Comparative Study of Machine Learning Methods for State of Health Estimation of Maritime Battery Systems

Abstract

This paper tests two data-driven approaches for predicting the state of health (SOH) of lithium-ion-batteries (LIBs) for the purpose of monitoring maritime battery systems. First, non-sequential approaches are investigated and various models are tested: ridge, lasso, support vector regression, and gradient boosted trees. Binning is proposed for feature engineering for these types of models to capture the temporal structure in the data. Such binning creates histograms for the accumulated time the LIB has been within various voltage, temperature, and current ranges. Further binning to combine these histograms into 2D or 3D histograms is explored in order to capture relationships between voltage, temperature, and current. Second, a sequential approach is explored where different deep learning architectures are tried out: long short-term memory, transformer, and temporal convolutional network. Finally, the various models and the two approaches are compared in terms of their SOH prediction ability. Results indicate that the binning with ridge regression models performed best. The same publicly available sensor data from laboratory cycling tests are used for both approaches.