Optimizing Cycle Life Prediction of Lithium-ion Batteries via a Physics-Informed Model

TL;DR

This paper presents a hybrid physics-informed machine learning model that predicts the full capacity loss curve of lithium-ion batteries from early data, enhancing robustness and interpretability over traditional cycle life models.

Contribution

It introduces a novel combination of physics-based equations with a self-attention neural network to predict complete capacity loss curves, not just cycle life.

Findings

Model achieves performance comparable to existing methods.

Predicts entire capacity loss curves, not just cycle life.

Provides robustness and physical interpretability.

Abstract

Accurately measuring the cycle lifetime of commercial lithium-ion batteries is crucial for performance and technology development. We introduce a novel hybrid approach combining a physics-based equation with a self-attention model to predict the cycle lifetimes of commercial lithium iron phosphate graphite cells via early-cycle data. After fitting capacity loss curves to this physics-based equation, we then use a self-attention layer to reconstruct entire battery capacity loss curves. Our model exhibits comparable performances to existing models while predicting more information: the entire capacity loss curve instead of cycle life. This provides more robustness and interpretability: our model does not need to be retrained for a different notion of end-of-life and is backed by physical intuition.