A combined state-of-charge estimation method for lithium-ion battery using an improved BGRU network and UKF

Cui, Zhenhua; Kang, Le; Li, Liwei; Wang, Licheng; Wang, Kai

doi:10.1016/j.energy.2022.124933

Cited by 131 publications

(34 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is because the IUM mechanism enables the model to fit the local variation of SOH well. In addition, the Ellman and LSTM models can still estimate the overall trend of SOH, which proves the effectiveness of the proposed features [56].…”

Section: High-temperature and Low-temperature Validationmentioning

confidence: 57%

Online estimation of SOH for lithium-ion battery based on SSA-Elman neural network

Guo

Yang

Zhang

et al. 2022

Prot Control Mod Power Syst

114

View full text Add to dashboard Cite

The estimation of state of health (SOH) of a lithium-ion battery (LIB) is of great significance to system safety and economic development. This paper proposes a SOH estimation method based on the SSA-Elman model for the first time. To improve the correlation rates between features and battery capacity, a method combining median absolute deviation filtering and Savitzky–Golay filtering is proposed to process the data. Based on the aging characteristics of the LIB, five features with correlation rates above 0.99 after data processing are then proposed. Addressing the defects of the Elman model, the sparrow search algorithm (SSA) is used to optimize the network parameters. In addition, a data incremental update mechanism is added to improve the generalization of the SSA-Elman model. Finally, the performance of the proposed model is verified based on NASA dataset, and the outputs of the Elman, LSTM and SSA-Elman models are compared. The results show that the proposed method can accurately estimate the SOH, with the root mean square error (RMSE) being as low as 0.0024 and the mean absolute percentage error (MAPE) being as low as 0.25%. In addition, RMSE does not exceed 0.0224 and MAPE does not exceed 2.21% in high temperature and low temperature verifications.

show abstract

Section: High-temperature and Low-temperature Validationmentioning

confidence: 57%

Online estimation of SOH for lithium-ion battery based on SSA-Elman neural network

Guo

Yang

Zhang

et al. 2022

Prot Control Mod Power Syst

114

View full text Add to dashboard Cite

show abstract

“…Therefore, the development of new computing methods for future materials and equipment based on artificial intelligence (AI) will solve this problem. At present, there are performance predictions for lithium batteries and supercapacitors based on AI calculation methods, but there is less research on performance prediction for air filter [189] , [190] , [191] , [192] .…”

Section: Discussionmentioning

confidence: 99%

High-performance multifunctional electrospun fibrous air filter for personal protection: A review

Shao

Chen²,

Wang³

et al. 2022

Separation and Purification Technology

View full text Add to dashboard Cite

“…4. New computational methodologies based on artificial intelligence (AI) and its associated branches need significant attention for their application in self-powered sensors . The challenges associated in device design, output prediction, and device optimization can be addressed using AI or its associated branches.…”

Section: Summary and Future Perspectivesmentioning

confidence: 99%

Triboelectric Nanogenerators as Power Sources for Chemical Sensors and Biosensors

2022

View full text Add to dashboard Cite

The recent advances of portable sensors in flexible and wearable form factors are drawing increasing attention worldwide owing to their requirement applications ranging from health monitoring to environment monitoring. While portability is critical for these applications, real-time data gathering also requires a reliable power supply�which is largely met with batteries. Besides the need for regular charging, the use of toxic chemicals in batteries makes it difficult to rely on them, and as a result different types of energy harvesters have been explored in recent years. Among these, triboelectric nanogenerators (TENGs) provide a promising platform for harnessing ambient energy and converting it into usable electric signals. The ease of fabrication and possibility to develop TENGs with a diverse range of easily available materials also make them attractive. This review focuses on the TENG technology and its efficient use as a power source for various types of chemical sensors and biosensors. The paper describes the underlying mechanism, various modes of working of TENGs, and representative examples of their utilization as power sources for sensing a multitude of analytes. The challenges associated with their adoption for commercial solutions are also discussed to stimulate further advances and innovations.

show abstract

A combined state-of-charge estimation method for lithium-ion battery using an improved BGRU network and UKF

Cited by 131 publications

References 42 publications

Online estimation of SOH for lithium-ion battery based on SSA-Elman neural network

Online estimation of SOH for lithium-ion battery based on SSA-Elman neural network

High-performance multifunctional electrospun fibrous air filter for personal protection: A review

Triboelectric Nanogenerators as Power Sources for Chemical Sensors and Biosensors

Contact Info

Product

Resources

About