Practical Battery Health Monitoring using Uncertainty-Aware Bayesian Neural Network

TL;DR

This paper presents a Bayesian neural network approach for battery health prediction that accounts for uncertainty, improving prediction accuracy and providing quantifiable confidence levels, thus enhancing practical deployment in industry.

Contribution

The study introduces a Bayesian neural network model that captures uncertainty in battery health prediction, addressing practical deployment issues neglected by prior accuracy-focused research.

Findings

Prediction error rate averaged 13.9%

Uncertainty quantification improved by 66% during battery lifespan

Prediction error as low as 2.9% for certain batteries

Abstract

Battery health monitoring and prediction are critically important in the era of electric mobility with a huge impact on safety, sustainability, and economic aspects. Existing research often focuses on prediction accuracy but tends to neglect practical factors that may hinder the technology's deployment in real-world applications. In this paper, we address these practical considerations and develop models based on the Bayesian neural network for predicting battery end-of-life. Our models use sensor data related to battery health and apply distributions, rather than single-point, for each parameter of the models. This allows the models to capture the inherent randomness and uncertainty of battery health, which leads to not only accurate predictions but also quantifiable uncertainty. We conducted an experimental study and demonstrated the effectiveness of our proposed models, with a prediction error rate averaging 13.9%, and as low as 2.9% for certain tested batteries. Additionally, all predictions include quantifiable certainty, which improved by 66% from the initial to the mid-life stage of the battery. This research has practical values for battery technologies and contributes to accelerating the technology adoption in the industry.