Data Science-based Techniques for Modelling and Diagnostics of Battery Cells Based on End-of-Life criteria

This research work focuses on implementing Data Science techniques for Battery Energy Storage Systems (BESSs) according to Health and Charge indicators based on End-of-Life (EOL) criteria. A simple Equivalent Circuit Model (ECM) is implemented to illustrate the behavior of a battery cell in parallel with numerical methods. Density-based spatial clustering of Applications with Noise (DBSCAN), Ordering Points to identify the Clustering Structure (OPTICS), and Local Outlier Factor (LOF) are the Unsupervised techniques implemented for anomaly detection, while Multi-Layer Perceptron (MLP), Long-Short Term Memory (LSTM), and Gated Recurrent Unit (GRU) are the Supervised algorithms executed for diagnostics. Similar results are obtained in the outlier analysis, additionally, Supervised algorithms show a high level of performance and provide a basis for determining the capacity of the battery based on the End-of-Life criteria (EOL) of a Battery Energy Storage System (BESS).