State of charge estimation of lithium-ion batteries using hybrid autoencoder and Long Short Term Memory neural networks

The state of charge (SOC) of a battery indicates its useable capacity. In the case of lithium-ion batteries, an accurate estimate improves their performance. With the recent tendency in the increased use of lithium-ion batteries in electric vehicles, the estimation of SOC has become even a more critical issue than before. In this paper, the combination of an Autoencoder neural network and a Long Short-Term Memory (LSTM) neural network is proposed for the estimation of the SOC of a battery with high precision. The Dynamic Stress Test (DST) drive cycle and the Federal Urban Driving Schedule (FUDS) drive cycle datasets are used to test the proposed algorithm at three different temperatures. To reveal the performance of the proposed method, the results are compared with several other methods from the literature. It is observed that the SOC estimation by the proposed method yields to a significantly better accuracy at all three temperatures.