Comparing deep learning methods to predict the remaining useful life of lithium-ion batteries

Zraibi, Brahim; Mansouri, Mohamed; Loukili, Salah Eddine

doi:10.1016/j.matpr.2022.04.082

Cited by 9 publications

(2 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Two RNN variations, LSTM and GRU, are utilized to regulate the propagation of gradient information and remember the parameters as successive inputs during the long-term sequence in order to solve this problem. [13].…”

Section: Cnn-bgru-dnn Architecturementioning

confidence: 99%

“…The equivalent circuit model [11], electrochemical model, data-driven model, and hybrid method ASTESJ ISSN: 2415-6698 model are the four primary models that have been used in recent decades to perform substantial research on RUL estimate and SOH prediction of lithium batteries. The approach of the data model is receiving increasing amounts of attention as a result of the growth in lithium battery data [12], [13].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Hybrid Neural Network Method for Predicting the SOH and RUL of Lithium-Ion Batteries

Zraibi¹,

Mansouri²,

Loukili³

et al. 2022

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

The use of a battery to power an electrical or electronic system is accompanied by battery management, i.e. a set of measures intended to preserve it for preventative maintenance, thus the cost reduction. This management is generally based on two key parameters, the (remaining useful life) RUL and the (State-of-health) SOH, which relate respectively to the charge output and the aging of the Lithium-ion battery. The issue will be resolved and advances in production, battery utilization, and optimization will be made possible by accurate SOH determination and dependable RUL prediction. The CNN-BGRU-DNN hybrid strategy, which we suggest in this study, integrates Convolutional Neural Networks (CNN), Bidirectional Gated Recurrent Units (BGRU), and Deep Neural Networks (DNN) to increase the precision of SOH and RUL estimates for Lithium-ion batteries. To that purpose, the performance of the prediction findings is assessed using the MAE, RMSE, AE, and RE as well as the NASA datasets of lithium-ion batteries for experimental validation. The verification tests' findings show that, in comparison to existing approaches in the literature, the suggested method may greatly reduce prediction error and achieve high estimation accuracy of the battery's state of health.

show abstract

Section: Cnn-bgru-dnn Architecturementioning

confidence: 99%