Bayesian hierarchical modelling for battery lifetime early prediction

TL;DR

This paper introduces a hierarchical Bayesian linear model that predicts battery lifetime early in the cycle life using initial cell features and population data, significantly improving prediction accuracy over non-hierarchical models.

Contribution

The novel hierarchical Bayesian approach effectively combines individual and population features for early battery life prediction, addressing variability and limited data challenges.

Findings

Predicts battery end of life with 3.2 days RMSE

Achieves 8.6% mean absolute percentage error

Outperforms baseline models by 12-13%

Abstract

Accurate prediction of battery health is essential for real-world system management and lab-based experiment design. However, building a life-prediction model from different cycling conditions is still a challenge. Large lifetime variability results from both cycling conditions and initial manufacturing variability, and this -- along with the limited experimental resources usually available for each cycling condition -- makes data-driven lifetime prediction challenging. Here, a hierarchical Bayesian linear model is proposed for battery life prediction, combining both individual cell features (reflecting manufacturing variability) with population-wide features (reflecting the impact of cycling conditions on the population average). The individual features were collected from the first 100 cycles of data, which is around 5-10% of lifetime. The model is able to predict end of life with a root mean square error of 3.2 days and mean absolute percentage error of 8.6%, measured through 5-fold cross-validation, overperforming the baseline (non-hierarchical) model by around 12-13%.