Predicting Li-ion Battery Cycle Life with LSTM RNN
This work addresses the need for reliable and safe battery usage, but it is incremental as it applies an existing LSTM method to battery data.
The paper tackles the problem of predicting lithium-ion battery cycle life by training an LSTM RNN model on sequential discharge capacity data from early cycles, achieving promising prediction accuracy on test sets of around 80 samples.
Efficient and accurate remaining useful life prediction is a key factor for reliable and safe usage of lithium-ion batteries. This work trains a long short-term memory recurrent neural network model to learn from sequential data of discharge capacities at various cycles and voltages and to work as a cycle life predictor for battery cells cycled under different conditions. Using experimental data of first 60 - 80 cycles, our model achieves promising prediction accuracy on test sets of around 80 samples.