Battery health prediction under generalized conditions using a Gaussian process transition model

TL;DR

This paper introduces a Gaussian process-based model for predicting battery health that effectively handles diverse usage conditions and input variables, providing accurate capacity forecasts with uncertainty estimates.

Contribution

It presents a novel Bayesian non-parametric approach that incorporates arbitrary operational inputs and feature selection for generalized battery health prediction.

Findings

Accurately predicts non-linear capacity fade with 4.3% RMSE.

Effectively models diverse usage scenarios using Gaussian process regression.

Provides reliable uncertainty estimates for capacity predictions.

Abstract

Accurately predicting the future health of batteries is necessary to ensure reliable operation, minimise maintenance costs, and calculate the value of energy storage investments. The complex nature of degradation renders data-driven approaches a promising alternative to mechanistic modelling. This study predicts the changes in battery capacity over time using a Bayesian non-parametric approach based on Gaussian process regression. These changes can be integrated against an arbitrary input sequence to predict capacity fade in a variety of usage scenarios, forming a generalised health model. The approach naturally incorporates varying current, voltage and temperature inputs, crucial for enabling real world application. A key innovation is the feature selection step, where arbitrary length current, voltage and temperature measurement vectors are mapped to fixed size feature vectors, enabling them to be efficiently used as exogenous variables. The approach is demonstrated on the open-source NASA Randomised Battery Usage Dataset, with data of 26 cells aged under randomized operational conditions. Using half of the cells for training, and half for validation, the method is shown to accurately predict non-linear capacity fade, with a best case normalised root mean square error of 4.3%, including accurate estimation of prediction uncertainty.