On The Use of Machine Learning Methods For EV Battery Pack Data Forecast Applied To Reconstructed Dynamic Profiles

Lithium-ion batteries play a key role in electric vehicles, so it is essential to continuously monitor and control their health. However, since today's battery packs are composed of hundreds or thousands of cells, monitoring them all continuously is challenging. Additionally, the performance of the entire battery pack is often limited by the weakest cell. Therefore, developing effective monitoring techniques to reliably forecast the remaining time to depletion (RTD) of lithium-ion battery cells is essential for safe and efficient battery management. However, even in robust systems, this data can be lost due to electromagnetic interference, microcontroller malfunction, failed contacts, and other issues. Gaps in voltage measurements compromise the accuracy of data-driven forecasts. This work systematically evaluates how different voltage reconstruction methods affect the performance of recurrent neural network (RNN) forecasters that are trained to predict RTD through quantile regression. The paper uses experimental battery pack data based on the behavior of an electric vehicle under dynamic driving conditions. Artificial gaps of 500 seconds were introduced at the beginning, middle, and end of each discharge phase, resulting in over 4300 reconstruction cases. Four reconstruction strategies were considered: a zero-order hold (ZOH), an autoregressive integrated moving average (ARIMA) model, a gated recurrent unit (GRU) model, and a hybrid unscented Kalman filter (UKF) model. The reconstructed signals were fed into LSTM and GRU RNNs to estimate RTD, which produced confidence intervals and median values for decision-making purposes.