No abstract

The prediction lifetime of a Lithium-ion battery is able to be utilized as an early warning system to prevent the battery’s failure that makes it very significant for assuring safety and reliability. This paper represents a benchmark study that compares its RUL prediction results of single and hybrid methods with similar articles. We suggest a hybrid method, named the CNN-LSTM, which is a combination of Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM), for predicting and improving the accuracy of the remaining useful life (RUL) of Lithium-ion battery. We selected three statistical indicators (MAE, R², and RMSE) to assess the results of performance prediction. Experimental validation is performed using the lithium-ion battery dataset from the NASA and results reveal that the effectiveness of the suggested hybrid method in reducing the prediction error and in achieving better RUL prediction performance compared to the other algorithms.

No abstract

No abstract

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.