Hybrid deep learning for estimation of state-of-health in lithium-ion batteries

Abstract

Lithium-ion (li-ion) batteries have a high energy density and a long cycle life. Lithium-ion batteries have a finite lifespan, and their energy storage capacity diminishes with use. In order to properly plan battery maintenance, the state of health (SoH) of lithium-ion batteries is crucial. This study aims to combine two deep learning techniques (hybrid deep learning), namely convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM), for SoH estimation in li-ion batteries. This study contrasts hybrid deep learning methods to single deep learning models so that the most suitable model for accurately measuring the SoH in lithium-ion batteries can be determined. In comparison to other methodologies, CNN-BiLSTM yields the best results. The CNN-BiLSTM algorithm yields RMSE, mean square error (MSE), mean absolute error (MAE), and mean absolute percentage error (MAPE) in the following order: 0.00916, 0.000084, 0.0048, and 0.00603. This indicates that CNN-BiLSTM, as a hybrid deep learning model, is able to calculate the approximate capacity of the lithium-ion battery more accurately than other methods.