_37 and CS2_38 of CALCE dataset are used to train and test several related algorithm models. In this experiment, in order to experience the performance of the CS-VMD-GRU combined model, five models of LSTM, EMD-LSTM, CEEMDAN-LSTM [14], VMD-LSTM and VMD-Bi-LSTM were selected for comparison and explanation.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Remaining Useful Life Prediction for Lithium-Ion Batteries Based on CS-VMD and GRU

2022

View full text Add to dashboard Cite

Accurate prediction the remaining useful life (RUL) and estimation the state of health (SOH) are critical to the management of lithium-ion batteries. In this paper, a lithium battery capacity prediction method based on cuckoo search optimization variational mode decomposition (CS-VMD) and gated recurrent unit (GRU) is proposed. Firstly, the VMD algorithm is used to divide the capacity into some intrinsic mode functions (IMFs) to reduce the impact of capacity regeneration and other situations. The number of decomposition layers and the quadratic penalty factor of VMD are optimized by the cuckoo search (CS) algorithm. Then, the GRU network is introduced to capture small changes in the capacity degradation process and perform the capacity prediction of decomposed sequence. Finally, some prediction results are integrated effectively. Based on two publicly available lithium-ion battery datasets, the model proposed in this paper can significantly reduce the complexity of the sequence and have high prediction accuracy, which is better than other prediction models. The root mean square error (RMSE) is controlled within 2%, and the maximum mean absolute error (MAE) does not exceed 2%.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Xiang et al [13] proposed an improved ensemble empirical mode decomposition (EEMD) and Gaussian regression process for RUL prediction. At the same time, the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) has also been used to reduce the complexity of battery capacity sequences [14], [15].…”

Section: Introductionmentioning

confidence: 99%

Remaining Useful Life Prediction for Lithium-Ion Batteries Based on CS-VMD and GRU

2022

View full text Add to dashboard Cite

show abstract

“…For the generalization experiment, we utilized four groups of battery datasets (CS2 series) from the center for advanced life cycle engineering (CALCE) at the University of Maryland. 37 All four batteries in this dataset have a cathode material of lithium cobalt oxide (LiCoO2) with an initial capacity of 1100 mAh. Charging was carried out with a constant current of 0.5 C until the voltage reached 4.2 V, followed by a constant voltage charge at 4.2 V until the charging current dropped to 0.05 A. Discharging was performed with a constant current of 1 C until the voltage reached 2.7 V, at which point the discharge was terminated.…”

Section: Model Generalization Experimentsmentioning

confidence: 99%

Estimation of SOH of Lithium-Ion Batteries Based on PSO-Bi GRU-Attention Network

Hou,

Xu,

Jia

et al. 2024

J. Electrochem. Soc.

View full text Add to dashboard Cite

The state of health (SOH) of lithium-ion batteries is a critical parameter that characterizes their actual lifespan, and its accurate assessment ensures the safe and reliable operation of batteries. However, in practical applications, SOH cannot be directly measured. To further improve the accuracy of SOH estimation for lithium-ion batteries, this study employs the particle swarm optimization (PSO) algorithm to search for the optimal parameters of the bidirectional gated recurrent unit (Bi GRU) neural network, enabling the prediction of time series information. Additionally, attention mechanism is integrated to allocate weights to the prediction results, resulting in the SOH prediction for lithium-ion batteries. The proposed model is validated using the B0005 battery from the NASA lithium battery dataset. Experimental results demonstrate that, compared to the Bi GRU-Attention and Bi GRU models, the proposed model reduces the root mean square error by 52.34% and 66.88%, respectively.

show abstract

“…The cells may be almost new and even with low internal resistance. Usually the retaining capacity is more than a half of the initial capacity declared by the manufacturer [24]. The loss in capacity can be compensated by increasing the number of cells in parallel to allow high current load.…”

Section: Proposed Steps Of Choice and Reproducible Reuse Of Li-ion La...mentioning

confidence: 99%

Method of creation of power sources for home appliances under constraints of limited resources

Perepelitsyn

Tetskyi

2023

reks

View full text Add to dashboard Cite

The subject of study in this article is the voltage ranges, methods, and tools for prototyping independent sources of power supply and artificial lighting for home appliances with reuse of only widespread components. The goal is to improve the efficiency of the creation and use of independent power supply sources for home appliances. Task: to analyze the history of the development of voltage standards for households; analyze existing autonomous power sources and types of batteries; analyze different loads; find rational voltage ranges based on fundamental values; analyze charge control and balancing circuits for lithium-based batteries; propose the technique of prototyping independent sources of power supply based on reused lithium-ion (Li-ion) accumulators; provide an example of the practical application of the results of research. According to the tasks, the following results were obtained. The evolution of voltage standards of electrical supply networks is analyzed. Types of autonomous power supplies, including pure sine versions, are discussed. The analysis of batteries for autonomous power sources of different chemical compositions is performed. It is proposed to use the water analogy of current and area as an analogy of battery capacity for visual representation of electrical processes. Models of constant current consumption and constant power consumption are considered. It is proposed to reduce the internal resistance of the battery assembly by parallel connection of the reused lithium-ion accumulators. Correspondence of voltage ranges of sequential connection of lithium-ion cells to ensure compatibility with existing devices is investigated. Rational parameters of voltage ranges to ensure compatibility of lithium-ion and acid accumulators with the ability to charge directly from solar panels without a charge controller are found. Charge controllers, battery management systems (BMS), and battery balancing circuits are analyzed. A set of steps for reuse of lithium-ion accumulators for the creation of autonomous power sources is proposed. Conclusions. The main contribution of this research is the proposed method of creation of power supply and interior lighting based on the reuse of accumulators without additional components. The discovered and proposed magic numbers of 3, 5, 7, 9, 11 and 13 for series connection of lithium-ion cells allows to obtain the equivalent of standard voltage ranges of 12 V, 19 V, 27 V, 36 V, 42 V and 48 V. The proposed technique of adjusting the voltage of the passive balancer allows adding 4.5 % to the capacity of the battery assembly. The described solutions allow to build the completely scalable autonomous low-voltage electrical supply network with the ability to charge directly from solar panels without expensive charge controllers.

show abstract

Remaining useful life Prediction for lithium-ion battery based on CEEMDAN and SVR

Cited by 10 publications

References 17 publications

Remaining Useful Life Prediction for Lithium-Ion Batteries Based on CS-VMD and GRU

Remaining Useful Life Prediction for Lithium-Ion Batteries Based on CS-VMD and GRU

Estimation of SOH of Lithium-Ion Batteries Based on PSO-Bi GRU-Attention Network

Method of creation of power sources for home appliances under constraints of limited resources

Contact Info

Product

Resources

About