Hybrid Physics-Informed Neural Networks for Prognosis and Fleet Management of Li-Ion Batteries Under Large Load Variations

The growing number of electric-powered vehicles and the associated large demand for energy storage have created the need for reliable management of a fleet of Li-ion batteries over long periods of time. The aging of such batteries is mostly attributed to capacity degradation that operators desire to monitor (and potentially, slow down) to extend battery cycle life. An important tool for this purpose are prognosis models for battery state-of-charge (SOC) and state-of-health (SOH). These models are used to forecast capacity degradation and help operators to optimize their usage profiles. In addition, they are useful tools for discharge predictions and to ensure safe and reliable operation by correctly forecasting end-of-discharge (EOD). A hybrid electro-chemistry-based model fused with neural network and Gaussian processes is presented to capture the contributions of large variations in operating conditions and temperature to SOC and SOH. The goal of this approach is to create a SOC model capable of predicting battery discharge depending on a large variety of loading conditions where, apart from the current amplitude, we also leverage data from cell temperature build-up during discharge. Additionally, our model captures the aging mechanisms in the form of degradation, which relate those to the SOH in form of battery capacity; and failure prediction through a probabilistic classifier based on Gaussian processes. For model training and validation purposes, we use an accelerated battery life testing dataset, where we applied various loading conditions to battery packs. Our model predictions for SOC, SOH and battery failure show close alignment with experimental data for all loading conditions.