Machine learning pipeline for battery state of health estimation

TL;DR

This paper presents a machine learning pipeline that accurately estimates battery health in real-time using experimental data, feature engineering, and confidence intervals, applicable to various battery conditions.

Contribution

The study introduces a scalable machine learning pipeline for battery SOH estimation that combines feature selection, calibration, and confidence bounds, validated on 179 cells under different cycling conditions.

Findings

Achieved 0.45% RMSE in SOH estimation for fast-charging cells.

Engineered 30 features from charge curves for model input.

Pipeline generalizes to other components requiring real-time health estimation.

Abstract

Lithium-ion batteries are ubiquitous in modern day applications ranging from portable electronics to electric vehicles. Irrespective of the application, reliable real-time estimation of battery state of health (SOH) by on-board computers is crucial to the safe operation of the battery, ultimately safeguarding asset integrity. In this paper, we design and evaluate a machine learning pipeline for estimation of battery capacity fade - a metric of battery health - on 179 cells cycled under various conditions. The pipeline estimates battery SOH with an associated confidence interval by using two parametric and two non-parametric algorithms. Using segments of charge voltage and current curves, the pipeline engineers 30 features, performs automatic feature selection and calibrates the algorithms. When deployed on cells operated under the fast-charging protocol, the best model achieves a root mean squared percent error of 0.45\%. This work provides insights into the design of scalable data-driven models for battery SOH estimation, emphasising the value of confidence bounds around the prediction. The pipeline methodology combines experimental data with machine learning modelling and can be generalized to other critical components that require real-time estimation of SOH.