Machine learning systems applied in satellite lithium-ion battery set impedance estimation

In this work, the internal impedance of the lithium-ion battery pack, an essential measure of the degradation level of the batteries, is estimated employing ensembles of machine learning models. In this study, we take the supervised learning techniques Multi-Layer Perceptron bagging neural network and gradient tree boosting into account. Characteristics of the electric power system, in which the battery pack is inserted, are extracted and used in the modeling and training phases. During this process, the architecture of the ensembles and the configuration of their base learners are tuned through validation iterations. Finally, with the application of statistical testing and similarity analysis techniques, the best ensembles of models are examined and compared to other methods found in the literature. Results indicate that our approach is a suitable manner to estimate the internal impedance of batteries.