Batteries, Vol. seven, Pages 66: Attention-Based Long Short-Term Memory Recurrent Nerve organs Network for Capacity Wreckage of Lithium-Ion Batteries
Batteries doi: 10. 3390/batteries7040066
Writers: Tadele Mamo Fu-Kwun Wang
Monitoring cycle existence can provide a prediction from the remaining battery lifetime. To improve the prediction accuracy of lithium-ion electric battery capacity degradation, we offer a hybrid long immediate memory recurrent neural network model with an interest mechanism. The hyper-parameters of the proposed model are also optimized by a differential evolution algorithm. Using open public battery datasets, the suggested model is compared in order to some published models, and it gives better prediction performance in terms associated with mean absolute percentage mistake and root mean square error. In addition , the proposed model can achieve higher conjecture accuracy of battery finish of life.
