Tensorflow-based Long-Short term Memory Network for SOH Prediction of a Lithium-ion Cell

Authors:

Abstract
Lithium-ion battery is energy storage devices that are currently used in many popular applications. It is necessary to predict the aging of lithium-ion single cell that constitutes a mass storage device to prevent failure or explosion. In order to predict SOH, a factors that affect the aging state of the battery can be selected as a characteristic parameter. The selected characteristic parameter is composed of the input of the Neural Network for predicting the SOH. Through the preliminary experiments, the variation of SOH of the lithium-ion battery according to the cycle was confirmed, and it can be divided in to the training data sets and prediction data sets. The training of the Neural Network was performed with the training data sets, and the SOH predicted through the Neural Network was compared with the actual data.